Top 20 Python mcp-tool Projects
-
I opened a pull request to FastMCP (27k stars) at 23:12:32 UTC. A bot closed it at 23:12:47. Fifteen seconds.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
claude-skills
345 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 330+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.
Project mention: I Built a Dual-Pool Adversarial Review System for AI Agents — And It Actually Works | dev.to | 2026-06-27I tested this on my own PR to alirezarezvani/claude-skills (18.7K stars):
-
The AWS Labs MCP GitHub repository
-
claude-code-guide
Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!
-
ios-simulator-skill
An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with your apps, and to proxy xcodebuild to save token wastage - LLMs directly calling xcb have to eat a lot of output!
-
arcade-mcp
MCP Server Framework and Tool Development library for building custom capabilities into agents.
Project mention: Should you build or buy an MCP runtime for enterprise AI agents in 2026? | dev.to | 2026-05-13Agent-optimized tools. Arcade's catalog of over 8,000 agent-optimized MCP tools are not API wrappers. They translate natural-language intent into structured API calls, so an agent asked to "send this to Finance" does not have to hallucinate the target recipient_user_id. The token cost shows up in benchmarks: for identical CRM queries, intent-level tooling produced 100x fewer response tokens than a raw API-passthrough approach, with token output equivalent to 3.7% of a 200K context window versus 373%. At scale, that overhead translates to context-window overflow in multi-step workflows and degraded agent accuracy. The runtime handles parallelized tool execution, failover, and retries. The Arcade MCP Framework lets you build custom proprietary tools that federate into the same control plane with the same auth and governance wrapping.
-
RAGLight
RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.
Project mention: Show HN: RAGLight, serve a RAG pipeline as a REST API and chat UI in one command | news.ycombinator.com | 2026-03-05 -
Fast-LLM-Agent-MCP
This repo covers LLM, Agents, MCP Tools, Skills concepts with sample codes: LangChain & LangGraph, AWS Strands Agents, Google Agent Development Kit, Fundamentals.
Project mention: Simple DEV Blog Post Writer with LangGraph Multi Agents with Memory, AWS Bedrock Nova: Generator & Evaluator Pattern | dev.to | 2026-05-10 -
Project mention: Show HN: MCPcat – A free open-source library for MCP server monitoring | news.ycombinator.com | 2025-08-28
-
-
synapse-ai
Build AI agents that actually do things. Synapse is an open-source platform for creating, connecting, and orchestrating AI agents powered by any LLM — local, cloud or CLIs.
Project mention: Open source DAG for managing multi-agent pipelines | news.ycombinator.com | 2026-04-22 -
metatron
Git-native context layer for AI coding agents. Your team's real engineering decisions — patterns, pitfalls, conventions — live as reviewed markdown files in your repo; agents consult them before writing code and record what they learn. Files-first, no server required; MCP as an optional serving layer. (by kerbelp)
Project mention: Show HN: Metatron – give coding agents your team's conventions over MCP | news.ycombinator.com | 2026-06-08 -
SchemaPin
The SchemaPin protocol for cryptographically signing and verifying AI agent tool schemas to prevent supply-chain attacks.
-
shinzo-py
Python SDK for MCP server observability, built on OpenTelemetry. Gain insight into agent usage patterns, contextualize tool calls, and analyze server performance across platforms. Integrate with any OpenTelemetry ingest service including the Shinzo platform.
Project mention: Shinzo Python SDK: OpenTelemetry-Native Observability for MCP Servers | news.ycombinator.com | 2025-11-21- Exports to any OTel backend (Datadog, Grafana, Prometheus, or self-hosted collectors)
Why OpenTelemetry Matters
Other observability tools in the space use proprietary formats, and even the ones that support OTel do so as a second-class citizen, not a primary concern. Treating OTel as a primary feature means zero vendor lock-in and compatibility with your existing stack. Switch backends as you need without touching the instrumentation.
What's Next
We’re currently hard at work on new context intelligence features: token optimization analysis to identify which tool responses bloat context windows, and relevance scoring to track which outputs agents actually use.
Multi-Language Support
TypeScript has been available since July. Python releases today. Go and C# planned 2026 (looking for contributors!).
Links
GitHub (Python SDK): https://github.com/shinzo-labs/shinzo-py
-
Project mention: Show HN: Mcpscore – validate any MCP server compliance with a new MCP version | news.ycombinator.com | 2026-08-04
-
mcp-github-pr-issue-analyser
A Model Context Protocol (MCP) application for automated GitHub PR analysis and issue management. Enables LLMs to fetch PR details, analyse diffs, manage issues, and handle releases through a standardised interface
-
agent2agent-strands-ai21-maestro
Agent-to-Agent AI Integration: AWS Security Analysis with AI21 Maestro & Strands Agents
-
bluerock
Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes. Apache 2.0
Project mention: Show HN: MCP Python Hooks – sys.addaudithook and import hooks for MCP | news.ycombinator.com | 2026-05-06 -
actenon-kernel
The open verifier for proof-bound consequential execution. Verifies cryptographic proof at the execution edge before any side effect — payments, deletes, deploys, access changes. 51 conformance vectors. Python/TS/Go/Rust SDKs. No valid proof, no execution.
Project mention: GPT-5.6 Sol's file deletion isn't a bug you patch. It's proof that filtering an agent's actions doesn't contain it. Here's why, and what actually does. | dev.to | 2026-07-14Repo, if you want to poke at the boundary approach (runs with no keys, no network): https://github.com/Actenon/actenon-permit and https://github.com/Actenon/actenon-kernel. Both repos work together for consequential actions protection and proof, and I'd genuinely rather you try to route around it than star it. Where does it leak?
-
mcp-debug-proxy
A reverse proxy that sits between an MCP client and a third-party remote MCP server for debugging.
Project mention: Show HN: MCP-debug-proxy – A visual reverse proxy for MCP and OAuth traffic | news.ycombinator.com | 2026-08-07
Python mcp-tools discussion
Python mcp-tools related posts
Index
What are some of the best open-source mcp-tool projects in Python? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | fastmcp | 27,081 |
| 2 | claude-skills | 23,957 |
| 3 | mcp | 9,567 |
| 4 | claude-code-guide | 4,504 |
| 5 | ios-simulator-skill | 1,206 |
| 6 | arcade-mcp | 889 |
| 7 | RAGLight | 670 |
| 8 | Fast-LLM-Agent-MCP | 85 |
| 9 | agentcat-python-sdk | 53 |
| 10 | mcp-server-fuzzer | 46 |
| 11 | synapse-ai | 41 |
| 12 | metatron | 23 |
| 13 | SchemaPin | 16 |
| 14 | shinzo-py | 13 |
| 15 | mcpscore | 9 |
| 16 | mcp-github-pr-issue-analyser | 6 |
| 17 | agent2agent-strands-ai21-maestro | 3 |
| 18 | bluerock | 2 |
| 19 | actenon-kernel | 1 |
| 20 | mcp-debug-proxy | 0 |
Sponsored