# yjacquin/fast-mcp

A Ruby Implementation of the Model Context Protocol

Repository: https://github.com/yjacquin/fast-mcp
Canonical: https://ross.abutalabs.com/products/fast-mcp
Language: Ruby
License: MIT
License Family: permissive
Topics: ai, llm, mcp, rack, ruby
Last push: 2025-12-15T19:19:43+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 57, release rhythm 50, longevity 38
- inputs: {"age_days": 541, "days_push": 261, "days_rel": 339, "gap_med": 8.0, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1187, forks 106 (observed 2026-08-28T04:03:55.251422+00:00)

## What it is
Fast MCP is a Ruby implementation of the Model Context Protocol (MCP), letting AI models call Ruby tools and read app resources. It supports STDIO, HTTP, and SSE transports and integrates with Rails, Sinatra, or any Rack app.

## Use cases
- expose ruby methods as tools for llms
- add mcp server to a rails app
- connect claude or other ai clients to my ruby backend
- share application data as mcp resources
- secure ai endpoints with authentication
- filter mcp tools by user permissions

## When to choose
- you have a Ruby or Rack-based application you want LLMs to interact with
- you need MCP tool/resource support with argument validation
- you want multiple transport options (STDIO, HTTP, SSE)

## When to avoid
- your stack is Python, TypeScript, or another non-Ruby language
- you need an MCP client rather than a server
- you need features beyond tools/resources such as sampling

## Facets
- artifact type: library
- maturity: active
- function: mcp, agent-framework, middleware, auth, api-framework
- domain: large-language-models, backend, web-development, developer-tools
- platform: ruby, cli
- tags: model-context-protocol, rack, rails, sinatra, stdio-transport, sse, dry-schema, tools-and-resources, ai-agents, web-server

## Member repositories
- yjacquin/fast-mcp (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:55.251422+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:23:46.576026+00:00, confidence not recorded.
  - readme: https://github.com/yjacquin/fast-mcp (fetched 2026-08-28T04:03:55.251422+00:00, sha 887090f4144a)
- Data as of 2026-08-30T08:39:29.467469+00:00.