mcpbeat Sign in

Primary Sources MCP Server

not responding

Primary Sources is listed as active in the registry but did not answer our last check. It exposes 50 tools.

Free primary-source APIs (SEC EDGAR, World Bank, GDELT, HKMA, FRED) with provenance envelopes.

The linked repository no longer exists on GitHub — it was deleted or made private.

Uptime history 24 days of history · worst day 0%
24 days agonow
0.0%
Uptime 24h
0 of 92 checks
50
Tools
read from the server
90 ms
Response time
average over 24h
open, no key
Access
streamable-http

What changed 63

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 3 October 2026. No other catalogue keeps this.

3 Oct 38 tools appeared acra_sg_company, arxiv_search, ckan_search and 35 more
3 Oct 12 tool descriptions were rewritten companies_house_company, companies_house_search, fred_series and 9 more
3 Oct 12 tools changed the parameters they ask for companies_house_company, companies_house_search, fred_series and 9 more
3 Oct a tool changed version

Primary Sources does not always answer

Over the last week it answered 0.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.

run in your terminal
claude mcp add primary-sources-mcp --transport http https://primary-sources-mcp.vercel.app/mcp
Settings → Connectors → Add custom connector, then paste this address
https://primary-sources-mcp.vercel.app/mcp
~/.codex/config.toml
[mcp_servers.primary-sources-mcp]
url = "https://primary-sources-mcp.vercel.app/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "primary-sources-mcp": {
      "url": "https://primary-sources-mcp.vercel.app/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "primary-sources-mcp": {
      "type": "http",
      "url": "https://primary-sources-mcp.vercel.app/mcp"
    }
  }
}

Available tools 50

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

open
hk_open_data_filter
Query a DATA.GOV.HK dataset resource with structured filters (free, no key). Pass the resource URL from hk_open_data_search plus filters as an array of [column, operator, values] triplets. Use to extract rows from a specific HK dataset.
hk_open_data_search
Search the Hong Kong government open-data catalogue DATA.GOV.HK (free, no key). Returns dataset titles, notes, organizations and resource download URLs. Use to discover HK datasets; use hk_open_data_filter to query a resource.
open_library_search
Search Open Library for books (free, no key). Returns titles, authors, first-publish year, ISBNs and Open Library URLs. Use for bibliographic/book metadata; use gutendex_books for full public-domain texts.
open_meteo_forecast
Fetch current weather from Open-Meteo (free, no key). Returns current temperature, humidity, wind speed and weather code for a coordinate. Use for point weather data; use usgs_earthquakes for seismic events.
companies
companies_house_company
Fetch one UK company record by company number (requires COMPANIES_HOUSE_API_KEY). Returns the full Companies House profile object (registered office, officers summary, SIC, status). Use after companies_house_search. Free key required.
companies_house_search
Search the UK Companies House register by name (requires COMPANIES_HOUSE_API_KEY). Returns company number, status, type, address and a Companies House URL per hit. Use for UK entity existence/status; use companies_house_company to fetch one record by number. Free key required.
hkex
hkex_announcements
List Hong Kong listed-company announcements from HKEXnews by stock code (free, no key). Resolves a 5-digit code or company name to the internal HKEX stockId, queries the titleSearch servlet for a date range, and returns metadata plus a direct PDF link per filing. Use for HKEX/SEHK primary disclosures; use sec_edgar_fulltext for US filings. Category codes: 10000 Announcements, 20000 Circulars, 40000 Financial Statements/ESG, 50000 Next Day Disclosure, 51500 Monthly Returns.
hkex_company
Resolve a Hong Kong listed company and show its recent HKEXnews filings (free, no key). Returns the internal stockId, code, name, an HKEXnews filings URL, the headline category taxonomy and the 25 most recent filings. Use to identify/resolve an HK issuer before drilling into a filing; use hkex_announcements to filter by date or category.
sec
sec_edgar_company
US SEC registrant profile plus recent filings by ticker or CIK (free, no key). Resolves a ticker via EDGAR company_tickers.json, then returns name, CIK, SIC, a filings URL and the 25 most recent filings. Use when you know the ticker or CIK; use sec_edgar_fulltext for phrase search.
sec_edgar_fulltext
Full-text search US SEC EDGAR filings (free, no key). Searches the EDGAR full-text index and returns matching filings with form type, filing date, CIK and an Archives URL. Use for primary-source corporate disclosures when you have a phrase or company name but not a ticker. For a known ticker or CIK, prefer sec_edgar_company.
world
world_bank_country
Look up country reference metadata from the World Bank (free, no key). Returns ISO codes, name, region, income level, lending type and capital/lat-long. Use for canonical country/region metadata; use world_bank_indicator for time-series indicators.
world_bank_indicator
Fetch a World Bank development-indicator time series for one country (free, no key). Returns year/value observations for an indicator such as GDP or population. Use for long-run country macro data; use fred_series for US/global economic series.
acra
acra_sg_company
Search Singapore's ACRA corporate-entity registry via data.gov.sg (free, no key, Singapore Open Data Licence). Search by entity name or exact UEN; returns UEN, name, status, entity type, issue date and registered address. Registry snapshot only: no officers, shareholders or financials.
arxiv
arxiv_search
Search arXiv preprints (free, no key). Returns titles, abstracts, authors, publication dates and PDF links. Use for preprints in physics, math, CS and related fields; use pubmed_search for biomedical literature.
ckan
ckan_search
Search a national CKAN open-data portal (free, no key). Supported portals: uk (data.gov.uk) and au (data.gov.au). Returns dataset titles, notes, organizations and resource URLs. Use for government datasets by country; use hk_open_data_search for Hong Kong.
clinicaltrials
clinicaltrials_study
Search ClinicalTrials.gov studies (free, no key). Returns NCT ids, brief titles, status and start date with study URLs. Use for registered clinical trial records.
comtrade
un_comtrade
Fetch UN Comtrade annual trade data for a reporter (free, no key, preview endpoint). Returns import/export records by commodity code. Use for official bilateral merchandise-trade statistics.
crossref
crossref_works
Search Crossref for scholarly works (free, no key). Returns DOIs with title, authors, publication date, container and URL. Use for DOI/citation metadata discovery; use openalex_works for citation counts and richer metadata.
data
data_europa_search
Search the data.europa.eu EU open-data catalogue (free, no key). Returns dataset identifiers, titles, descriptions and countries. Use for EU-wide open datasets; use ckan_search for UK/Australia.
datacite
datacite_dois
Search DataCite for research-data DOIs (free, no key). Returns DOIs with titles, years, publishers and creators. Use to find citable datasets and their metadata; use crossref_works for articles.
dbnomics
dbnomics_series
Search a DBnomics dataset and return matching series (free, no key). DBnomics aggregates the World Bank, IMF, OECD, Eurostat, ECB, BIS and many national providers behind one API. Provide provider and dataset codes plus an optional query; returns series codes, names, dimensions and values. Use as a single entry point for multi-provider macro data.
doaj
doaj_articles
Search the Directory of Open Access Journals (free, no key). Returns open-access articles with title, authors, journal, year and DOI. Use for OA scholarly articles with permissive reuse.
ecb
ecb_series
Fetch an ECB Data Portal time series in SDMX-JSON (free, no key). Provide an ECB flow and key; returns the SDMX header and datasets, bounded in size. Use for euro-area monetary/financial series; use dbnomics_series for other providers.
europepmc
europepmc_search
Search Europe PMC (free, no key). Returns PMIDs, DOIs, titles, journals, years and authors across life-science literature. Use as an alternative/complement to pubmed_search with Europe PMC's broader indexing.
fred
fred_series
Fetch observations for a St. Louis Fed FRED economic series (requires FRED_API_KEY). Returns dated observations, newest first. Use for US and international economic time series (rates, CPI, GDP); use world_bank_indicator for cross-country development data. Free key required.
gbif
gbif_species
Search the GBIF taxonomic backbone (free, no key). Returns scientific names, canonical names, rank, status and kingdom. Use for biodiversity/species name resolution.
gdelt
gdelt_news
Search GDELT DOC 2.0 global news (free, no key). Returns matching articles with title, URL, domain, language, seen date and source country, or a volume timeline. Use for news-volume trends and cross-outlet coverage; use hn_search for tech-community discussion.
gleif
gleif_lei
Look up Legal Entity Identifier (LEI) records from GLEIF (free, no key, CC0). Search by legal name or fetch one record by LEI; returns legal name, status, jurisdiction, legal form, registration status, managing LOU and address. Use to identify legal entities and ownership/issuer identifiers across jurisdictions.
gutendex
gutendex_books
Search Project Gutenberg's public-domain catalogue via Gutendex (free, no key). Returns book ids, titles, authors, languages, download counts and Gutenberg URLs. Use to find free public-domain texts and their formats.
hkma
hkma
Call the Hong Kong Monetary Authority public API (free, no key). Pass an HKMA data path to retrieve monetary, banking or market statistics as JSON. Use for HK monetary/liquidity data; use world_bank_indicator for development indicators.
hn
hn_search
Search Hacker News stories and comments via Algolia (free, no key). Returns titles, URLs, authors, points, comment counts and timestamps, sorted by relevance or date. Use for tech-community signal and discussion; use gdelt_news for mainstream news coverage.
internet
internet_archive_search
Search the Internet Archive (free, no key). Returns identifiers, titles, years, creators and media types with item URLs. Use for public-domain texts, audio, video and archived web materials.
jina
jina_read
Fetch any URL as clean markdown via Jina Reader (free tier, no key). Use as an extraction fallback when a page is not available as structured data; returns up to 40,000 characters of readable text.
mcp
mcp_registry_search
Search the official MCP Registry for installable MCP servers (free, no key). Returns server names, titles, descriptions, versions and repository URLs. Use to discover MCP servers by capability.
nasa
nasa_apod
Fetch NASA Astronomy Picture of the Day entries (free; uses NASA_API_KEY or the shared DEMO_KEY which is heavily rate-limited). Returns date, title, explanation and media URL. Use for NASA APOD imagery and captions.
nominatim
nominatim_geocode
Geocode a place name with OpenStreetMap Nominatim (free, no key; usage policy requires a valid User-Agent and at most 1 request/second). Returns display name, latitude/longitude, type, category and address. Use for address/place coordinates.
openalex
openalex_works
Search OpenAlex scholarly works (free, no key, polite pool). Returns titles, years, DOIs, citation counts and authors. Use for literature discovery and citation signal; use crossref_works for canonical DOI metadata.
openfda
openfda_drug
Query openFDA drug adverse-event reports (free, no key). Returns safety report ids, receive dates, seriousness, product and reaction terms. Use for pharmacovigilance signals from the FDA FAERS data.
pubchem
pubchem_compound
Look up a chemical compound in PubChem (free, no key). Returns CID, molecular formula, molecular weight, SMILES and IUPAC name. Use for chemical/compound reference data.
pubmed
pubmed_search
Search PubMed biomedical literature via NCBI E-utilities (free; optional NCBI_API_KEY raises limits). Resolves matching PMIDs and then fetches article summaries. Use for biomedical/clinical citations; use arxiv_search for preprints and europepmc_search for a European mirror with full-text links.
sdg
un_sdg
Explore UN Sustainable Development Goal indicators (free, no key). Without a series code, list/filter the SDG series catalogue; with a series code, return that series' data. Use for official UN SDG statistics.
semantic
semantic_scholar_works
Search Semantic Scholar papers with citation counts (free, no key; keyless requests are heavily rate-limited and may return HTTP 429 — retry later or supply a key for higher limits). Returns titles, years, DOIs, citation counts and URLs. Use when citation counts matter.
treasury
treasury_fiscal
Query the US Treasury Fiscal Data API (free, no key). Returns records for a fiscal-service endpoint such as debt to the penny. Provide an endpoint path and optional OData filter. Use for US federal fiscal/accounting primary data.
usgs
usgs_earthquakes
Query the USGS earthquake catalogue (free, no key). Returns magnitude, place, time, coordinates and event URL. Use for seismic-event primary data.
vies
vies_vat
Validate an EU VAT number against the European Commission VIES service (free, no key). Returns validity, the registered trader name and address. Use to verify an EU business VAT identity; not a full company register.
who
who_gho
Query the WHO Global Health Observatory (free, no key). List/filter health indicators, or pass an indicator code to retrieve its data values. Use for official global health statistics.
wikidata
wikidata_search
Search Wikidata entities by label (free, no key, CC0). Returns Q-IDs with labels, descriptions and entity URLs. Use to resolve people, organizations, places and concepts to stable identifiers.
wikimedia
wikimedia_pageviews
Fetch Wikimedia pageview metrics for an article (free, no key, CC0). Returns daily view counts between two dates for a project/article. Use to gauge public attention or topic momentum.
wikipedia
wikipedia_summary
Fetch a Wikipedia article summary (free, no key; content CC BY-SA, attribution required). Returns the lead extract, description, Wikidata id and article URL. Use for a quick encyclopedic overview and to bridge to Wikidata.
zenodo
zenodo_records
Search Zenodo research outputs (free, no key). Returns records with DOIs, titles, creators and publication dates. Use for datasets, software and papers deposited in Zenodo.

Endpoints

URLTransportStateLatencyChecked
https://primary-sources-mcp.vercel.app/mcp streamable-http answering 90 ms 4 min ago

Alternatives to Primary Sources

same job, measured the same way
Veris
by jakeyoung1

Provenance-first web + SEC EDGAR data for AI agents: every fact carries its verifiable source.

39 installs/wk local only
Sec
by pipeworx-io

SEC MCP — SEC EDGAR public APIs (free, no auth)

45 tools answering
Edgar
by pipeworx-io

EDGAR MCP — SEC EDGAR public APIs (free, no auth)

59 tools answering
slashyear - sourced history
by slashyear

Sourced history by year: events, world leaders, prices and No. 1 songs, each with its source.

11 tools answering
Calculators
by logiccommons

Find and run trustworthy calculators with clear methods, provenance, and sources.

3 tools answering
FilingSift
by filingsift

Source-cited SEC filing search and retrieval with provenance and verification states.

answering
Autario MCP
by autario

Query 8,000+ verified open datasets (World Bank, Eurostat, FRED, SEC) with stats and charts.

178 installs/wk local only
BUMIT
by bumit

Swiss business verification with per-check source provenance and evidence freshness.

1 tools answering

Primary Sources — questions

Answers built from our own checks of this server.

What can Primary Sources do?
It exposes 50 tools, read directly from the server on our last check. Among them: acra_sg_company, arxiv_search, ckan_search, clinicaltrials_study, companies_house_company, companies_house_search and 44 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
What is Primary Sources mostly used for?
Its tools cluster around open, companies and hkex. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is Primary Sources working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 0 of 92 checks got a reply (0.0%), average response time 90 ms. The bar chart above shows every period we have measured.
Is Primary Sources still maintained?
The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.
The registry lists Primary Sources as active — why does it not respond?
The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.
How do I connect Primary Sources?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Primary Sources need an API key?
No. Primary Sources completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 50 of them are readable on this page. This is what we observed, not what the docs claim.