io.github.strale-io由 GitHub 帳號 strale-io 發布v0.2.12更新於 Nov 8, 2026
Hundreds of pay-per-call tools for agents: company records, screening, validation, web reading.
Strale 是按次付費的能力市集，讓助理搜尋、執行並稽核數百個公司資料、合規、驗證與 Web3 工具。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.strale-io%2Fstrale/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"strale": {
"type": "http",
"url": "https://api.strale.io/mcp?src=mcp-registry"
}
}
}Pay-per-call tools for AI agents — one API key or an x402 wallet. MCP server, REST API, TypeScript and Python SDKs.
[npm] [npm] [PyPI] [License: MIT] [strale.io]
Strale is a capability marketplace for AI agents. Agents call strale.do()
at runtime to reach tools — company registry lookups,
compliance checks, financial validation, Web3 security, and more — plus
bundled solutions for multi-step workflows like a full KYB check or company
due diligence, instead of the agent's own code hardcoding integrations and
managing credentials for every data source it might need.
Each tool page lists inputs, output fields, price, limitations and source. Testing modes vary by tool. Read the current catalogue, free-tier list and country coverage from platform facts.
Works with Claude Desktop, Claude Code, Cursor, and any MCP client
supporting Streamable HTTP. For local stdio instead, or the full tool
surface, see packages/mcp-server/README.md.
Full reference: packages/sdk-typescript/README.md.
Full reference: packages/sdk-python/README.md.
A subset of capabilities (email/IBAN/crypto-address validation, DNS lookup,
JSON repair, URL-to-markdown, and more) work with no signup, no API key, and
no wallet — only an IP-based monthly allowance. Read the current list from
GET /v1/platform/facts (free_tier_slugs), not from a number in this
file. Get a key and trial credits at strale.io when
you need the rest of the catalog.
Each package's own README is the reference for that integration; this file only points at them. Every distribution PR against an external framework repo, and every publish of one of these packages, follows CLAUDE.md's Distribution PR Integrity Protocol — a package claiming framework-native integration is verified against the published artefact, not the source tree, before the claim ships.
Web3 capabilities (wallet risk scoring, token honeypot detection, ENS resolution, DeFi protocol data, gas oracle, EU MiCA VASP verification, market sentiment) and bundled solutions for on-chain agents are available via the x402 payment protocol — pay per call with USDC on Base mainnet, no signup required. Not every capability is x402-eligible; read the live, dynamic subset from:
Testing modes vary by tool. Inspect current availability, test mode and last-tested time in public test signals, and read limitations and sources in the catalogue before use.
Every capability publishes its limitations honestly, including coverage gaps. Methodology: strale.io/security.
Drop these into your project to give your coding agent security guidance for trust-sensitive data (IBANs, company registries, sanctions, PII):
docs/ide-rules/strale-compliance.mdc → .cursor/rules/docs/ide-rules/strale-compliance.windsurfrules → project root, or .windsurf/rules/ as .mddocs/claude-md-snippet.md → your project's CLAUDE.mdThese prevent the most common vibe-coding vulnerabilities: client-side IBAN validation, hardcoded API keys, missing provenance metadata, and direct registry scraping.
SKILL.md files for Claude Code, Cursor, Copilot, and Codex. Copy skills/strale/ into .claude/skills/, .github/skills/, or .cursor/skills/.apps/api/scripts/ and apps/api/src/capabilities/ carry the same idea at
capability-authoring scope — read CLAUDE.md's "Adding New Capabilities"
section before writing a new executor.
Where truth lives. Product, state, and roadmap truth is migrating from
Notion into this repository (docs/project/), but the migration is not
complete: docs/project/START-HERE.md and the rest of docs/project/ are
explicitly candidates (authority_active: false) until a founder-
confirmed cutover. Until then, Notion (Project Home, the To-do & Build
Plan, the Decisions DB) is authoritative, and CLAUDE.md / AGENTS.md say
so at the top of every session. docs/README.md indexes every docs/
subtree with its current authority status; docs/project/STRUCTURE.md
records exactly where the repo's layout still deviates from the migration's
target and why.
Where work in flight lives. Multi-batch work is tracked in
docs/programs/ (start at docs/programs/README.md): each program has a
PROGRAM.md with a "Resume here" section and a machine-checked
tracks.yaml. A session resuming a program reads only those two files and
follows their pointers — chat history is never required.
How sessions work. CLAUDE.md is the canonical operating manual for
Claude Code sessions; AGENTS.md is its condensed derivative for Codex-CLI
sessions and points back at CLAUDE.md for anything that can drift rather
than restating it. Every session ends through a handoff gate
(scripts/handoff/handoff-check.mjs, installed as a git hook) that refuses
to let a session leave uncommitted work, an unpushed branch, a stale
worktree, or code changes with no resume surface for the next session.
Batch work happens in an isolated git worktree, never the shared primary
checkout — see WORKTREES.md.
What CI checks, by category, not by exhaustive list (see
.github/workflows/ci.yml for the exact, current set): an ephemeral-
Postgres integration lane for money- and audit-chain-critical behavior;
typecheck and lint across apps/api and every published package; capability
manifest structural and fixture-consistency gates; framework-package
integrity (a published *-strale package must contain real code from the
framework it claims to integrate with); a family of content-as-data
registers, each with its own checker and generated index — research
(docs/research/), design tokens (design/), the environment-variable
manifest (config/), the model-id registry, the public claims register
(docs/company/claims.yaml), program track registers
(docs/programs/*/tracks.yaml), and this repository's own docs/
structure (docs:check, archive:index -- --check); and the session-
handoff gate itself. Every one of these checkers plants a failure case in a
throwaway fixture and proves it fails before the fix — see
docs/company/LESSONS.md family F5.
archive/ holds closed, historical, and superseded material — see
archive/README.md for what each subtree holds, generated (with hand-
written prose above it) by npm run archive:index. handoff/ holds one
file per session's end-of-session record; handoff/README.md is a
generated, reverse-chronological index of all of them by date and stated
intent. Neither directory is required reading to resume work — the program
register and docs/project/START-HERE.md are.
MIT
來源：README.md，提交 9743a24
Check connection
Checks that the Strale API is reachable and the MCP server is running. Call this before a series of capability executions to verify connectivity, or when troubleshooting connection issues. Returns server status, version, tool count, capability count, solution count, and a timestamp. No API key required.
無需輸入參數。
Get started with Strale
Explains how to start using Strale and what is available without credentials. Call this on first connection. Returns the current free-tier capability list with example inputs, the pay-per-call (x402) route that needs no signup, and how to reach the full registry. No API key required.
無需輸入參數。
Run a Strale tool
Executes a Strale capability by slug and returns the result. Use this when you need to perform any verification, validation, lookup, or data extraction from the capability registry. Inputs follow the capability's own schema, which strale_search lists; the API is documented at https://strale.io/docs. Call strale_search first to find the right slug and required input fields. Returns a result object with the capability output, latency, price charged, and data provenance. Several capabilities are free without an API key (monthly per-IP allowance; see GET /v1/platform/facts, static.free_tier_monthly_limit) — strale_search reports which. Paid capabilities debit from the wallet — check strale_balance first for high-value calls.
slug必填inputs必填max_price_centsSearch tools and bundles
Searches the Strale capability registry by keyword, category, or natural language query. Use this when you need to find the right capability for a task but don't know the exact slug. Returns matching capabilities and solutions ranked by relevance, each with slug, name, description, category, and price in EUR cents. The registry spans company data, compliance, finance, web intelligence, and developer tools. No API key required to search.
query必填offsetcategoryRead wallet balance
Returns the current Strale wallet balance. Call this before executing paid capabilities to verify sufficient funds, or after a series of calls to reconcile spend. Returns balance in EUR cents (integer) and formatted EUR string. Requires an API key — returns an auth instruction if none is configured.
無需輸入參數。
Read testing and source notes
Explains testing modes, source context and transaction retrieval. No API key required.
無需輸入參數。
Read current test and availability signals
Reads current public test results for a tool or bundle: badge, tested flag, recent pass rate and last-tested time where available. Use the catalogue for inputs, limitations and sources. No API key required.
slug必填typeRead a transaction record
Retrieve a past execution record by transaction ID. Returns inputs, outputs, latency, price, data provenance, success/failure status, and failure categorization. Use this to inspect what a previous strale_execute call returned, debug failures, or provide an audit trail. Free-tier transactions are accessible by ID without an API key.
transaction_id必填Check on-chain counterparty
Returns a decision-ready answer about an on-chain counterparty (wallet, smart contract, token, DeFi protocol, or bridge) in a single call. Surfaces verdict (proceed/review/block/insufficient_evidence), reason_codes (machine-parsable UPPERCASE_SNAKE_CASE), critical_flags, suggested_action, evidence map (sanctions, mixer-graded, scam-cluster, wallet-history, token-safety, contract-verification, protocol-risk, EAS attestations, ERC-8004 reputation, more), and a sidecar audit_url. Two modes: 'outbound' (agent vetting recipient pre-payment, full evaluator set, 8s budget) or 'reverse-call' (service publisher gating an inbound x402 buyer in real-time, critical evaluators only, limited evaluator set). Use before any agent transacts on-chain — sending value, swapping, staking, minting, bridging, or interacting with a contract.
modechainactiontarget必填agent_idamount_usdtarget_typecaller_jurisdiction已滿足適用檢查項的 100%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
{ "mcpServers": { "strale": { "type": "streamableHttp", "url": "https://api.strale.io/mcp?src=gh-readme", "headers": { "Authorization": "Bearer sk_live_your_key_here" } } }}npm install straleioimport Strale from "straleio";
const strale = new Strale({ apiKey: process.env.STRALE_API_KEY });const result = await strale.do("eu-vat-validate", { vat_number: "SE556000000001" });pip install straleiofrom straleio import Strale
strale = Strale(api_key="your_api_key")result = strale.do("eu-vat-validate", {"vat_number": "SE556000000001"})GET https://api.strale.io/x402/catalog?src=gh-readmeGET https://api.strale.io/.well-known/x402.jsonGET https://api.strale.io/v1/capabilities/vat-validatestrale/├── apps/api/ Hono API server: routes, capability executors,│ Drizzle schema + queries, Stripe/matching/auth│ helpers. drizzle/ holds the migration history.├── packages/ Published SDKs and framework integrations (see the│ table above) plus internal workspace packages.├── manifests/ One YAML file per live capability: pricing, data│ source, field-reliability declarations, test│ fixtures. The onboarding pipeline│ (apps/api/scripts/onboard.ts) is the only│ sanctioned way a capability enters the system —│ see CLAUDE.md's Capability Onboarding Protocol.├── design/ Design tokens as data (colors, type, spacing) —│ one active file per surface, candidates carry a│ status, promotion is a decision plus a file swap.├── config/ Cross-cutting configuration as data, e.g. the│ environment-variable manifest every process.env│ read is registered against.└── scripts/ Repo-root tooling: the checkers behind every `npm run *:check` script, the session-handoff gate, and one-off operator scripts.