mcpField
E
Ecfr

Ecfr

Remote
pipeworx.ioLegal & Government0Updated 2w ago

About Ecfr

Ecfr is an MCP server for searching and reading the US Code of Federal Regulations. It provides full-text search, title indexes, and current section or part text for users researching federal rules.

Key features

  1. 01Search all 50 CFR titles
  2. 02List titles and currency dates
  3. 03View top-level title structure
  4. 04Retrieve section or part text

Use cases

  1. 01Find regulations by topic
  2. 02Verify the current text of a rule

MCP support

It exposes regulation search, title structure, and text retrieval tools to MCP clients. It is available through the Pipeworx gateway or as a local stdio MCP server.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/ecfr/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-ecfr

eCFR (Electronic Code of Federal Regulations) MCP.

Part of Pipeworx — an MCP gateway connecting AI agents to 1784+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolDescription
search_regulationsFull-text search across all 50 titles of the US Code of Federal Regulations (federal agency regulations) via the official eCFR API. Returns matching sections with citation, heading, and excerpt. e.g. "drone operation", "food labeling", "overtime pay". Optionally restrict to one CFR title number. Keyless.
list_titlesList all 50 titles of the US Code of Federal Regulations (Title 1 General Provisions … Title 50 Wildlife and Fisheries), with currency dates. This is the index for the title filter in search_regulations. Keyless.
title_structureGet the top-level structure (chapters/subtitles) of one CFR title — the agencies and major divisions within that title. Returns a summarized one-level view, not the full deep tree. Keyless.
get_section_textGet the actual REGULATION TEXT currently in force — a single CFR section OR a whole CFR part. PREFER for "what does 14 CFR 91.113 say", "read the text of ", "the exact wording of ", "text of 22 CFR part 120", "40 CFR part 261". Pass the title number plus EITHER a section (e.g. title 14, section "91.113" → that section) OR a part (e.g. title 22, part "120" → every section in the part). Returns the heading(s) and full paragraph text. Use search_regulations first to find the citation if unknown.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "ecfr": {
      "url": "https://gateway.pipeworx.io/ecfr/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/ecfr/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1784+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/search_regulations \
  -H 'Content-Type: application/json' \
  -d '{"query":"drone operation"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/search_regulations. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "ecfr": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-ecfr"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-ecfr

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Ecfr data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

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.