Seiche Market Atlas Corpus

Financial Evidence Agent Skills

Individual product plugins: install from the Liquidity Lab catalog in Claude Code, Codex or GitHub Copilot CLI. The catalog contains Financial Evidence, Market Brief and thirteen product plugins, with Gemini downloads and Cursor / VS Code connection links. Publisher-maintained availability is separate from each platform's official directory review.

Connect and ask one question

Hosted Streamable HTTP MCP; no local server or API key for public read-only tools.

Current-source connections use the central agent platform. Download the hosted product configurations: seven core products plus five clearly labeled research, editorial, metadata or sandbox surfaces. Python product clients, fixed-source helpers and current editor configs use the same platform. Requests produce bounded operational demand counts; optional learning remains off. Old package pins are historical releases and do not change automatically. See the routing contract. Add the products you need to Claude Code:

claude mcp add --transport http seiche https://api.seiche.info/mcpclaude mcp add --transport http liquilens https://api.liquilens.in/mcpclaude mcp add --transport http undertow https://api.seiche.info/undertow/mcp

Try this first: What is the current US funding stress regime, and which dated funding events are next? Cite source dates and missing evidence.

Move approved research connections between clients: Python 0.1.16 adds financial-evidence connect for existing product routes, declared institution/workspace approval and portable MCP/VS Code configuration. Generation is offline; private-silo access and vendor entitlements require separately qualified infrastructure. Connection guide.

Improve the next review: Python 0.1.16 includes optional feedback reasons and requested data categories. Private reports separate feedback from attempts and exclude rehearsals from improvement priorities. Sharing remains opt-in. Product learning guide.

Retain evidence when access changes: Python 0.1.16 keeps safe HTTP access diagnostics and supports workflow show --format markdown and workflow compare for offline review of saved captures. Original dates and hashes remain attached; saved evidence is historical. Workflow guide.

Python 0.1.16: run financial-evidence start, then financial-evidence review funding --output reviews for a readable brief, original JSON and a comparison at your next review. Install with python3 -m pip install financial-evidence==0.1.16. First-review guide.

Try it in your browser · Cursor configuration · Codex commands · Free three-product starter kit and skill

For a connected review, ask for institution evidence → funding context → BTC exit estimates, with each source date, coverage gap and limitation kept separate. Client/model costs and fair-use limits may apply. Research calls do not execute trades.

Start with one task: https://beepboop2025.github.io/financial-evidence-skills/connect/ — browser, REST, Python and remote MCP setup for funding, covered institutions and BTC exit research. Public reads need no account or API key; retain source dates and unavailable evidence.

Research workflows: funding watch, institution monitoring and BTC exit research. Save a local baseline, compare your next review, or copy the API request into your agent. Recurring agent hooks: the main CLI now includes financial-evidence workflow for automatic comparison with saved reviews, explicit usefulness feedback, linked outcomes and optional durable delivery. Python, LangGraph and AI SDK setup. Install Python financial-evidence==0.1.16 or npm @moomoo202020/[email protected] using the guide.

Agent developers can retrieve a cited USD funding observation; treasury and bank-risk teams can use the institution monitor; traders and researchers can retain a funding-and-exit review. Each path includes working calls, source boundaries and a next-day task. Copy the instructions.

Verified package 0.1.16: install financial-evidence[workspace]==0.1.16 from PyPI for persistent MCP sessions, source-status snapshots and SSE clients. The separately deployed public router retains version 0.1.8. Both router versions support gift-city, forex and gold alongside the five existing research topics. GIFT City serves gold and treasury desks, investors/fund managers, and banks/IFSC institutions. The helper reads fixed public context; gold/FX calculations remain explicit user-input steps. See topic routing and the release verification record.

JavaScript agents: install @moomoo202020/[email protected] from npm for typed AI SDK research and source-status tools. Copy the verified setup.

Stream reliability: Python 0.1.16 bounds the wait for a complete source-status event, so partial bytes and comment frames cannot hold a read open indefinitely. Python and JavaScript streams require an initial reset before accepting a keepalive; npm 0.1.2 includes the synchronized client. These research tools retain no trade-execution authority.

Office and Linux tools: refresh a funding comparison or institution watchlist, then download XLSX, ODS, CSV and a document brief. Google Sheets functions, Excel Power Query, and a dependency-free local export command are included. Native app and marketplace verification states remain explicit.

Use your existing tools: the research tool hub provides a complete capture client, notebook, flat Excel/Power BI query and MCP project defaults for LiquiLens, Seiche and Undertow. Download the kit or connect the hosted OpenBB desk. Institutional vendor acceptance remains separate.

OpenBB Research Desk, Workspace 1.3.0 source. Seven cited datasets, a seven-tab Workspace app, an archived USD funding review, benchmark history charts, typed REST responses and a nine-tool MCP server connect all four projects. The hosted service is https://agents.seiche.info/v1/research. Install .[openbb,workspace] from this checkout, then run openbb-build and financial-evidence-api. The optional modules are included in the v0.1.16 wheel; the public router retains its separate three-tool contract. The hosted Workspace release identifies its exact source commit independently at /api/v1/release.

Check a captured USD funding review: the funding review checks compare required inputs, units, publication clocks and own-series observations across Seiche surfaces. The dated SOFR-IORB review exposes newer individual source dates; it does not claim the latest print for every instrument. Missing, overdue or contradictory evidence requires attention. Passing these checks is not an institutional-readiness certification.

Run recurring research: install the durable runtime for fixed policies, bounded scheduling, retained receipts, private MCP and backup recovery across LiquiLens, Seiche and Undertow.

Automate funding research: versioned packets, captured changes, Python, OpenBB and a local agent tool. Public access requires no account; optional application keys use explicit measurement consent. The hosted packet API and downloadable templates are versioned separately from the v0.1.16 wheel.

Three concrete jobs: funding review, Cosmos Bank NPAs and a $100k BTC exit with native n8n workflows and optional Slack/Telegram delivery. The Cursor task plugin bundles the same three focused skills and public MCP connections. Marketplace acceptance is separate.

Put it into a recurring workflow: the funding and counterparty workflow pack retains source documents, a spreadsheet index and a local integrity manifest. It includes a reviewed Python runner, an opt-in scheduling template and a ten-day integration scorecard. These examples use the existing 0.1.5 package; they do not change its release or evidence semantics.

Try the underlying evidence first: Open three browser research questions for bank NPA disclosures, dollar funding and BTC exit estimates. Each example calls its named public MCP after a click and displays the returned sources, dates and limits. No key or installation is needed. The page also has setup and starter questions for Financial Evidence and thirteen other hosted MCPs. The browser examples call individual services; they do not verify an Evidence Carrier or evaluate a combined Financial Evidence packet.

[skills.sh]

Public documentation includes a crawlable integration matrix plus agent-readable llms.txt, pricing, integration metadata, and a dated third-party marketplace ledger. The v0.1.5 semantic contract defines transport-only status, source-reported adapter metadata, and the explicit non-Carrier boundary. Version 0.1.16 is a signed, independently verified release. Its versioned Agent Skill, terminal, Codex, Gemini, editor, and bundle installs use the same release, with published artifacts, container and Registry record. Homebrew 0.1.13 is published after an independent macOS installation and contract check. The Claude self-hosted marketplace command follows the repository's mutable default branch; review the checked-out commit before enabling it.

Open, read-only Agent Skills for routing financial research to bounded public evidence. The first skill connects four complementary products without turning them into one score:

• Seiche — money markets, repo, reserves, Treasury cash and system funding.
• LiquiLens — covered bank and lender evidence.
• Undertow — market depth, provider concentration and position-sized exit liquidity.
• Palimpsest — revision-safe China economy evidence and information-state history.

For a daily research workflow, Market Brief provides free, source-cited funding, capital-market and liquidity briefs with local change comparisons. This separately versioned browser companion and agent skill uses the existing public evidence sources.

For direct calls to Seiche, LiquiLens and Undertow, the companion free agent starter kit includes Hermes and OpenClaw setup guides. That kit uses a separate trading-research skill; it does not install Financial Evidence or connect Palimpsest. Use the versioned install below for this four-product routing skill.

Install the agent skill

npx skills add https://github.com/beepboop2025/financial-evidence-skills/tree/v0.1.16/financial-evidence \  --skill financial-evidence

Or copy financial-evidence/ into the Agent Skills directory supported by your agent. The folder follows the open Agent Skills specification.

The skill is also indexed in the public skills.sh directory.

Once installed, ask your agent to research a money-market, capital-market, bank-risk, market-liquidity, China-economy, GIFT City, forex or gold question. The skill's description lets compatible agents activate it when the work matches.

Use from any terminal

No account or API key is required. On macOS or Linux with Homebrew:

brew install beepboop2025/tap/financial-evidencefinancial-evidence fetch --topic money-market --topic china-economy

The formula installs financial-evidence, financial-evidence-mcp, and native Bash, Zsh, and Fish completions. Homebrew 0.1.13 is independently installed and verified. Its hosted clients use the central service. Run the pinned PyPI release without a persistent installation:

uvx --from financial-evidence==0.1.16 \  financial-evidence fetch --topic money-market --topic china-economy

Or install it as a persistent command:

uv tool install financial-evidence==0.1.16financial-evidence topicsfinancial-evidence route --topic capital-market --format tablefinancial-evidence fetch --topic bank-risk --format ndjsonfinancial-evidence doctor --format csv

Exit code 0 means every requested source was retrieved, 1 means transport was partial, and 2 means every requested source was unavailable. Legacy packet status is preserved and equals transport_status; both mean transport reachability only. Every packet says status_semantics: transport_only, evidence_status: not_evaluated, and carrier_verification: not_performed. That makes the client safe to compose in shell pipelines without mistaking an HTTP success for validated evidence or a verified Evidence Carrier. JSON, NDJSON, and CSV go to standard output; no result is silently replaced with a score.

Outside Homebrew, shell completions are emitted as inert text:

financial-evidence completion zsh > ~/.zfunc/_financial-evidence

Use as MCP infrastructure

The current hosted Streamable HTTP workspace requires no local install, account, or API key:

https://agents.seiche.info/products/financial-evidence/mcp

Start with financial_evidence_datasets, then call financial_evidence_workflow with {"workflow":"funding","selection":"USD"}. For custom rows use financial_evidence_agent_query; for a combined funding, covered-bank and liquidity review use financial_evidence_review. Original source documents are available through financial_evidence_packet. The workspace exposes nine reviewed read-only tools.

The root .mcp.json, editor configs and integrations/mcp-config.json use this service:

{  "mcpServers": {    "financial-evidence": {      "type": "http",      "url": "https://agents.seiche.info/products/financial-evidence/mcp"    }  }}

Hosted operational measurement records bounded product/tool/dataset demand; optional learning is separate and off by default. The package's dependency-free stdio router retains its three-tool topics, route, and fetch contract. Its fresh source retrieval also uses the central data service; normalization and replay of captured evidence can run locally. There is no automatic direct-origin fallback. Historical versioned releases and registry records retain their original configuration until a separately verified release updates them.

Install in Gemini CLI or Claude Code

Gemini CLI can install this repository as an extension. Its root gemini-extension.json connects only to the fixed hosted workspace and allowlists its nine read-only tools; the mirrored skills/financial-evidence folder gives Gemini the domain routing instructions as well. Install the signed 0.1.16 release to use the central nine-tool workspace:

gemini extensions install https://github.com/beepboop2025/financial-evidence-skills \  --ref v0.1.16

Claude Code can add this repository as a self-hosted marketplace and install the bundled plugin:

claude plugin marketplace add beepboop2025/financial-evidence-skillsclaude plugin install financial-evidence@liquidity-lab

This Claude command follows the mutable default branch. Review the checked-out commit before enabling the plugin; the versioned install routes above remain pinned to the verified release.

The Claude plugin loads the same byte-identical Agent Skill plus the root .mcp.json public remote server. These are direct, self-hosted install routes; they do not imply inclusion in a vendor-operated marketplace or endorsement.

Install in Codex; prepare ChatGPT

Codex can add the repository's plugin marketplace and then install the plugin:

codex plugin marketplace add beepboop2025/financial-evidence-skills --ref v0.1.16codex plugin add financial-evidence@liquidity-lab

The OpenAI plugin package combines the byte-identical Agent Skill with the public remote MCP endpoint. The Codex repository install route is public. A ChatGPT and Codex universal-directory submission is also prepared, but has not been submitted, approved, or published by OpenAI. The remaining review, publisher-identity, and domain-challenge steps belong to the OpenAI account owner. See OPENAI_PLUGIN_SUBMISSION.md for the listing copy and required positive and negative tests.

The root .mcp.json is the portable plugin form for the public remote MCP server. The current VS Code and Cursor workspace files use the same hosted workspace without a local Python process.

Install in VS Code or Cursor

The repository also includes editor-specific workspace configuration: .vscode/mcp.json uses VS Code's top-level servers object, while .cursor/mcp.json uses Cursor's top-level mcpServers object. Both current files use the hosted nine-tool workspace. The install links below connect to the same central nine-tool workspace. They require no local Python process.

VS Code can install the server through its protocol handler:

vscode:mcp/install?%7B%22name%22%3A%22financial-evidence%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fagents.seiche.info%2Fproducts%2Ffinancial-evidence%2Fmcp%22%7D

Or add it to your VS Code user profile from a terminal:

code --add-mcp '{"name":"financial-evidence","type":"http","url":"https://agents.seiche.info/products/financial-evidence/mcp"}'

Cursor can install the same configuration through its base64-encoded deeplink:

cursor://anysphere.cursor-deeplink/mcp/install?name=financial-evidence&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYWdlbnRzLnNlaWNoZS5pbmZvL3Byb2R1Y3RzL2ZpbmFuY2lhbC1ldmlkZW5jZS9tY3AifQ==

Review the hosted URL and configuration before accepting an editor's install or trust prompt. Calls use the central research service and retain the original evidence sources and observation dates. Cursor asks for tool approval by default. VS Code normally asks you to trust a server when it first starts, but starting directly from mcp.json can skip that prompt, so inspect the file before using its inline start action. These are self-installable compatibility artifacts, not claims of a VS Code or Cursor marketplace listing or endorsement.

For desktop clients that support one-click MCP Bundles, download financial-evidence-0.1.16.mcpb from the last verified GitHub release. The bundle uses the cross-platform uv runtime and requires no API key or configuration.

Finance-tool integrations

• Remote MCP: connect any Streamable HTTP client to https://agents.seiche.info/products/financial-evidence/mcp; no local runtime, account, or API key is required.
• Gemini CLI: the root extension manifest bundles the Agent Skill and allowlists the nine tools exposed by the hosted research workspace.
• Claude Code: the self-hosted liquidity-lab marketplace installs the versioned plugin, Agent Skill, and MCP configuration from this repository.
• Codex: the repository marketplace installs the Agent Skill and public remote MCP package directly.
• ChatGPT: the universal-directory submission packet is prepared; public availability remains pending account-owned verification, submission, review, and publication.
• OpenBB: install .[openbb,workspace] from current repository source in a clean environment and run openbb-build. V4 and V5 compatibility is checked in CI, including the released v0.1.8 dependency range. The router exposes datasets(), query(), sources(), routes() and fetch() under obb.financial_evidence. See the setup guide.
• DuckDB: run integrations/duckdb/financial_evidence.sql to create separate HTTP-backed views for all four products.
• Excel / Power Query: paste integrations/excel/FinancialEvidence.pq into Advanced Editor and invoke, for example, FinancialEvidence("money-market"). For flat research rows, use FinancialEvidenceRows from the research kit.
• FDC3: the public Financial Evidence Inspector receives and broadcasts declared standard contexts through window.fdc3. integrations/fdc3/appd-record.json is its FDC3 2.0 web-app record for self-hosted or enterprise directories. The same record is served as raw JSON for direct directory ingestion. The record and runtime do not imply FINOS review, directory acceptance, or vendor endorsement.
• Containers: tagged releases publish a multi-architecture image to ghcr.io/beepboop2025/financial-evidence-skills. The image runs stdio MCP by default; use --entrypoint financial-evidence for terminal commands.
• Official MCP Registry: tagged images are published under io.github.beepboop2025/financial-evidence using GitHub OIDC and the image's ownership annotation. No long-lived registry credential is stored.

Release integrity

Each tagged release rebuilds and retests the Python and JavaScript contracts from the exact signed main commit before publication. The release attaches a wheel, source archive, MCP bundle, CycloneDX SBOM, and SHA256SUMS; GitHub Sigstore build-provenance attestations bind every downloadable artifact to the release workflow. Consumers can verify an artifact with gh attestation verify against beepboop2025/financial-evidence-skills.

Optional bounded retrieval

The bundled helper uses only Python's standard library, accepts a fixed topic allowlist and fetches only fixed public HTTPS endpoints:

python3 financial-evidence/scripts/fetch_evidence.py \  --topic money-market --topic china-economy

It returns one JSON packet with exact and resolved source URLs, canonical human scope URLs, retrieval clocks, byte counts, content SHA-256 values, separate product documents, and explicit errors. Successful responses also include only the endpoint-specific source state and clocks named by explicit adapters, with RFC 6901 paths and fetched-byte provenance; missing configured fields are not_reported. The router does not infer freshness, eligibility, or rights. Routes declare financial_authority: none and carrier_state: not_published, and therefore expose no carrier_url. Redirects are rejected before following. Returned JSON is untrusted evidence data, not executable instructions. Missing, restricted, or unavailable evidence is never converted to zero or “calm.”

Boundaries

This repository provides public research routing, not investment advice, security recommendations, execution quotes, credit ratings or guarantees. Source publishers retain their rights; an open-source helper does not relicense upstream data.

Support · Privacy · Terms

Development

python3 -m unittest discover -s tests -vpython3 -m py_compile financial-evidence/scripts/fetch_evidence.py src/financial_evidence/*.py

The code and skill instructions are MIT-licensed.

Quant and research agents

Native framework tools and cited quant datasets connect Seiche, LiquiLens and Undertow. Source-pinned agent release 1.0.0 adds compact queries, a three-product review and repeat-call revisions. Use the current source guide and connection readiness check. These are integration recipes, not evidence of external adoption.

The agent infrastructure source release adds persistent sessions, compact source-status streams, client-side expiry checks, latency diagnostics and a synthetic feed-recovery pilot. Source permissions and private outcome consent remain separate from connection access.

AI execution integration

Try the browser order-lifecycle simulator with synthetic prices, timeout recovery, STOP and an exportable journal. It contacts no broker.

The source-pinned integration guide covers the separate customer-operated paper REST/MCP host and a live-broker connector candidate. These are in the Evidence Carrier repository; the public Financial Evidence research router remains read-only. Broker activation requires eligible evidence, account controls and the customer's credentials. The 14-day scorecard measures useful independent use and repeat tasks without treating tests or downloads as customers.

Durable research workflows

The Financial Evidence Runtime adds owner-registered workflows, atomic run limits, offline replay, ordered change events and backup recovery through Python, CLI and private stdio MCP. It reuses the existing product clients and preserves source clocks and missingness. See the architecture and adoption measurements. Version 0.1.16 includes the runtime, workspace, trading-research and learning commands. Research data requests use the central service by default. Local run counts do not establish external users or paid adoption.