Sato Hub: Build Onchain & Crypto Agents

USE WHEN you need to look up crypto-agent tooling (frameworks, MCP servers, wallets, payment rails, data tools) by name, chain, standard or what it does, or check that a specific project exists and is maintained. A daily-rebuilt directory, each entry scored from public evidence and linking to a citable page. NOT FOR a build goal in plain words such as "a trading agent on Base" (use onchain_agent_recommend_stack instead), a RUNNING agent to hire or pay (use onchain_agent_search_agents), a downloadable agent package (use onchain_agent_search_listings), what an agent skill touches (use onchain_agent_search_skills), or one record by slug (use onchain_agent_get_resource). `search` is the one-box version for ChatGPT deep research. RETURNS (json): { total, count, offset, has_more, next_offset?, resources: [...] }; each resource has chains, status, liveness, github_stars, verification_status and the marketplace fields (is_agent/is_hirable/is_licensable). Read-only. With NO argument it is a compact overview (rule "defaulted": complete rows, fewer, plus directory counts); detail: "full" is the full first page. FILTERS: query (free text, AND-matched terms), chain, status, liveness, featured, and the taxonomy facets (docs/taxonomy.md) entity_class, resource_type, use_case, standard and iface — closed vocabularies listed in the input schema: anything else is refused with the list, never answered with an empty result. Legacy flags still work: category, is_agent, is_skill, is_harness. Sort by priority (default), newest_release, stars, or name. Paginates via limit/offset. Deprecated resources are never returned. STARTING POINTS: a query asking for somewhere to start — "tutorial", "starter", "beginner", "template", "example", "docs" — returns starting points labelled as such: listings named as a starter or template first, then listings whose install Sato Hub reproduced, plus the wiki guides. "starter" / "template" / "x402 starter" also carry `templates`: a pointer to onchain_agen

USE WHEN you need to judge one specific directory project: is it open source, still maintained, who is behind it, what does it support. NOT FOR a REGISTERED running agent (use onchain_agent_get_agent_passport instead), a published agent package (use onchain_agent_inspect_listing), install steps (use onchain_agent_get_deploy_spec), or finding a slug (use onchain_agent_search_resources first). RETURNS (json): { resource: {...full record incl. marketplace + liveness fields}, recent_activity: [...], agent_docs } by slug, optionally with recent releases and posts. `agent_docs` is where the project's machine-readable docs are, each dated: { as_of, read_first, llms_txt, llms_full, docs_mcp, agent_card }, or null with `agent_docs_reason` (not_yet_archived, read_failed) when none is archived; null is not "no docs". An unknown or Deprecated slug is an error. Read-only. Example: { slug: "coinbase-agentkit" }

USE WHEN you want one query box over Sato Hub, the daily-rebuilt index of what onchain and crypto AI agents are built from (frameworks, MCP servers, wallets, x402 and stablecoin payment rails, data tools), plus its dated answers, agent-economy numbers and wiki. Not for token prices, trading or investment advice. NOT FOR filtered or paginated directory queries (use onchain_agent_search_resources instead) or registered agents (use onchain_agent_search_agents). RETURNS (json): { results: [{ id, title, url }] }, at most 10, best first, from one query string; url is the canonical satohub.ai page to cite. Pass an id to `fetch` for the full text. A query nothing matches returns results: [] — never padded with unrelated records — plus scope_note, what Sato Hub covers. Read-only. Examples: "coinbase agentkit", "x402 payment rails on Base", "how many ERC-8004 agents by chain", "MCP servers that answer".

USE WHEN you hold an id that `search` returned and want that record from Sato Hub, the daily-rebuilt index of what onchain and crypto AI agents are built from, as plain text to quote. Not for token prices, trading or investment advice. NOT FOR a directory slug (use onchain_agent_get_resource instead) or an id you made up (call `search` first). RETURNS (json): { id, title, text, url, metadata: { as_of, kind, sato_score?, source } }. text is plain prose to quote: for a listing, what it is, its category and chains, its Sato Score with the date (how open, active and verifiable it is — not a safety or returns grade), its last observed activity, and whether Sato Hub reproduced its install; for an answer, number or wiki page, the answer with its date. url is the canonical satohub.ai page to cite. An id without a prefix is read as the record with that exact slug, or a listing it names exactly (the same name written differently, a recorded alias, the listing's own name); such an answer is labelled { interpreted_as, requested, rule, note } and its text starts with the note. Anything else is a miss that serves nothing (not an error: { miss, candidates, suggestions } beside an empty record whose text says so): it lists the ids `search` ranks for it as candidates ({ candidates: [{ id, title, url }] }), each an exact fetch to make. Read-only. Example: { id: "resource:coinbase-agentkit" }

USE WHEN a component has been picked (from onchain_agent_recommend_stack, onchain_agent_build_plan or a search) and the next step is installing it, once per pick, or you are about to write setup instructions and want steps checked against a clean install rather than copied from a README. NOT FOR choosing components (use onchain_agent_recommend_stack instead), whether an install command takes your key (use onchain_agent_check_install), or a full evidence list (use onchain_agent_preflight). RETURNS the deploy manifest for one resource by slug: runtime, install command(s), entry snippet, required keys/env/wallet/RPC, chains, license, whether it is itself an MCP server, and a deploy_status. KEYS AND MONEY COME WITH IT: every answer carries `trust_spec` — what this install does with your keys and money, from Sato Check, dated (key access, whether a planted test key was observed leaving, fund-moving actions, the version read, the Preflight verdict, what the reading does not cover). A hosted API with no package says so. Show `trust_spec.line` to the person you are building for before installing; `trust_warnings` appears only when a planted key was observed leaving or code reads key material its setup does not declare. PREFLIGHT COMES WITH IT: `preflight_summary` is the Preflight verdict from Sato Hub's records (no live handshake), its rule and the readings it turned on; `full_check` is the onchain_agent_preflight call for every evidence line. A verdict is not a security review, and `unknown` means no record, not a problem. deploy_status is a trust signal, NOT a safety guarantee: "verified" = the documented install was reproduced in a clean container; "self_reported" = parsed from the project's README, not reproduced. Verify keys, permissions and funds before running anything. RETURNS (json): { slug, name, github_url, docs_url, sato_url, deploy_spec, preflight_summary, trust_spec, trust_warnings?, save_stack_url, next_step, note, agent_docs }. `agent_docs` says where t

USE WHEN asked what has changed recently across crypto-agent tooling, or what has happened to one specific project over time, and you want dated, attributable HEADLINE events (a human-readable feed). Omit slug for the SITE-WIDE feed; pass slug for ONE resource's history, the auditable Listing History. NOT FOR keeping a local copy in sync (use onchain_agent_get_changes instead, which returns added/updated/removed since a date) or a listing's daily check record and score series (use onchain_agent_get_listing_history). RETURNS (json): { scope, total, changes: [{ date, kind, slug, name, title, detail?, tone }] }. tone is positive | negative | neutral. Events: status flips, verification grants, Sato Score tier moves, liveness (a project going dormant or active again), new releases, field enrichment. Derived from the daily snapshot time-series + the change-event log; high-signal only (passive score/liveness drift is suppressed). Read-only. Example: { days: 7 } · { slug: "coinbase-agentkit" }

USE WHEN you need the valid category values before filtering onchain_agent_search_resources, or want to see how the crypto-agent landscape divides up by size. NOT FOR chain names (use onchain_agent_list_chains instead) or finding projects (use onchain_agent_search_resources). RETURNS (json): { total, categories: [{ name, count }] }, every resource category with counts, most populated first. Read-only. Example: {}

USE WHEN you need the valid chain names before filtering onchain_agent_search_resources, or want to know which chains have real agent tooling behind them rather than an announcement. NOT FOR category names (use onchain_agent_list_categories instead) or onchain agent counts per chain (use onchain_agent_get_agent_economy). RETURNS (json): { total, chains: [{ name, count }] }, every blockchain represented in the directory with resource counts, spotlight chains first (Base, Ethereum, Solana, COTI, Injective…). Read-only. Example: {}

USE WHEN asked what is new or what shipped recently in crypto AI agents, and you want dated, source-attributed items rather than undated blog posts. Official releases (GitHub), project announcements, and reputable RSS, strongly filtered to the agent economy. Filter by kind (release/tweet/news/research) and/or chain; paginate via limit/offset. NOT FOR changes to the directory's own records (use onchain_agent_recent_changes instead) or a concept explainer (use onchain_agent_get_wiki_page). RETURNS (json): { total, count, offset, has_more, next_offset?, news: [{ kind, title, summary, url, source, author_handle, chains, resource_slug, published_at }] }. Read-only. Example: { kind: "release", limit: 10 }

USE WHEN you need one current, citable headline figure for the onchain agent ecosystem rather than a number from an article of unknown age: the ERC-8004 Identity Registry registered-agent count (read directly from Ethereum mainnet) and the curated Top Project Tokens index (only tokens of directory-listed projects, never the whole agent-token category or its aggregate market cap). NOT FOR counts by venue, chain or stage (use onchain_agent_get_agent_economy instead), a time series (use onchain_agent_get_trend), or token prices for trading. RETURNS (json): { erc8004: { network, registered_agents, live, checked_at, other_chains: { tool, args, note } }, top_agent_tokens: [{ symbol, name, current_price, market_cap, price_change_percentage_24h, resource_slug }] }. Read-only. Example: { token_limit: 5 }

USE WHEN asked to explain a crypto-agent concept (what x402 is, how agents hold wallets, what ERC-8004 does) and you want a sourced explainer you can cite. Find slugs with onchain_agent_list_wiki_pages. NOT FOR a specific project (use onchain_agent_get_resource instead) or how the Sato Score works (use onchain_agent_get_score_methodology). RETURNS (json): the full wiki page by slug: summary, why it matters, how it works, key components, examples, risks, related resources/pages. A near-miss slug that plainly means a page ("what-are-erc-8004" or the bare "erc-8004" for "what-is-erc-8004") serves that page and says which one in alias_of; when the slug is also a directory listing, also_listing names onchain_agent_get_resource. An unknown slug is a miss (not an error) carrying the nearest real slugs as suggestions; the Sato Score has no wiki page, so "what-is-sato-score" is a miss that points at onchain_agent_get_score_methodology. Read-only. Example: { slug: "what-are-mcps" }

USE WHEN you need a RUNNING agent to work with, hire or pay (not a tool to build one with) and want to see who registered it, on which chain, and whether it accepts payment. NOT FOR tools to build an agent from (use onchain_agent_search_resources instead), one agent's full manifest (use onchain_agent_get_agent_passport with a slug from here), or a ranked pick for a task (use onchain_agent_route_agent). RETURNS (json): { total, agents: [{ sato_agent_id, slug, name, description, agent_type, chains_supported, stack, payment/x402 metadata, verification_status, profile_url, manifest_url }] }. Searches the Sato Agent Registry: agents whose creators registered them for a Sato Agent Passport (distinct from the resource directory, which lists the things agents are built FROM). Filter by free-text query, chain, agent_type, or x402_only. Only human-review-listed agents are returned. Registry agents come first; when the registry has no match for a query, matching agent-type directory listings come back in listings[] with kind "listing" (not passports), and total counts both. A query that names a brand ("aixbt", "olas") also returns brands[]: the identities someone declared for it (ERC-8004 ids, wallets, builder codes), each saying who declared it (the brand, the platform that lists it, or the registrant); brands are not registry results and are not counted in total. Read-only. This is the Sato Agent Registry only: agents whose builders registered them with Sato Hub, a small set. It does not search agents registered onchain under ERC-8004, so an empty answer here says nothing about them. For those, call onchain_agent_get_agent_economy with venue "erc8004" (measured counts by chain), or see https://satohub.ai/agent-economy/erc8004 and https://satohub.ai/erc8004/<chain>. Trust rule: registration is self-reported by the creator; verification_status distinguishes Self-Reported from evidence-reviewed Verified/Audited. Nothing here implies safety or performance. Example: { chain:

USE WHEN you are about to work with, pay or depend on a REGISTERED agent and want its published identity before committing. Find slugs with onchain_agent_search_agents. NOT FOR a project in the directory such as a framework or MCP server (use onchain_agent_get_resource instead; aixbt, almanak and coinbase-agentkit have no passport). RETURNS the full Sato Agent Passport manifest (sato.agent.manifest/v1) for one registered agent by slug: identity (sato_agent_id), agent types, chains, model/framework, the stack of Sato Hub directory resources it runs on, links, payment/x402 endpoint metadata, and verification + liveness status. It also carries `registration` (the passport's lookup URL and any Sato Hub attestations recorded onchain on Base and Solana) and `erc8004` (the ERC-8004 ids its proven wallets own, with links). An attestation is a registration record: it shows the registrant proved control of the wallets, and says nothing about what the agent does. Payment metadata is self-configured by the creator, published for interoperability, not as an endorsement. An unknown slug, or an agent that is not listed, is a miss (not an error) carrying the nearest slugs as suggestions, or a pointer to onchain_agent_search_agents; a directory project's slug answers that it has no passport and points to onchain_agent_get_resource. Read-only. There is deliberately no example slug: the registry is small and its slugs are not guessable. ('my-trading-agent' was this tool's own placeholder and four separate clients sent it as if it were real.) Example: call onchain_agent_search_agents first, then { slug: <a slug it returned> }

USE WHEN someone wants to build any onchain or crypto agent ("Build any crypto agent") and says what it should do in plain words: "a trading agent on Base", "an ElizaOS agent that charges via x402", "a TypeScript agent with a policy-controlled wallet". This is the FIRST call for a build goal: goal → stack here, then onchain_agent_get_deploy_spec once per pick → install steps. NOT FOR looking up one named project (use onchain_agent_search_resources instead), the same stack as one composed answer with deploy specs, Preflight and a first action (use onchain_agent_build_plan), or the runnable repo itself (use onchain_agent_create_agent). RETURNS (json) real directory listings in slots (framework, wallet, payments, trading, data, MCP tooling, security; live agents someone else runs are kept out of trading), each pick with its Sato Score, liveness, deploy-spec status, github_url and a records-only `preflight_summary` (verdict, rule, the readings it turned on), plus honest gaps. A standard (x402, ERC-8004, A2A, MCP), runtime (TypeScript/Node, Python) or wallet control (policy, spending limit, session keys, permissions) the goal names lifts the picks whose own record names it — quoted in the reason, self-reported. `save_stack_url` opens the goal in the Sato Hub planner for the person you are building for. When a nightly-checked template answers the goal, `create` names it and the first next step is to generate that runnable repo with onchain_agent_create_agent. Only when no template matches, a Base goal with a wallet, swap, trading or x402 payments that names TypeScript/Node or no runtime carries `starter`, a TypeScript template repo built by Sato Hub (holds no key, signs nothing, not audited; `runtime_basis` says whether the goal named the runtime) — never a pick. KEYS AND MONEY COME WITH IT: every pick carries `trust_spec` — what it does with your keys and money, from Sato Check, dated: whether it takes your key, whether a planted test key was observed leaving, whether

USE WHEN you need the slug for a crypto-agent explainer before calling onchain_agent_get_wiki_page, or want to see which concepts have a sourced page you can cite. NOT FOR reading a page (use onchain_agent_get_wiki_page instead) or finding projects (use onchain_agent_search_resources). RETURNS (json): { total, pages: [...] }, every Onchain Agent wiki page with slug, title, keyword, summary and last_updated. Read-only. Example: {}

USE WHEN you keep a local copy of the directory and need only what moved since your last sync (machine-readable added / updated / removed), rather than re-fetching the whole catalog. NOT FOR a readable headline feed or one project's history (use onchain_agent_recent_changes instead), or the current state of one record (use onchain_agent_get_resource). RETURNS (json): what changed since a given date: additions, per-resource change events, and retirements. { since, until, window_days, next_since, counts:{added,changed,removed}, added:[...], changed:[{slug,name,url,events:[...]}], removed:[...], coverage:{...}, full_export }. CURSOR: `next_since` is the date to pass as `since` on your next call. It starts the next window at a snapshot taken before this read, so a change cannot fall between two calls; it overlaps by a couple of days, so dedupe by slug. To watch a fixed list of listings, call on a schedule with `since` = the last `next_since` and look for your slugs in each lane. A call with no argument returns a truncated sample: take the cursor from a call with `since` or detail "full", not from the sample. COVERAGE (also stated in the response): `added` is exact. `updated` is a field-level diff of every catalog field between the snapshot on `baseline_date` and the live record — complete at daily resolution, so a quiet copy edit IS caught. `changed` is the richer event log (score moves, releases, verification) and explains WHY. `removed` is approximate. Mirror from added + updated + removed. Read-only. WITH NO `since` (and no detail: "full") the answer is compact, labelled rule "defaulted": exact counts for the default 14-day window and the newest rows of each lane (summary: true, shown, omitted, order, example_calls). It is a sample, not a sync. Pass `since` (any date) or detail: "full" for every row; a later `since` is a shorter window and a smaller answer. All free. Examples: - "what moved recently" -> {} (compact) · every row -> { detail: "full" } - "what'

USE WHEN asked how big the onchain agent economy actually is (how many agents are really registered, launched, paying or trading) and you want measured chain reads instead of a figure from a deck or an announcement. Covers the agent venues Sato Hub tracks: registries, launchpads, payment rails and account infrastructure, measured weekly from public chain reads. NOT FOR a series over time (use onchain_agent_get_trend instead), one headline ERC-8004 count (use onchain_agent_get_metrics), or agents registered with Sato Hub (use onchain_agent_search_agents). RETURNS (json): { week, as_of, rules, evidence_tiers, venues: [{ id, name, unit, entry_cost, measurable, overlaps_with, headline_safe, contracts:[...], chains:[{ chain, stages:[{ stage, value, unit, method, evidence_tier, sample_size, denominator, covered_days, publishable, caveat }] }], platforms:[...] }] }. With no venue, chain or include_platforms (and no detail: "full") it is a compact summary instead, labelled rule "defaulted": { summary: true, week, as_of, rules, venues: [{ id, name, venue_unit, headline_safe, overlaps_with?, stage, unit, caveat, as_of, readings: [{ chain, value, sample_size, publishable, evidence_tier, unit?, caveat? }], more_chains, paired_stage? (the second stage of a venue quotable only as a two-stage figure, same shape), other_stages, full_detail: { tool, args } }], full_detail }. The week is the payload's, one for every venue; each stage's unit and caveat are its own rows', not the venue's. HOW TO USE THESE NUMBERS. Never add them together: an ERC-8004 registration, an Olas staked service, a Virtuals launch and a Mech task are four different objects, and each venue's `unit` says which. Every number names its stage — "19,180 launched, 1,233 graduated" is true, "58,400 agents" is not. A null value means UNKNOWN, never zero. A rate whose sample_size is below 20 is returned with `publishable: false` and should not be quoted. Solana identity registries are covered as UPPER BOUNDS (program-a

USE WHEN someone is about to install an agent skill and should know what it will touch first: keys, credentials, remote scripts, outbound hosts. Crypto-relevant agent skills from ClawHub and skills.sh, each with a static DISCLOSURE: hosts it contacts, whether it generates or handles private keys, whether it asks the user to paste a credential, whether it pipes a remote script into a shell, whether it grants itself unrestricted tools, whether it registers the agent with a third-party host, whether it schedules itself. Each flag carries evidence lines on the skill's page. NOT FOR finding frameworks, MCP servers or wallets (use onchain_agent_search_resources instead), an npm/pip/MCP install command (use onchain_agent_check_install), or one skill's Preflight verdict (use onchain_agent_preflight with skill). RETURNS (json): { total, skills: [{ id, name, registry, canonical_url, installs, stars, disclosure_flags, hosts_contacted, declared_env, registry_scan, belongs_to_slug, skill_md_sha256, as_of }], note }. A disclosure is a description, not a safety verdict — a wallet skill that generates keys is doing its job, and no flags is not a clearance. The registry's own scan status is attributed to the registry. `slug` is the directory listing a skill targets: a slug that matches no skill comes back empty, and says whether it is a directory listing (onchain_agent_get_resource reads it), a wiki page or Sato Hub's own planner. Read-only. Cite https://satohub.ai/skills. Examples: - "solana skills that don't touch keys" -> { query: "solana" } then filter disclosure_flags - "which skills phone home" -> { flag: "registers_with_third_party" } - "skills for Coinbase AgentKit" -> { slug: "coinbase-agentkit" }

USE WHEN the question is whether a measurement is going up or down (ANSWERS ONE QUESTION). Returns a bounded series (at most 30 points, default 8) for ONE venue, ONE chain and ONE stage from Sato Hub's own weekly (or daily) chain reads, each point with its date, value, sample_size and method. NOT FOR this week's numbers across venues (use onchain_agent_get_agent_economy instead) or one listing's score or check history (use onchain_agent_get_listing_history). Pass stage (required). Venue is optional: name it to read exactly one series; omit it and a stage that only one venue reports is read from that venue, while a stage several venues report comes back as one SEPARATE series per venue. Stages by venue: erc8004 reports registered (weekly), registered_new_1d (daily), active_7d, mcp_endpoint_answers; olas reports registered and working; virtuals reports launched; virtuals_acp reports jobs_created; x402 reports settled_to_catalogued_seller, answers_402 (weekly) and facilitator_txs_1d_known (daily). A stage name alone is enough when one venue reports it; when several do (registered is reported by more than one venue) you get one separate series per venue. RULE ENFORCED: points are never summed across venues, chains or stages — the tool refuses to blend chains and tells you which chains exist when you omit one, and several venues are never combined. A null point is UNKNOWN for that period, never zero. The weekly point is the citable one; daily points feed a trend and never a headline. Raw rows are not returned. RETURNS (json): { venue, chain, stage, grain, unit, points: [{ date, value, sample_size, method, evidence_tier }], direction_first_to_last, known_points, rules, as_of, source } — or, when a stage several venues report is asked without a venue, { stage, grain, series: [that same object per venue], needs_chain?, no_reading?, rules }. Read-only. Examples: - "are ERC-8004 registrations on Base growing" -> { venue: "erc8004", chain: "Base", stage: "registered" }

USE WHEN the question is how two directory listings compare on the axes Sato Hub tracks for both (ANSWERS ONE QUESTION), e.g. "AgentKit or Solana Agent Kit?". NOT FOR a single project's detail (use onchain_agent_get_resource instead) or a ranked stack for a goal (use onchain_agent_recommend_stack). RETURNS the SAME derived table the /compare pages render — category, chains, interfaces, standards, open-source status, listing status, last activity, last release, install proof, verification, Sato Score, GitHub stars — every cell read off the live records, never typed. RULE ENFORCED: there is NO winner field and none can be derived from the table; `caveat` is mandatory and names what the data cannot settle (for a curated pair, the comparison page's own caveat). The Sato Score is openness/activity/verifiability, not a safety, quality or returns grade. RETURNS (json): { a: { slug, name, liveness, observed_success_pct, sato_url }, b: {...}, rows: [{ label, a, b, note? }], caveat, rules, comparison_page, source }. Read-only. Example: { a: "coinbase-agentkit", b: "solana-agent-kit" }

USE WHEN the question is where a published Sato Hub number comes from (ANSWERS ONE QUESTION) and you need its method, sample and reproduce call before quoting it. NOT FOR fresh measurements (use onchain_agent_get_agent_economy instead) or how old a data surface is (use onchain_agent_get_data_freshness). RETURNS: for any https://satohub.ai/numbers/<slug> page { slug, page, question, method, window, reproduce, mcp_server, rules } — how the number is measured and the exact call that reruns it. Otherwise it returns one finding from the State of Onchain Agents report by slug — the figure with its stage, method, sample, as-of date, the SQL query that reproduces it, and its citable page at https://satohub.ai/numbers/<slug>. RULE ENFORCED: a number never travels without its stage, method, sample and date; it is never summed across venues, chains or stages. CITE THE URL in the payload, not this response. Returns an error while the report is unpublished. RETURNS (json): { slug, title, number, unit, stage, method, sample, lines, query, as_of, url, cite, rules }. Read-only. Example: { slug: "erc-8004-agents-registered-on-base" }

USE WHEN you are about to describe, apply or compare the Sato Score — or when asked how to tell whether a crypto-agent project is real, maintained or open — so you quote the rubric instead of guessing it. NOT FOR one project's score (use onchain_agent_get_resource instead; its record carries the score) or a score's movement over time (use onchain_agent_get_listing_history with score_days). RETURNS the six components with their maximum points and what each measures, the tier cutoffs, what "provisional" means, what is deliberately NOT in the score, how it is computed and reproduced, and where a dispute goes. RULE ENFORCED: the Sato Score is a 0–100 measure of how OPEN, ACTIVE and VERIFIABLE a project is, from public evidence, recomputed daily. It is NOT a safety, security, quality, legitimacy or returns grade, and this tool says so in the payload. Self-reported claims earn nothing in it. CITE https://satohub.ai/sato-score when you explain it. RETURNS (json): { name, scale, components: [{ key, label, max, measures }], tiers, provisional, not_in_score, computed, reproduce, dispute, caveat, url }. Read-only. Example: {}

USE WHEN you are about to quote a Sato Hub number, score, count or feed item and want to know how old it is — or when a figure looks stale and you need to know whether the pipeline behind it is late. NOT FOR how a number is measured (use onchain_agent_explain_number instead) or what changed in the directory (use onchain_agent_recent_changes). COVERS, per data surface (directory activity, news, Sato Score, liveness checks, snapshots, ERC-8004 counts, the weekly agent-economy measurements, x402, LP pools, skills, deploy verification and more): when it was last collected successfully, when a collection was last attempted and how that ended, how often it is expected to run, whether it is late, the next scheduled run, and the ledger step it was read from. RULE ENFORCED: late = now − last success > 1.5 × the expected cadence (daily 36h, weekly 252h). A surface built from several pipeline steps is as fresh as its stalest step, and one of its steps never succeeding makes it late. A surface with no recorded success at all returns `last_success_at: null` and `late: null` — unknown, never an invented date. If the ledger cannot be read, every surface is `unknown`, never "fresh". A late surface still serves its last good data: quote it WITH its date. RETURNS (json): { generated_at, ledger, rule, surfaces: [{ surface, what, expected_every, last_success_at, last_attempt_at, last_status, late, state, age_hours, late_after_hours, next_update, source, steps: [{ step, last_success_at, last_attempt_at, last_status }], served_by }], note, source_url, sato_url }. Timestamps and statuses of data jobs only — no usage figures. Read-only. Example: { surface: "sato_score" }

USE WHEN someone wants a ready-made onchain agent PACKAGE to download or fork rather than assemble one. Searches Sato Hub's published agent packages, each a public view of one sealed, immutable version: its task, inputs/outputs, required permissions, model support ("configured, not evaluated"), license, and evidence freshness for that exact digest. NOT FOR directory projects such as frameworks or MCP servers (use onchain_agent_search_resources instead), running agents to hire (use onchain_agent_search_agents), or generating a fresh repo from a goal (use onchain_agent_create_agent). RETURNS (json): { listings: [{ slug, title, task, version: { digest }, recipe, license, fork_permitted, evidence_freshness, integrity, acquisition_modes, sato_url, superseded_by, ... }], next_cursor }. `superseded_by` is the id of the nightly-checked template that replaces a package (generate it with onchain_agent_create_agent), or null; the package itself still downloads. RULE ENFORCED: evidence counts only rows recorded against the package's exact digest — "not_checked" means none exist. A result is scoped to its test; it is not a safety, security or returns claim. No signed download URL is ever returned; cite sato_url. Read-only. Example: { query: "treasury", limit: 10 }

USE WHEN you have a PACKAGE slug (from onchain_agent_search_listings) and need what it does, what it needs and what is on record about it before recommending a download or fork. NOT FOR directory listings such as a framework, MCP server or project (use onchain_agent_get_resource instead) or finding a package slug (use onchain_agent_search_listings). RETURNS the package's public fields only: task, description, creator display name, version digest and signing state, recipe, input/output schemas, required services and permissions, model support ("configured, not evaluated"), operating-cost basis as the creator wrote it, license and whether fork is permitted, support, evidence freshness for this digest, integrity, and acquisition modes (download, fork — there is no deploy or buy), and `superseded_by` (the template that replaces the package, or null). PACKAGES VS DIRECTORY: packages are agents published through Sato Hub, a separate set from the directory of projects and tools. A directory slug answers "directory listing, not a package". RULE ENFORCED: never a signed URL, account id or project id. "integrity: stale_evidence" means the stored artifact no longer matches the seal and download is withheld. Cite sato_url. manifest_url is the public signed release manifest a downloader checks the zip against offline with /verify-release.mjs — it proves the bytes are what Sato sealed, not that they are safe. Read-only. Example: call onchain_agent_search_listings first, then { slug: <a package slug it returned> }

USE WHEN the question is whether a listing has been answering Sato Hub's daily checks and whether its tool inventory has moved (ANSWERS ONE QUESTION), or how its Sato Score has moved day by day. NOT FOR a feed of events across projects (use onchain_agent_recent_changes instead) or the listing's current record (use onchain_agent_get_resource). RETURNS a bounded 30-day shape from the listing's observed record — days observed, share of OUR checks that succeeded, current state and streak — plus the MCP tool-inventory changes in the window (date, count after the change, added, removed) and the current Sato Score. RULE ENFORCED: success_rate_pct is the share of Sato Hub's own checks that succeeded, never "uptime" — a failure can be on our side. At most 30 entries; the daily rows are not returned (rule 24: shape, not rows). Absence of a record is unknown, not down. Pass `score_days` to add `score_series`: the daily Sato Score readings we captured for this listing, up to 90 days without a key (a longer request is clamped, never refused, and `score_series_window` says what was served; the 180-day chart is on the listing's /verify/<slug>/history page). A day nobody measured is ABSENT from the array rather than carried forward — a gap is a gap — and every move is labelled `project` or `methodology`, the latter meaning Sato Hub revised the scoring rubric that day and the movement is ours. RETURNS (json): { slug, days, observed: { days_observed, window_days, success_rate_pct, rate_days, rate_window_start, current_state, current_streak_days, last_check }, tool_history: [{ date, count, added, removed }], tools_now, tools_peak, trust_score, trust_tier, score_series, score_series_window, rules, sato_url }. Read-only. Example: { slug: "jupiter-mcp", days: 30, score_days: 90 }

USE WHEN you are about to install a package, clone a repo, connect to an MCP endpoint, pay an agent, or trade a token, and you want to know what is on record about it FIRST — every evidence line, with the field it was read from and its date. Pass exactly one of repo, package, endpoint, agent, token, skill, x402 or address; with none (or a template placeholder) nothing is checked and the answer is { needs_input: true, accepted_forms, example_calls }. NOT FOR a stack pick's summary (onchain_agent_recommend_stack and onchain_agent_get_deploy_spec already carry a records-only `preflight_summary`), whether an install command or MCP config takes your key (use onchain_agent_check_install instead), or a recipient-address reading on its own (use onchain_agent_scan_recipient). Call this for the full evidence, for any target that is not a pick (a repo, package, token, skill or ERC-8004 agent you were handed), or for a live handshake with an unlisted MCP endpoint. RETURNS a verdict — go | caution | no | unknown — with one evidence line per check, each naming the field it was read from and when that field was written. The rules are written down in lib/preflight.ts and cited by id in `rule`. RULE ENFORCED: a verdict names WHAT WAS CHECKED AND WHEN. It is never a security review, a quality judgment or a statement about returns, and `unknown` means Sato Hub holds no record — not that something is wrong. An unlisted endpoint gets ONE live handshake (initialize + tools/list, 8 s cap) and can never come back `go`: a handshake is not a record. For agent=<chain>:<id> we confirm the ERC-8004 registration exists, fetch its registration file, and report the services it DECLARES; only a declared MCP service is probed. TOKEN LANE (token + chain; the EVM chains listed, and Solana): keyless chain reads. EVM: bytecode presence and size, the ERC-20 views, the Clanker v4 factory's OWN deployment record, and the Uniswap v3 factory across the four standard fee tiers against wrapped native. Solan

USE WHEN you are about to install a crypto package, MCP server or skill and want to know what it can do with your keys and funds: before npm/pnpm/yarn/bun add, npx -y, pip install, uvx or `claude mcp add`, or before pasting an {"mcpServers": …} config. NOT FOR a token, repo, endpoint or agent you were handed (use onchain_agent_preflight instead), install steps for a stack pick (use onchain_agent_get_deploy_spec), or an agent skill's disclosure (use onchain_agent_search_skills). RETURNS a Sato Check custody summary for every target in the command or config you pass, answering four questions: does it take your key, does your key leave, can it move funds on its own, what changed. Each answer rests on evidence of one class — declared (the project says so), traced (our static read of the published artifact) or observed (a sandbox run with planted test keys). A stored profile answers first; an unstored target is read live within a bounded budget. Targets that could not be profiled are listed in `unresolved` with the reason. `has_observed_key_egress` is true only when a planted test key was seen leaving — the one fact to stop on. RULE ENFORCED: a profile describes what was read and run, with dates. It is not a safety rating, an audit or an endorsement; "unknown" means we could not look, and "none found" is not "not there". Local signing is what a wallet does. RETURNS (json): { schema: "sato.custody/v1", subjects: [{ subject, summary: { key_access, key_egress, fund_action_count, notable, version, as_of, check_url }, answers: { key_access, key_egress, fund_actions, changes }, solana_receipt }], unresolved: [{ input, reason }], has_observed_key_egress }. `solana_receipt` is where that version's reading is recorded on Solana ({ attestation_address, explorer_url, cluster, as_of, digest_hex }), or null when none is. install/cmd/package/text are read as `command`, mcp/mcpServers as `config` (labelled); `{}` checks nothing and answers needs_input. Read-only. Example: { comman

USE WHEN an agent is about to pay or transfer to an address: an x402 payTo, a treasury sweep, a top-up. Pass the chain and the recipient; add the token, the origin whose 402 named the address and the paying wallet for a fuller reading. Sato Scan answers five questions, each with its own date and gap. NOT FOR checking a package, repo, token, endpoint or agent (use onchain_agent_preflight instead; its address lane wraps this reading in a wider check). WHAT IT READS: (1) does the recipient only LOOK like an address the payer pays, matching its first and last characters without being it; (2) is the token the issuer's contract, keyed by contract address and never by symbol; (3) did the paid party declare the address, through the origin that served it or an identity that names it; (4) does the address carry a structural mark from what it did onchain; (5) is the paying wallet itself the target of address poisoning. RULES: a reading describes what was looked at inside the stated limits, on the date given. `unknown` means Sato Hub holds no record either way. `go` means the payee was declared, the token is the issuer's contract and nothing was found within the limits: it is never a clearance. `caution` and `no` name the rule and the observed fact that decided them. A mark describes what an address did, not who controls it. The recipient, token, paying wallet, origin and amount are not stored; only the chain is. Nothing is signed or sent. RETURNS (json): { schema: "sato.scan.recipient/v1", verdict: go | caution | no | unknown, rule, reason, answers: { token, lookalike, declared, marks, targeted }, limits, limits_text, as_of, method_version, caveat }. Read-only. Example: { chain: "Base", to: "0x1bc0c42215582d5A085795f4baDbaC3ff36d1Bcb", token: "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913", origin: "https://api.example.com/paid" }

USE WHEN an agent wants a swap QUOTE with the venue chosen by liveness, verification and price and the fee disclosed. Asks every aggregator adapter that quotes on the chain, in parallel, and returns the chosen venue's quote and calldata. NOT FOR a swap checked against token, venue and recipient verdicts and a spending policy, with a simulated unsigned transaction and a receipt (use onchain_agent_swap instead), a launch venue (use onchain_agent_route_launch), or a liquidity pool (use onchain_agent_route_lp). RULE ENFORCED: a route is a RECOMMENDATION, not a verdict and not an assurance. `chosen_by` names every field it was chosen on — liveness, the observed record of Sato Hub's OWN daily checks (never "uptime"), verification state, then quoted price — with the field each was read from and `checked_at`. Nothing here is called best, safe or guaranteed. A quote is a quote, not a fill. NON-CUSTODIAL: this tool NEVER signs, holds, moves or broadcasts funds. It returns calldata the caller may sign. THE FEE: Sato Route swaps cost 3 bps stable-to-stable, 15 bps between majors (a chain's native coin such as ETH or SOL, its wrapped form, or a stablecoin), 75 bps with any other token and 25 bps cross-chain (75 bps when either side is any other token), taken as a parameter on the aggregator's own quote inside the transaction you sign; a failed, reverted or unsigned trade pays nothing. A token launch carries a disclosed share of the creator's LP fee, stated as fee.bps on every launch response, including when it is 0. Sato OS charges 3 / 15 bps on its own spot swap rail and a 3 bps perp builder fee, with no cross-chain tier. Some venues keep a share or pay later, and every quote says which. It is stated in `disclosure` before anything is signed. RETURNS (json): { route: { slug, name, listed, sato_url, liveness, observed_success_pct, install_verified }, quote: { venue, amount_in, amount_out, token_in, token_out, chain, calldata, tx, source_url }, sato_fee_bps, sato_fee_recipient

USE WHEN an agent needs another agent for a task and wants the pick explained by registration, answering service, feedback and liveness. Candidates are the listed Sato Agent Passports; the top 3 by the static ranking get one live MCP handshake before the pick is made. NOT FOR browsing registered agents with filters (use onchain_agent_search_agents instead) or one agent's manifest (use onchain_agent_get_agent_passport). RULE ENFORCED: a route is a RECOMMENDATION, chosen by the listed fields at checked_at. `chosen_by` names every signal, its value and the exact field it was read from. An ERC-8004 registration proves a claim was made on-chain, not that the agent works; wallet_verified proves the key, not the product; a probe proves the declared service answered once. A null feedback count is unknown and ranks below every number, including zero. No job-outcome data exists yet. COVERAGE: agents registered on-chain but holding no Sato passport are absent from the pool — there is no keyless ERC-8004 enumeration callable from a request. Absent means unseen, not unqualified. When nothing qualifies the answer is `unknown` with a reason, never a low-confidence pick. RETURNS (json): { route: { agent, chosen_by: [{ signal, value, source_field }], checked_at, alternatives: [{ id, name, source, behind_on }], caveat } | { unknown, reason }, preflight, candidates_considered, probed, coverage, rules, caveat, checked_at }. Example: { capability: "trading", chain: "Base", requires_mcp: true }

USE WHEN an agent or a builder is about to launch a token and wants the venue chosen on published facts, with the fee disclosed before anything is signed. Venues covered: Clanker v4, Bankr, Virtuals, Zora creator coins. NOT FOR a swap (use onchain_agent_route_swap or onchain_agent_swap instead), a liquidity pool (use onchain_agent_route_lp), or generating a launch-prep repo (use onchain_agent_create_agent with the token-launch-prep template). RULE ENFORCED: a launch route is a RECOMMENDATION. `chosen_by` names every fact it was chosen on, each with the venue page it was read from and the date it was read (`facts_as_of`). A fee schedule says nothing about what a token will do after it launches, and nothing here is a security review or an audit. `null` is unknown and never zero — a venue that publishes no per-party fee split is unread, not generous. NON-CUSTODIAL: this tool NEVER deploys, signs, holds keys or moves funds. For the Clanker lane it returns a PREPARED CONFIG in the documented clanker-sdk v4 `deploy()` shape (the SDK is deliberately not a dependency of this service) which the caller reads and signs itself. Other venues are recommend-only: named, with a stated reason why no config is emitted. THE FEE: Sato's slice is one entry in the venue's own reward-recipient list — the deployer takes `10000 - bps`, Sato takes `bps`, and the two always total 10000. It is disclosed in `fee` on EVERY response, including when it is 0, and at 0 no Sato recipient appears in the config at all. A launch that is never signed pays nothing. RETURNS (json): { route_id, goal, chain, venue: { slug, name, lane, pool_fee_pct, creator_share_pct, programmable_fee_split, facts: [{ fact, source_url, as_of }], unconfirmed, docs_url }, reason, chosen_by: [{ signal, value, source_field }], checked_at, alternatives: [{ slug, name, behind_on }], fee: { bps, recipient, basis, disclosed }, prepared_deploy, prepared_deploy_unavailable, facts_as_of, caveat, rules }. When no venue documents the

USE WHEN someone describes the onchain agent they want and needs ONE composed answer that goes from goal to install steps (stack, deploy specs, Preflight, first action, open questions) rather than advice. NOT FOR only the ranked stack (use onchain_agent_recommend_stack instead, the lighter first call), a plan plus a pointer to the repo generator (use onchain_agent_scaffold_plan), or the runnable repo itself (use onchain_agent_create_agent). COMPOSES onchain_agent_recommend_stack, onchain_agent_get_deploy_spec and onchain_agent_preflight: the goal restated, a stack of REAL directory listings (each with Sato Score, liveness, observed check record and `sato_url`), the deploy spec for every item that publishes one, a records-only `preflight_summary` and a dated `trust_spec` (what it does with your keys and money, from Sato Check) on every item with `trust_warnings` first when a planted key was observed leaving or code reads undeclared key material, the first action when the goal implies one (a swap route, or a prepared token-launch config), the questions the user still has to answer, and the next steps. RULE ENFORCED: nothing in a plan is invented. Every component is a listing that exists; every number names the field it was read from; `null` is unknown and never zero. A Sato Score measures how open, active and verifiable a project is — it is not a security review, a quality judgment or a statement about returns. A Preflight `unknown` means Sato Hub holds no record, not that something is wrong. OURS, LABELLED: on a trading or swap goal the plan also carries an `execution` block for Sato OS — Sato Hub's OWN self-hosted trading OS, which we sell. It always carries `ours: true` and says "built by Sato Hub". It is NOT a stack pick: it fills the execution layer (where the stack runs), it is never ranked against a directory listing, and no listing loses a position to it. On any other intent `execution` is null. SKILLS: a plan also carries up to three crypto-relevant agent

USE WHEN an agent is deciding which Uniswap pool and fee tier to provide liquidity to for a pair Sato Route already quotes, and wants the observed readings rather than an opinion. NOT FOR a swap (use onchain_agent_route_swap or onchain_agent_swap instead) or a token launch (use onchain_agent_route_launch). RETURNS every v3 pool the weekly LP lane found across the four standard fee tiers, each with its in-range liquidity, the swaps and volume actually counted, the window that count covered, and a fee-revenue proxy. RULE ENFORCED: a route is a RECOMMENDATION. `chosen_by` names every field the pick was made on and where each was read. THE LARGEST TERM IS MISSING ON PURPOSE: impermanent loss is not modelled, not approximated and not bounded, and it appears in `chosen_by` as an explicit null rather than being quietly omitted. A fee-revenue figure here is a PROXY — the pool's published fee rate multiplied by volume we counted, in token0's own units — and is never called revenue, an APR or a yield. Readings are never scaled up from the window covered to a full week. THE PICK: highest observed fee-revenue proxy per day per unit of in-range liquidity, among pools whose window could be read. When nothing is rankable the answer is `chosen: null` with a reason per pool, never a low-confidence pick. COVERAGE: Uniswap v3 on Base and Ethereum, for the pairs the router quotes. Uniswap v4 rows come back `null` WITH THEIR REASON — v4 is a singleton PoolManager and publishes no per-pair pool id — and null is unknown, never zero. Every non-Uniswap venue is outside the reading entirely. NON-CUSTODIAL: this tool never signs, holds, moves or provides liquidity, and nothing it returns is advice. RETURNS (json): { chain, pair, week, latest_week?, note?, pools: [{ venue, pool, fee_tier_ppm, fee_tier_pct, liquidity, swaps_observed, volume_token0_observed, fee_revenue_proxy, fee_revenue_proxy_per_day, proxy_per_day_per_liquidity, token0, token1, covered_days, window_days, window_complete

USE WHEN someone wants the code for an onchain agent, not advice: describe the goal and get a runnable TypeScript repo generated from a template that is re-checked every night. Same handler as POST /api/create and the create-sato-agent CLI. NOT FOR choosing a stack or advice (use onchain_agent_recommend_stack or onchain_agent_build_plan instead) or a plan with no repo (use onchain_agent_scaffold_plan). The goal picks the template; it never changes a template code file. A goal no template answers returns no_template with the nearest templates instead of improvised code — each with its id, framework, intents, chains and `mismatched` (what differs from the request), so the next call can name one. TEMPLATES, as template (intents: frameworks): base-guarded-trader (trading, swap: agentkit, ai-sdk, claude-agent-sdk, openai-agents, plain-ts); persona-agent (general, payments: claude-agent-sdk); research-report (data, research: plain-ts); solana-guarded-swapper (trading, swap: plain-ts); token-launch-prep (launch: plain-ts); treasury-monitor (data, treasury: plain-ts); x402-seller (payments: plain-ts). Any other intent × framework pair answers no_template. The repo carries policy.json (spending caps, allowed chains and tokens), sato.lock.json (dependency custody readings) and sato.create.json (the manifest, signed when a key is configured). It generates for a local fork by default and testnet on request; mainnet is refused unless network is "mainnet" and mainnet_risk_accepted is true, and a template that does not run on the network says so. RULE ENFORCED: the goal is not stored or logged. A refusal names its error code and, where one applies, the rule. `last_green` is the day the template last passed its nightly checks, or null — never invented. Nothing is audited, and nothing here signs, holds keys or moves funds. RETURNS (json): { schema: "sato.create.response/v1", ok: true, template: { id, version, digest, framework }, files: [{ path, encoding, content }], zip_base64

USE WHEN a plan has been agreed and the next question is which repository to start from. Builds the plan (same brain as `onchain_agent_build_plan`) and returns it with a `create` pointer to `onchain_agent_create_agent`, which generates the runnable repo from a nightly-checked template. NOT FOR the full plan with deploy specs and Preflight on every pick (use onchain_agent_build_plan instead) or the repo itself: this tool no longer writes repository files, so use onchain_agent_create_agent to generate it. Every door (this server, POST /api/create, the CLI and the Agent Architect) downloads the same repo from the same engine. RETURNS (what comes back): the plan summary (goal, intent, chain, plan_url, checked_at, stack slugs), the environment names the stack's own deploy specs ask for, any documented install that pipes a remote script into a shell (`quarantined_installs`, to read before running it), and `create`: the tool name, the CLI command and the template the goal maps to, or null when no template answers it. KEPT FOR COMPATIBILITY: `files` is an empty list and `bytes` is 0; `include_zip` is accepted and ignored. `mode` is "plan_only". RULE ENFORCED: nothing is generated. Every value is a field of the plan. An install line we were not told is never invented. NON-CUSTODIAL: nothing here holds keys, signs, deploys or moves anything. RETURNS (json): { mode: "plan_only", name, files: [], env_names, quarantined_installs, bytes: 0, plan: { goal, intent, chain, plan_url, checked_at, stack_slugs }, caveat, create: { tool, command, template, note } }. Example: { goal: "a Base trading agent that swaps USDC to ETH on a signal", chain: "Base" }

USE WHEN an agent (or the person it works for) wants to be told if something in its stack stops checking out — rather than re-running a Preflight on a schedule of its own. This WRITES one subscription row. NOT FOR a one-off check now (use onchain_agent_preflight instead) or a record's change history (use onchain_agent_recent_changes). Goes through the SAME path the public form uses: same validation, same normalisation, same rate limit, one row per address and target. WHAT HAPPENS: the target is re-checked once a day by the public Preflight path, and an email is sent ONLY when the verdict CHANGES. Never on a schedule, never a digest. A transition INTO `unknown` (a check that failed to run) is recorded and never mailed — a failed check is not news about the target. wallet: get told when Sato Scan sees address poisoning aimed at that wallet. FREE WHILE IN PREVIEW. No price is set and no payment is taken. WHAT IS STORED: the normalised target, the address (a notice has to be delivered), an HMAC of it for counting, and the baseline verdict. No IP address and no name. Asking twice is idempotent; `action: "unsubscribe"` stops the mail and answers the same way whether a row existed or not. RULE ENFORCED: a verdict describes what was checked and when. It is not a safety, security or returns judgment, and a CHANGE is a change in what was observed — not a warning. RETURNS (json): { ok, action, target_kind, target, watch_id, verdict, notice, caveat }. Example: { target_kind: "package", target: "solana-agent-kit", notify_to: "[email protected]" }

USE WHEN an agent has found, built or maintains a crypto-agent project that is not in the directory and wants it considered. NOT FOR correcting a listing that already exists (that goes through the claim flow on its page), checking whether a project is listed (use onchain_agent_search_resources first), or registering a running agent (use onchain_agent_register_agent). This WRITES: it files the same row the /submit form files, into the same queue, and the daily triage run evaluates it through the same single apply path — probe the public evidence, validate against the listing schema, list it or hold it or decline it with a reason. WHAT HAPPENS NEXT: the website, the repository and any declared endpoint are probed from public sources. A project that clears that evidence is listed; one that does not is held for a person, or declined with the reason. If `contact_email` is given you get exactly ONE email, and only if it is listed. A hold sends nothing — silence means a person is looking. SUBMISSION IS NOT VERIFICATION. It is a request to be looked at. Being listed says what was observed about a project on a date, not that it is safe, audited, profitable or endorsed. Copy carrying profit, safety or risk claims is refused here rather than quietly cleaned up. DEDUPE: the website host and the repository are checked against the live directory and against submissions already waiting. A match returns that existing entry instead of filing a second row — correcting a listing that already exists goes through the claim flow on its page, which proves control of the domain first. LIMIT: 5 write calls an hour per caller. Nothing is written when it trips. RETURNS (json): { ok, duplicate, submission_id | slug, next, caveat }. Example: { name: "Example Agent Kit", website_url: "https://example.dev", repo_url: "https://github.com/example/kit", category: "Agent Framework", description: "A TypeScript toolkit for wiring agents to Base with viem and an MCP server.", chains: ["Base"] }

USE WHEN an agent wants a public, machine-readable identity: an Agent Passport at satohub.ai/agents/<slug> plus a manifest at /api/agents/<slug>/manifest that another agent can read before deciding to work with it. This WRITES a passport. NOT FOR submitting a project, framework or tool to the directory (use onchain_agent_submit_project instead), reading a passport (use onchain_agent_get_agent_passport), or the free wallet-signed join that needs no form and takes EVM and Solana wallets together (use onchain_agent_join_passport instead; to change a passport afterwards, onchain_agent_passport_action). TWO STEPS. Call it with `name` and `wallet_address` and no signature, and it returns the exact challenge to sign (EIP-191 personal_sign) and the `signed_at` that goes with it — the same string GET /api/agents/challenge returns, deterministic, valid 15 minutes. Call it again with `wallet_signature` and `signed_at` plus the registration fields, and the passport issues immediately. WITHOUT A SIGNATURE the registration is accepted and lands PENDING for human review; `contact_email` is required on that path. Signature verification is EVM-only for now — a Solana wallet can register, unsigned. WHAT THE SIGNATURE PROVES: control of the key. Nothing else. verification_status is Self-Reported on every passport issued here and no input can change it. Declared standards, endpoints and stack are claims; the endpoint gets one live probe and the wallet one on-chain lookup, and both are reported as what was observed, not as approval. LIMIT: 5 write calls an hour per caller. The challenge step counts, so fetch it once and sign it. RETURNS (json): unsigned first call { challenge, signed_at, expires_in_seconds, next }; registration { ok, slug, sato_agent_id, status, wallet_verified, passport_url, manifest_url, note }. Example: { name: "Example Agent", wallet_address: "0x…" } then the same plus { description, agent_type: ["Trading"], chains_supported: ["Base"], wallet_signature: "0x…",