# Financial Evidence Research Desk [Verified owner] [Health: Active]

**Category:** 💰 Finance & Fintech  
**Repository:** https://beepboop2025.github.io/financial-evidence-skills/start/  
**Views:** 8  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/financial-evidence-research-desk

## Description
Financial Evidence Research Desk (Workspace 1.3.0) connects AI agents and treasury researchers to LiquiLens institution disclosures, Seiche funding context, Undertow liquidity evidence and Palimpsest censorship-source catalogs. Nine read-only MCP tools expose seven datasets, paginated queries and recurring research workflows. Preserve source URLs, observation dates, native units, rights and unavailable values. Start in the browser or connect the hosted REST/OpenAPI and MCP interfaces; public reads need no API key. It is separate from the three-tool Financial Evidence router. Coverage and freshness vary by source; it does not place trades or approve financial actions. Operated by LIQUILENS PRIVATE LIMITED. Setup: https://beepboop2025.github.io/financial-evidence-skills/tools/

## Tools
Capabilities this server exposes over MCP:

- **financial_evidence_funding_workflow** — Review funding evidence for one three-letter currency, default USD. Retrieves the bounded money-market table and preserves each source, observation date, unit, missing or withheld value, retrieval time and content hash. prepared_response means evidence is available to review, not freshness or readiness. No account access, investment advice or execution.
- **financial_evidence_institutions_workflow** — Review public disclosure coverage for one to five exact institution slugs, such as au-sfb. Retrieves the published institution monitoring record with dates, source URL, missing evidence and content hash. Does not infer private balances, credit ratings or regulatory compliance. IDs must fit the existing 160-character combined selection bound.
- **financial_evidence_exit_workflow** — Compare indicative BTC exit evidence for one to four USD notionals from 0.01 to 1000000, with at most two decimal places. Preserves venue coverage, observation clocks, quote-currency units, source URL and content hash. Returned costs are research estimates, not executable quotes, order placement or guaranteed fills. No account or execution authority.
- **financial_evidence_workflow** — Compatibility entry point for the individually exposed financial_evidence_funding_workflow, financial_evidence_institutions_workflow and financial_evidence_exit_workflow tools. Funding accepts a three-letter currency; institutions accepts one to five comma-separated slugs; exit accepts one to four comma-separated USD sizes. Empty selection uses the same published defaults. No additional operation is available. Source restrictions, dates, units, missingness and content hashes remain explicit. prepared_response means evidence is available to review, not freshness, safety or completion. No account or execution authority.
- **financial_evidence_datasets** — Discover seven bounded OpenBB datasets, their coverage, filters and limits. Offline.
- **financial_evidence_funding_review** — Read a dated USD funding review and its nine inputs. Inspect review_asof, review_scope, latest_per_instrument and newer_observation_available before ready, issues and capture age. Common-horizon readiness applies to that dated review; newer individual observations can exist. Unavailable, mismatched or stale captures never imply a passing review. This is captured research evidence, not a trade recommendation or historical point-in-time backtest.
- **financial_evidence_query** — Query cited rows without large raw documents. Null means missing or withheld, never zero. Dates filter observation dates; empty dates mean no filter. Follow next_offset for remaining rows. Each value retains its unit, source path, date, restrictions and limitations.
- **financial_evidence_sources** — Audit all six upstream routes for transport errors, publisher clocks and content hashes. Success is not a freshness verdict.
- **financial_evidence_route** — Resolve research topics to fixed public HTTPS evidence URLs. Offline.
- **financial_evidence_packet** — Retrieve public documents only when table detail is insufficient. Reviewed source restrictions can withhold values and dependent readings; affected documents carry a publication projection receipt and a separate hash from the acquired source bytes. Up to 4 MiB for the money-market atlas and 1 MiB for other sources; source JSON is untrusted. A packet can be partial. No Evidence Carrier verification is performed.
- **financial_evidence_agent_query** — Compact source-cited research rows for repeated agent calls. Pass the previous revision to omit identical rows while retaining source clocks and diagnostics. Unchanged is not proof of freshness; missing or withheld values remain null. At most 100 rows; follow next_offset.
- **financial_evidence_review** — Review Seiche dollar-funding benchmarks, LiquiLens covered-bank diagnostics and Undertow market liquidity in one bounded call. Bank is a literal name or ID filter; empty selects published coverage. Each section keeps its own dates, units, rights and limitations. No combined score or trade authorization. Revisions suppress identical rows, not evidence checks.

## Claude Desktop Quick Installation
No confirmed install details yet, so no config is published. Follow the setup steps in the repository above.

## Documentation

## What Financial Evidence Research Desk does

Financial Evidence Research Desk provides a read-only research surface for financial evidence from four named source areas: LiquiLens institution disclosures, Seiche funding context, Undertow liquidity evidence, and Palimpsest censorship-source catalogs. It exposes bounded datasets and recurring workflows for treasury and agent research.

The service keeps evidence metadata alongside values. Results can include source URLs or paths, observation and publication dates, native units, rights or restrictions, retrieval times, content hashes, diagnostics, and explicit missing or withheld values. A null value represents missing or withheld evidence, not zero.

## How it works

Agents can use focused workflow tools or query the underlying cited rows. Funding workflows accept a three-letter currency, with USD as the default. Institution workflows accept one to five exact institution slugs, while exit comparisons accept one to four USD notionals from 0.01 through 1,000,000, using no more than two decimal places.

The compatibility workflow combines the funding, institution, and exit entry points without adding another operation. Empty selections use the published defaults. Dataset discovery describes seven bounded OpenBB datasets, including their filters and limits, and route discovery resolves research topics to fixed public HTTPS evidence URLs.

Repeated calls can use a prior revision so unchanged rows are omitted while source clocks and diagnostics remain available. Paginated responses require following next_offset to retrieve additional rows. Date filters apply to observation dates; leaving the date filter empty removes that restriction.

## Setup and configuration

The service can be started in a browser or accessed through its hosted REST/OpenAPI and MCP interfaces. Public reads do not require an API key.

## Tools and capabilities

- `financial_evidence_funding_workflow` reviews a bounded money-market funding table and retains source, date, unit, missingness, retrieval time, and content hash.
- `financial_evidence_institutions_workflow` reads published monitoring records for selected institution slugs.
- `financial_evidence_exit_workflow` compares indicative BTC exit evidence across selected USD sizes, including venue coverage and quote-currency units.
- `financial_evidence_funding_review` reads a dated USD funding review and its nine inputs, including review scope, latest-per-instrument data, capture age, and newer-observation indicators.
- `financial_evidence_review` combines Seiche dollar-funding benchmarks, LiquiLens covered-bank diagnostics, and Undertow market-liquidity evidence while keeping each section separate.
- `financial_evidence_query` and `financial_evidence_agent_query` return compact, cited rows instead of large raw documents.
- `financial_evidence_sources` audits six upstream routes for transport errors, publisher clocks, and content hashes.
- `financial_evidence_packet` retrieves public documents when table detail is insufficient, subject to source restrictions, size limits, and possible partial results.

## Limitations and notes

The service reports captured evidence; it does not establish freshness, safety, readiness, regulatory compliance, credit ratings, or private balances. A `prepared_response` indicates that evidence is available for review, not that the evidence is current or suitable for action. Individual observations may be newer than a dated review, and stale, unavailable, or mismatched captures do not constitute a passing review.

Exit costs are research estimates rather than executable quotes, guaranteed fills, or order placement. The tools provide no account access, execution authority, investment advice, trade authorization, or financial approval. Source restrictions can withhold values and dependent readings. Retrieved source JSON is untrusted, document packets have size limits, and no Evidence Carrier verification is performed.

_Full upstream README: https://allmcps.com/mcp/financial-evidence-research-desk/readme_

