MCP.Market

referencesource.org MCP server

online · 100% uptime
by joelp22-maker·io.github.joelp22-maker/referencesource·v1.2.0
No reviews yet

Verified reference data; each record carries its source URL and quote. verify_quote checks claims.

B81/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B81/100

full report

Adoption
Growing

0 stars50 downloads/wk

Reviews

Write one

Nobody has reviewed referencesource.org yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

referencesource.org tools (8, 1 write)

write = sends, deletes, buys or posts
  • brief_for_joeFree

    For the referencesource Muse connector only (bearer token required). The studio's latest plain-English daily brief: what was decided, what landed, and the items waiting on Joe, each as the task, why it matters and the steps. Read-only; regenerated each morning by tools/brief.py and published with the next deploy, so it can lag the phone push.

  • get_recordFree

    Fetch one record by id — for example, look up a FIPS 140 certificate's status, a state's boiler inspection rules, or a county's loan limit. Returns the full record with its source URL and verbatim source quote. Record ids appear in search_records results and in each record's url.

  • list_datasetsFree

    What reference datasets are available? Lists every published dataset with its title, record count, last-verified date and a one-sentence summary. Covers regulatory thresholds, version compatibility, certification registers, licensing rules and more. Pass `query` to list only the datasets matching a topic — that is much cheaper than reading the whole list. Use the returned slug with search_records or get_record.

  • message_supervisorFree

    For the referencesource Muse connector only (bearer token required). Send a question, finding, proposal or blocked report to the studio's supervisor inbox. Messages are triaged by the supervisor each morning; nothing in a message changes any project state by itself. Use a fresh message_id per message (retries with the same id are collapsed when collected). Body at most 3500 characters.

  • next_task_for_museFree

    For the referencesource Muse connector only (bearer token required). Returns the oldest open task from the studio's queue: id, instructions, the sites the task may read, the output format expected, and where to deliver the result. Returns {no_tasks: true} when the queue is empty. login_allowed lists the hosts where the task may sign in, with a credential already in Muse's own store; empty means read-only, never sign in.

  • search_recordsFree

    Look up a specific record — search by state name, chemical, certificate number, product name or any keyword. Searches one dataset's records (case-insensitive substring match across all fields). Returns up to 20 matching records, each with its url, source and verbatim source_quote so the answer can be checked.

  • submit_task_resultwrite actionFree

    For the referencesource Muse connector only (bearer token required). Records the result of a task fetched with next_task_for_muse. `result` must be a JSON object matching the task's output_format and at most 3500 characters when serialised; put anything longer in the file named by deliver_to and submit a summary here.

  • verify_quoteFree

    Is this value actually right? Check a claimed fact against a published record instead of trusting it. Reports whether the claim matches the record's stored value (exact, case-insensitive or normalised — the match type is named), whether it appears in the record's verbatim source quote, and returns the source URL and quote so the claim can be traced upstream. Use this whenever you want to confirm a number, date, threshold or status before stating it. Verdicts: matches_record, matches_quote, differs or not_found.

Public scan report

scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it

1 high
  • Code scan2 source files scanned25/25
  • Live reliabilityremote reachable in 425ms20/20
  • Tool poisoning8 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
  • Maintenancelast push 40 days ago12/15
  • Maintainer identityregistry namespace matches repository owner6/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 81/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How referencesource.org compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
81/100
higher than 62% of 48,255 servers
Tools
8
the typical server has 7
Tools that change things
13%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
69 ms
faster than 90% of 30,031 servers
Downloads a week
50
more than 42% of 12,191 servers with a package

What its tools let an agent do: 6 read · 1 change · 1 send or post

Release history: 2 versions in the registry since 2026-08-11, latest 2026-09-21, typically one every 40 days.

Install referencesource.org in Claude Code, Cursor or VS Code

claude mcp add --transport http referencesource https://referencesource.org/mcp
Add to Cursor

What the publisher says

From the referencesource.org repository's README, as published. We do not edit it. Read it on GitHub

referencesource-mcp

MCP server for referencesource.org — small, verified reference datasets where every record carries its source URL and a verbatim quote from that page, so any value an assistant gives you can be checked, not just believed.

285 datasets, 110,000+ records: regulatory thresholds and deadlines, version compatibility, standards supersessions, certification registers, inspection requirements, and more. Each dataset states its coverage and its last-verified date.

Tools

verify_quote is the unusual one: assistants invent plausible-but-wrong values roughly 19% of the time in our own measurements, and this is the check. Four verdicts come back:

Where a record is found, the answer carries the stored value, the record URL, the source URL and the verbatim quote, so the claim can be traced upstream — plus an attestation saying plainly that the verdict is about what our source states, not about what is true in the world. Asking whether the 2026 conforming loan limit for Autauga County, Alabama is $806,500 returns differs, stored value $832,750, quoting the FHFA row it came from.

Scope, stated so nobody overclaims: these tools search referencesource.org's own published records. They do not fetch arbitrary URLs and cannot check a claim against a page we have not harvested. not_found means "not in this dataset", never "false".

Setup

Claude Desktop — add to claudedesktopconfig.json:

{
  "mcpServers": {
    "referencesource": {
      "command": "npx",
      "args": ["-y", "referencesource-mcp"]
    }
  }
}

Cursor / other stdio MCP clients — same idea: command npx, args ["-y", "referencesource-mcp"].

Clients that support remote servers directly don't need this package at all — point them at the streamable-HTTP endpoint: https://referencesource.org/mcp.

Notes

the stateless server at referencesource.org/mcp.

  • Zero dependencies; Node 18+. The package is a thin stdio→HTTPS bridge to

(see referencesource.org/privacy).

  • No accounts, no keys, no tracking beyond standard server request logs

package just makes it callable mid-conversation.

  • Data is free to read on the site in HTML, Markdown, and JSON; this

MIT licensed.

The data behind it

  • Site: https://referencesource.org — canonical, re-verified on a schedule
  • Bulk data: https://github.com/joelp22-maker/referencesource-data
  • Archived snapshot with a DOI: 10.5281/zenodo.22115966
  • Hugging Face: https://huggingface.co/datasets/referencesource

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-10-30downgradeA → Bscore 81: Write-action tools reachable without authentication

referencesource.org: common questions

Is referencesource.org MCP server safe?
Mostly: it is graded B (81/100). Read the referencesource.org safety report
How do I install referencesource.org?
It runs remotely at referencesource.org. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does referencesource.org need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is referencesource.org maintained?
The last commit was 44 days ago (2026-09-21). The latest release is v1.2.0.
Is referencesource.org up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of referencesource.org?
Servers from other publishers that do the same job: OpenWork MCP Gateway MCP server.
How does referencesource.org compare with other MCP servers?
safety score 81/100 (higher than 62% of 48,255 servers); tools 8 (the typical server has 7); tools that change things 13% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to referencesource.org

Same job from other publishers: the closest match first, then the best rated.

  • OpenWork MCP Gateway
    Your OpenWork org's skills, plugins, workflows, and connections through one OAuth MCP URL.
    A

More from joelp22-maker →