Skip to main content

MCP server for looking up IETF RFCs, with obsolescence warnings and section-level reads

Project description

mcp-server-rfc

An MCP server for looking up IETF RFCs.

{
  "mcpServers": {
    "rfc": {
      "command": "uvx",
      "args": ["mcp-server-rfc"]
    }
  }
}

No clone, no virtualenv, no path. That is the whole installation. Your client spawns the server on your machine and talks to it over stdin and stdout.

A client showing the server as connected has not necessarily used it, and a model will happily answer an RFC question from memory instead. On Claude Desktop the per-server log records only the handshake, so it cannot tell you either way — docs/desktop-verification.md says where the evidence actually is.

Tools

Tool What it does
search_rfcs Search titles, or the full text of every RFC if a mirror has been synced
list_sections An RFC's headings with line numbers — the cheap first call
get_rfc Read one section, or a line range

get_rfc refuses an unscoped read of an RFC over 1500 lines, and an uncapped read of a section over 1000, answering with its size and a pointer to list_sections rather than filling the context with a specification the model had one question about. list_sections reports each section's length so the choice can be made before the read, max_lines caps any read including a section, and full=true overrides both guards.

Every response carries a banner with the RFC's status and, when it applies, a warning that it has been superseded:

RFC 2616 — Hypertext Transfer Protocol -- HTTP/1.1  [DRAFT STANDARD]
!! OBSOLETED BY: RFC 7230, 7231, 7232, 7233, 7234, 7235

That warning is the reason to use this rather than let a model fetch rfc-editor.org itself. Models cite dead specifications with great confidence.

Full-text search

Works with no setup, fetching documents on demand. Full-text search additionally requires a local mirror, which the user creates from a shell:

uvx mcp-server-rfc sync

The same command that runs the server runs its CLI: sync downloads the corpus, status reports what is present, and uvx mcp-server-rfc <command> --help covers the rest. It is also the command the server names in the error you get when full-text search is asked for without a mirror.

512 MB, a few minutes, entirely optional. The server deliberately does not expose a sync tool: half a gigabyte pulled from a volunteer-run mirror should be a person's decision, not a model's.

If a mirror already exists — synced for the companion skill, say — this server picks it up automatically. Set $RFC_MIRROR to point at a non-default location.

HTTP mode

The config above is the stdio transport, which needs a client that can spawn a process on your machine. A session running in the cloud — claude.ai on the web, Cowork — cannot, and no configuration fixes that. For those, the server has to be deployed somewhere they can reach:

mcp-server-rfc --transport http --host 0.0.0.0 --port 8080

RFC_TRANSPORT, HOST and PORT are read from the environment too. The repository carries a Dockerfile and a fly.toml that do this. No public instance of this server exists and none is planned — if you want one, you host it, and you should put authentication in front of it, since the server has none and would otherwise be an open proxy to a volunteer-run mirror.

Full-text search is the one thing that does not survive: it reads a local 512 MB corpus, so a hosted instance returns an error saying so instead of silently answering a title search. The obsolescence banner, section reads and the unscoped-read guard all work, because they need only the 2 MB index.

If your client has a shell

Use the skill instead — Claude Code, Codex CLI, OpenClaw, Cursor and Zed all qualify. It does the same things with fewer moving parts and gives the agent ripgrep over the corpus:

clawhub install @shbernal/rfc-lookup

This server is for clients that give the model no shell of its own. Claude Desktop is the clearest case: its chat cannot run a command on your machine, but it will spawn this server there.

Source, issues and the skill: https://github.com/shbernal/rfc-ai-tooling

MIT.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_server_rfc-0.2.1.tar.gz (24.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_server_rfc-0.2.1-py3-none-any.whl (22.8 kB view details)

Uploaded Python 3

File details

Details for the file mcp_server_rfc-0.2.1.tar.gz.

File metadata

  • Download URL: mcp_server_rfc-0.2.1.tar.gz
  • Upload date:
  • Size: 24.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.12.1 {"installer":{"name":"uv","version":"0.12.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for mcp_server_rfc-0.2.1.tar.gz
Algorithm Hash digest
SHA256 638fc905fd433e49b2633e90da1d14259c05e1a52808b41e86e5748b0b9c6524
MD5 040ff817f67c5c828625784a86aae514
BLAKE2b-256 d9818767a0826db9edf703e930ec530b885e1b17757f1e9dfe6e716725f5c926

See more details on using hashes here.

File details

Details for the file mcp_server_rfc-0.2.1-py3-none-any.whl.

File metadata

  • Download URL: mcp_server_rfc-0.2.1-py3-none-any.whl
  • Upload date:
  • Size: 22.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.12.1 {"installer":{"name":"uv","version":"0.12.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for mcp_server_rfc-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 9928b9e4950ac50a59cd715137abf0d625be5ca28e3a98aea676b348db5c525b
MD5 711ace47c4b050c07013bedd88b9868f
BLAKE2b-256 b3ecad4a1dbecac482f57c2143257cce67a2da2046335285f146184bb5a58438

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page