io.github.joelp22-maker由 GitHub 帳號 joelp22-maker 發布v1.2.0更新於 Oct 24, 2026
Verified reference data; each record carries its source URL and quote. verify_quote checks claims.
檢索 referencesource.org 已核實的參考資料集，並用附有來源網址與原文引述的紀錄核對所聲稱的數值。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.joelp22-maker%2Freferencesource/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"referencesource-org": {
"type": "http",
"url": "https://referencesource.org/mcp"
}
}
}[referencesource.org MCP connector]
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.
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".
Claude Desktop — add to claude_desktop_config.json:
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.
referencesource.org/mcp.MIT licensed.
Every record carries source (the page the value was read from) and
source_quote (the verbatim line on that page which states it), so any answer
this server returns can be checked against its source. verify_quote runs that
check against a value you already hold: it tells you whether our record agrees,
and hands back the source and quote either way.
MIT — see LICENSE. The reference data itself is CC BY 4.0; see the data repository for the full position on the quoted excerpts.
來源：README.md，提交 e0de5e7
List reference datasets
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.
fullquerySearch records in a dataset
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.
query必填dataset_slug必填Get one record by id
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.
record_id必填dataset_slug必填Check a claimed value against a record
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.
fieldrecord_iddataset_slug必填claimed_value必填Next task for Muse
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.
無需輸入參數。
Submit a task result
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.
noteresult必填status必填task_id必填Daily brief for Joe
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.
無需輸入參數。
Message the supervisor
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.
body必填kind必填subject必填task_idmessage_id必填已滿足適用檢查項的 100%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
{ "mcpServers": { "referencesource": { "command": "npx", "args": ["-y", "referencesource-mcp"] } }}