RegDataLab

io.github.medley由 GitHub 帳號 medley 發布v1.1.0更新於 Nov 10, 2026

按公司、場所或產品查閱FDA公開記錄,並附來源日期和覆蓋範圍限制。

AI 翻譯由 AI 模型根據下方的原文描述翻譯,可能有誤。

原文描述

Review public FDA records by company, site or product, with source dates and coverage limits.

已驗證Streamable HTTP可網頁執行安全與監控資料與分析商業與電商

概覽

RegDataLab 的託管 MCP 服務(www.regdatalab.com);需要 OAuth 登入或 API 金鑰;Streamable HTTP。

暫無 AI 概覽:以下資訊來自註冊中心條目和服務本身。

端點
www.regdatalab.com
最近檢查

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 RegDataLab,將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

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。

交給代理程式安裝

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.medley%2Ffda-data/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。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "regdatalab": {
      "type": "http",
      "url": "https://www.regdatalab.com/mcp"
    }
  }
}

README

FDA Data MCP

Hosted MCP server for FDA regulatory, manufacturing, and compliance intelligence.

This is the public install and discovery repo for FDA Data MCP. The live MCP endpoint is hosted at RegDataLab. The private backend, ingestion system, and production data pipeline are not open-sourced here.

[Website] [Connect Guide] [Release]

[FDA Data MCP homepage screenshot]

Quick Links

What It Does

FDA Data MCP gives AI agents structured access to FDA data for questions like:

  • Which facilities does this company operate?
  • Has FDA inspected them recently?
  • Were those inspections NAI, VAI, or OAI?
  • Are there recalls, enforcement actions, or import refusals?
  • What does FDA show for 510(k), PMA, Drugs@FDA, NDC, and related regulatory records?

The strongest current use case is manufacturing and compliance intelligence for pharma, biotech, and medtech teams.

Quick Start

The hosted endpoint is https://www.regdatalab.com/mcp. Pick the first path your client supports:

  1. OAuth sign-in (claude.ai, Claude Desktop, ChatGPT custom MCP servers, other OAuth-capable clients): add the bare URL and sign in. No key in your config.
  2. Authorization header (Claude Code, Cursor, Windsurf, the OpenAI API, scripts): send Authorization: Bearer YOUR_API_KEY.
  3. npx wrapper (stdio-only clients such as claude_desktop_config.json): set FDA_DATA_API_KEY.

Never put an API key in a URL. URLs end up in server, proxy and browser logs. The canonical, current client steps are in the connect guide.

claude.ai, Claude Desktop and Claude Cowork

  1. Open Settings > Connectors and add a custom connector.
  2. Enter only https://www.regdatalab.com/mcp.
  3. Choose sign in, paste your RegDataLab API key on the RegDataLab consent page and approve read-only access.

ChatGPT

Add RegDataLab manually as a custom MCP server: in ChatGPT, open Plugins, choose +, then Add custom MCP server, enter only https://www.regdatalab.com/mcp and sign in (OpenAI's older docs call this a custom connector under Apps). Availability depends on your ChatGPT plan and workspace settings; the connect guide has the current steps. A RegDataLab directory listing has been submitted to OpenAI and is in review; it is not published, so it cannot be installed from the directory yet.

Claude Code

bash
claude mcp add fda-data https://www.regdatalab.com/mcp \  --transport http \  --header "Authorization: Bearer YOUR_API_KEY" \  --scope user

Verify with /mcp. You should see fda-data and the manufacturing-first toolset.

Cursor

Add to ~/.cursor/mcp.json (or .cursor/mcp.json in a project you do not commit):

json
{  "mcpServers": {    "fda-data": {      "url": "https://www.regdatalab.com/mcp",      "headers": { "Authorization": "Bearer YOUR_API_KEY" }    }  }}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

json
{  "mcpServers": {    "fda-data": {      "serverUrl": "https://www.regdatalab.com/mcp",      "headers": { "Authorization": "Bearer YOUR_API_KEY" }    }  }}

OpenAI API (Responses)

python
from openai import OpenAI
client = OpenAI()response = client.responses.create(    model="gpt-4.1",    tools=[{        "type": "mcp",        "server_label": "fda-data",        "server_url": "https://www.regdatalab.com/mcp",        "require_approval": "never",  # tools are read-only        "headers": {"Authorization": "Bearer YOUR_API_KEY"},    }],    input="Give me a manufacturing risk summary for Pfizer",)print(response.output_text)

VS Code One-Click Install

[Install in VS Code]

Generic MCP clients

  • URL: https://www.regdatalab.com/mcp (Streamable HTTP)
  • Auth: OAuth 2.1 with PKCE and dynamic client registration, or the header Authorization: Bearer YOUR_API_KEY
  • Discovery file: https://www.regdatalab.com/.well-known/mcp.json

npx wrapper (stdio-only clients)

For clients that can only start a local command, such as claude_desktop_config.json:

json
{  "mcpServers": {    "fda-data": {      "command": "npx",      "args": ["-y", "fda-data-mcp"],      "env": {        "FDA_DATA_API_KEY": "YOUR_API_KEY"      }    }  }}

Config file location:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Or from a shell: FDA_DATA_API_KEY=YOUR_API_KEY npx -y fda-data-mcp

The wrapper is a zero-dependency stdio-to-HTTP proxy:

The version on npm can lag this repo; see CHANGELOG.md for what each published version contains.

If you do not have an API key yet, sign up at regdatalab.com/signup. A new key starts with 50 credits; verifying your email unlocks 300 free credits a month.

Example Prompts

  • Give me a manufacturing risk summary for Pfizer.
  • Show recent VAI and OAI inspections for Moderna.
  • Summarize recalls, compliance actions, and import refusals for Thermo Fisher.
  • What does FDA have on this company across facilities, inspections, and enforcement?

Data Coverage

FDA Data MCP covers live hosted access to datasets including:

  • FDA inspections
  • FDA citations
  • FDA compliance actions
  • FDA import refusals
  • recalls and enforcement
  • 510(k) clearances
  • PMA approvals
  • Drugs@FDA
  • NDC directory
  • drug labels
  • device registrations and listings
  • device UDI
  • drug shortages
  • MES, QMS and LIMS software vendor evidence (software_* tools)

For the canonical and current product surface, use:

Auth and Pricing

  • Sign up for an API key at regdatalab.com/signup
  • OAuth-capable clients: add the bare URL and sign in; no key in your config
  • Other HTTP clients: send the Authorization: Bearer YOUR_API_KEY header
  • The npx wrapper: set FDA_DATA_API_KEY=YOUR_API_KEY
  • Never put a key in a URL or in an issue report
  • Free and paid plans are listed at regdatalab.com/pricing

Why This Repo Exists

This repo is intentionally public and lightweight so it can serve as:

  • the GitHub landing page for the hosted MCP
  • a stable place for setup examples
  • a future home for marketplace metadata and install helpers

The production backend and ingestion engine live separately.

Support

Changelog and Releases

Security

If you find a security issue, do not open a public issue. Use the policy in SECURITY.md.

來源:README.md,提交 f3e76e8

工具

0
該伺服器需要登入,因此 SourceWeft 無法在沒有帳號的情況下讀取其工具,也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

2
  1. v1.1.0最新Nov 3, 2026
  2. v1.0.0Sep 16, 2026

評分

已滿足適用檢查項的 85%

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。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分