mcpField
F
Factanker

Factanker

VerifiedFeaturedRemote
factanker.comAI & Agents0Updated 8w ago

About Factanker

FACTANKER is a read-only data service for AI systems and researchers working with US companies, banks, nonprofits, and federal spending. Its facts link to official filings and include citation details for tracing each value.

Key features

  1. 01Curated queries for financial data
  2. 02Resolve official entity identifiers
  3. 03Retrieve and search cited facts
  4. 04Inspect remote MCP server history

Use cases

  1. 01Check company figures against SEC filings
  2. 02Review bank and nonprofit financial metrics
  3. 03Trace federal spending and contract dependency

MCP support

FACTANKER exposes evidence lookup and query tools through a streamable HTTP MCP endpoint at https://factanker.com/mcp. MCP clients can retrieve facts with filing references and stable citation URLs.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://factanker.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

11
ParameterTypeRequiredDescription
paramsobjectNoTemplate parameters, e.g. {"cik":"320193","metric":"revenue","year_from":2023}
templateenumYesorg_profile | search_org | company_financials | bank_metrics | nonprofit_financials | nonprofit_profile | org_changes | peer_companies | company_financials_eu | peer_percentiles | metric_for_tickers | sector_summary | gov_top_recipients | gov_dependency | peer_ebitda | peer_ebitda_margin_percentiles | peer_working_capital | peer_wc_percentiles | bank_percentiles | bank_ranking

Details

From the project README

FACTANKER — MCP Server

The independent proof layer for AI answers. When an AI states a number, FACTANKER is the evidence behind it: every figure traces to an official primary record, from SEC filings to FFIEC call reports, IRS 990s and USAspending awards. FACTANKER does not fact-check news or opinions; it anchors numbers in filings.

1.18B+ evidence-backed facts about US companies, banks, nonprofits and federal spending. Every value carries its evidence: filing reference (e.g. SEC accession number), retrieval timestamp, license and a stable citation URL. Read-only, no API key, no auth, no signup.

Connect (Claude, ChatGPT, any MCP client)

{
  "mcpServers": {
    "factanker": {
      "type": "streamable-http",
      "url": "https://factanker.com/mcp"
    }
  }
}

Tools

ToolWhat it does
query_templateCurated queries: company financials (SEC), bank metrics (FFIEC), nonprofit finances (IRS 990), peer percentiles, federal-contract dependency. Answers include the executed query, result count, scope and an explicit not_claimed section.
list_templatesSelf-description of all templates: parameters, required fields, allowed enum values.
lookup_entityResolve a company, bank or nonprofit to all its official identifiers (CIK, LEI, EIN, UEI, RSSD, FDIC cert, NPI, QID).
get_factsAll current evidence-backed facts for one entity, each with source, filing reference and citable fact_url.
search_factsFull-text search across entities and predicates.
mcp_server_historyClaim history of remote MCP servers from FACTANKER's own periodic probes.

REST (same data, plain URLs)

curl 'https://factanker.com/api/query/company_financials?cik=320193&metric=revenue&year_from=2023'
curl 'https://factanker.com/api/lookup_entity?q=cik:0000936468'

Every fact URL serves JSON under Accept: application/json (same URL as HTML).

Citation

Please cite answers with their fact_url so readers can inspect the evidence: Cite as: FACTANKER, https://factanker.com/fact/<id>

Operator

Enerlio GmbH · [email protected] · https://factanker.com/impressum

The server code is operated privately; this repository is the public description and quickstart for the MCP endpoint.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.