Skip to main content
Glama

primary-sources-mcp

CI Secret Scan MCP Tool Definition Quality License: MIT

Free primary-source APIs for AI agents. SEC EDGAR, World Bank, GDELT, DATA.GOV.HK, HKMA, the official MCP Registry, UK Companies House, FRED and Jina Reader — as MCP tools, each result wrapped in a { source, retrievedAt, data } provenance envelope.

Zero runtime dependencies. Node >= 20. 12 tools, 10 of them keyless.

Quick start

{
  "mcp": {
    "primary-sources": {
      "type": "local",
      "command": ["npx", "-y", "@simonmak-ascent/primary-sources-mcp"],
      "enabled": true,
      "timeout": 120000
    }
  }
}

Hosted (Streamable HTTP): https://primary-sources-mcp.vercel.app/mcp.

Related MCP server: Agent Signals MCP

Tools

Tool

Source

Key

sec_edgar_fulltext

SEC EDGAR full-text search (US filings)

none

sec_edgar_company

SEC EDGAR registrant + recent filings

none

world_bank_indicator

World Bank development indicators

none

gdelt_news

GDELT DOC 2.0 global news

none

hk_open_data_search

DATA.GOV.HK catalogue search

none

hk_open_data_filter

DATA.GOV.HK filter API

none

hkma

Hong Kong Monetary Authority public API

none

mcp_registry_search

Official MCP Registry

none

jina_read

Jina Reader (URL → markdown)

none (free tier)

companies_house_search

UK Companies House search

COMPANIES_HOUSE_API_KEY

companies_house_company

UK Companies House record

COMPANIES_HOUSE_API_KEY

fred_series

St. Louis Fed FRED series

FRED_API_KEY

Environment

Variable

Required

Purpose

RESEARCH_CONTACT

no

User-Agent contact string (politeness for SEC/GDELT).

COMPANIES_HOUSE_API_KEY

for 2 tools

Free key from Companies House.

FRED_API_KEY

for 1 tool

Free key from the St. Louis Fed.

Provenance

Every data tool returns text of the form:

{ "source": "World Bank Indicators", "retrievedAt": "2026-10-02T16:00:00.000Z", "data": { } }

so an agent can cite the origin and time of every fact.

Development

npm install
npm run typecheck
npm test
npm run build
node dist/index.js   # stdio MCP server

License

MIT — see LICENSE.

Available Tools

12 tools
companies_house_companyA

Fetch one UK company record by number (requires COMPANIES_HOUSE_API_KEY).

Inputs: number (required).

fred_seriesC

FRED economic series observations (requires FRED_API_KEY). Free key.

Inputs: seriesId (required), limit.

gdelt_newsC

GDELT global news article search/trends (free, no key). Great for news volume and cross-outlet coverage.

Inputs: query (required), mode, timespan, maxrecords.

hkmaC

Hong Kong Monetary Authority public API (free, no key). e.g. path market-data-and-statistics/daily-monetary-statistics/daily-figures-interbank-liquidity.

Inputs: path (required), params.

hk_open_data_filterB

Query a DATA.GOV.HK dataset resource with filters (free, no key). filters is an array of arrays [column,"op",[values]].

Inputs: resource (required), filters, section.

jina_readA

Fetch any URL as clean markdown via Jina Reader (free tier, no key). Extraction fallback.

Inputs: url (required).

sec_edgar_companyC

US SEC registrant profile + recent filings by ticker or CIK (free, no key).

Inputs: tickerOrCik (required).

sec_edgar_fulltextB

Full-text search US SEC EDGAR filings (free, no key). Use for primary-source corporate disclosures.

Inputs: query (required), forms, dateRange.

world_bank_indicatorC

World Bank development indicator time series (free, no key). e.g. country HK, indicator NY.GDP.MKTP.CD.

Inputs: country (required), indicator (required), date, perPage.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 12 tools

    Disambiguation4/5

    Most tools target distinct providers/actions (sec_edgar_fulltext vs sec_edgar_company, companies_house_search vs companies_house_company). The main soft spot is hk_open_data_search vs hk_open_data_filter, where catalogue-level search versus dataset-level filtered query could be confused, and jina_read acts as a generic fallback that overlaps any fetch need.

    Naming Consistency4/5

    Names consistently use snake_case with a provider-prefixed pattern (sec_edgar_*, hk_open_data_*, companies_house_*). A few tools (hkma, gdelt_news, fred_series, jina_read) drop the explicit action verb, creating minor deviation but still readable and predictable.

    Tool Count5/5

    12 tools is well within the healthy 3-15 range for a multi-source data aggregator. Each tool maps to a recognizable external API or resource, so no entries feel redundant or padded.

    Completeness4/5

    The server covers a broad set of primary sources (US SEC, UK Companies House, HK open data, HKMA, World Bank, FRED, GDELT) with search+detail pairs where relevant. Minor gaps exist—no dedicated detail endpoints for World Bank/FRED/GDELT and no generic structured-data fetch beyond jina_read—but core workflows are workable.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables AI agents to access SEC EDGAR filings, US Treasury rates, BLS labor statistics, and economic indicators without API keys.
      6
      26 npm
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      One MCP server that gives AI agents nine live data tools — company hiring signals, SEC filings, academic papers, GitHub repos, Hacker News, Stack Overflow, clinical trials, Federal Register, and global news — all as flat, citation-ready JSON with pay-per-result billing.
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to perform company due diligence, OSINT, competitive, SEO, market, finance and regulatory research through a single MCP endpoint exposing 45 tools that draw on official public APIs, local D1 mirrors, and optional self-hosted sidecars. Every response is labelled by evidence class, so inferred estimates are never presented as equivalent to official data.
      6 npm
      MIT