#135 · Primary category: LLM Application Frameworks
fast-mcp
A Ruby Implementation of the Model Context Protocol
Project last updated:12/15/25
GitHub Stars
1.2K
Forks
106
Contributors
22
License
MIT
Why we included this project
If your application is built on Ruby and you want large language models to call your own code, Fast MCP gives you a clean way to make that happen. It implements the Model Context Protocol, so you define tools as ordinary Ruby classes and the library handles schema generation and argument validation via Dry-Schema. Resources are exposed the same way, and you can serve the server over STDIO, HTTP, or SSE from any Rack app. A Rails generator scaffolds the folder structure and auto-discovers your subclasses, and request-aware filtering lets you restrict which tools a given call sees based on role or API version. That makes it a practical fit for teams that want models to interact with their real application logic without building custom protocol glue.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform