About Regulations.gov MCP
Regulations.gov MCP connects federal rulemaking data to MCP clients, for people tracking regulatory changes that affect acquisition policy. It searches documents, dockets, and public comments, with tools for open comment periods and FAR case histories.
Key features
- 01Search proposed and final rules
- 02Retrieve document and docket details
- 03Search public comments
- 04Track open comment periods
- 05Review FAR/DFARS case histories
Use cases
- 01Find FAR cases with open comment periods
- 02Review the history of a docket
- 03Search proposed rules from an agency
MCP support
This MCP server exposes Regulations.gov API data and an access-status check to MCP clients. Local setup requires an api.data.gov key; hosted use does not.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx regulationsgov-mcpREGULATIONS_GOV_API_KEYSecretFree api.data.gov key from https://api.data.gov/signup/ for 1,000 req/hr.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEregulationsgov-mcp
Free, open-source MCP server for the Regulations.gov API. Federal rulemaking dockets, proposed rules, final rules, public comments, and comment period tracking.
Overview, demo video and hosted setup: https://1102tools.com/mcp/regulations-gov
Hosted: no key. Local: a free api.data.gov key. See Local or hosted.
Regression tests, including live checks against the Regulations.gov API. The October 2026 releases were also checked with realistic rulemaking questions (open comment periods, comment deadlines, FAR case histories, posted comments). See testing.md.
Local or hosted
| Local (desktop) | Claude (hosted) | ChatGPT (hosted) |
|---|---|---|
| Local setup | Install | Install |
- Local runs it on your computer, inside the Claude or ChatGPT desktop app or another AI app. You get your own full rate limits, and it relies only on the government service. It needs a free api.data.gov key. It doesn't update itself, so ask your AI to update it. You don't have to set it up by hand: give your AI this page's link and ask it to set it up or walk you through it.
- Hosted is always up to date, needs no setup or keys, and works in Claude or ChatGPT anywhere.
Compare local and hosted · Matching prompts
What it does
Exposes the Regulations.gov API plus a credential-readiness check as 9 MCP tools:
Core
search_documents- Search proposed rules, final rules, notices with flexible filtersget_document_detail- Full document details with optional attachmentssearch_comments- Search public comments (by docket, document, or keyword)get_comment_detail- Full comment text and submitter infosearch_dockets- Search rulemaking and nonrulemaking docketsget_docket_detail- Docket metadata, abstract, and RIN
Workflow
open_comment_periods- Currently open comment periods across procurement agenciesfar_case_history- Summary of a FAR/DFARS rulemaking case with its documents, paged
Setup
get_access_status- Check whether an API key is configured, without revealing it
API key (required)
This server calls api.regulations.gov, which requires an api.data.gov key:
1,000 requests per hour, yours alone. Without REGULATIONS_GOV_API_KEY the
server still starts and lists its tools, but data tools return setup
instructions instead of calling Regulations.gov.
Get a free key (takes 30 seconds):
- Go to open.gsa.gov/api/regulationsgov/#getting-started (or directly at api.data.gov/signup)
- Enter your name and email: no approval, no wait
- Copy the key from the confirmation page
- Paste it into your client config as
REGULATIONS_GOV_API_KEY(see below)
The same api.data.gov key works for every api.data.gov-backed API (Regulations.gov, GSA Per Diem, NASA, FEC, FCC, etc.), so if you already have one for another 1102tools MCP you can reuse it.
Installation
uvx --refresh-package regulationsgov-mcp --from regulationsgov-mcp regulationsgov-mcp
Configuration
Use the configuration below as the server definition and adapt its placement to your compatible MCP client. For practical requests using this source, see the prompt library.
With your key:
{
"mcpServers": {
"regulationsgov": {
"command": "uvx",
"args": ["--refresh-package", "regulationsgov-mcp", "--from", "regulationsgov-mcp", "regulationsgov-mcp"],
"env": {
"REGULATIONS_GOV_API_KEY": "paste-your-api-data-gov-key-here"
}
}
}
}
The --refresh-package flag tells uv to check PyPI for a newer release each time your client launches the server, so fixes arrive automatically; without it, uv keeps serving whatever version it first cached. It adds a moment of network time at startup, so raise your platform's MCP startup timeout if it enforces a short one.
Restart the client and the tools appear.
Example prompts
- "What FAR cases have open comment periods right now?"
- "Show me the full docket history for FAR-2023-0008."
- "Find all proposed rules from DARS posted in the last 6 months."
- "How many public comments were submitted on FAR Case 2023-008?"
- "Search for rulemaking dockets related to cybersecurity at DoD."
- "Find all SBA rules about size standards from the last year."
Important: case-sensitive filter values
Regulations.gov filter values are CASE-SENSITIVE. Use exact casing:
- Document types:
Proposed Rule,Rule,Notice(not lowercase) - Docket types:
Rulemaking,Nonrulemaking - Lowercase values silently return 0 results with no error
Companion tools
federal-register-mcp: what was published in the Federal Registerregulationsgov-mcp: the docket structure, public comments, and comment period statusecfr-mcp: what the regulation currently says after amendments
Together these three cover the full regulatory pipeline from proposal through public comment to codified rule.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.