SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 Python model-context-protocol Projects
-
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
Project mention: Show HN: MCP-C – cloud platform for running MCP agents and apps | news.ycombinator.com | 2025-10-28
-
-
mcp-context-forge
An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.
Project mention: Every AI toolchain is inventing its own safety layer. We shipped one that works across all of them. | dev.to | 2026-05-12Anthropic shipped Claude Code hooks — PreToolUse, PostToolUse, Notification, and friends. They run as subprocesses, get JSON on stdin, and decide whether the tool call proceeds. OpenAI ships tool guardrails in the Agents SDK — Python (and now TS) callables you attach to a tool, with tripwire booleans that abort the run. The MCP ecosystem is sprouting gateways and proxies for the same purpose: MCPX, IBM ContextForge, Microsoft's MCP Gateway, Lasso Security's MCP Gateway — all reasonable answers to the same wire-level question.
-
code-mode
🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.
Project mention: Code-Mode Library: First library for tool calls via code execution | news.ycombinator.com | 2025-11-23 -
-
MCP-Bridge
A middleware to provide an openAI compatible endpoint that can call MCP tools (by SecretiveShell)
-
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.
-
ainativelang
AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README)
And to consider AI agents are still mostly entirely limited to generating code in programming languages designed to be written, tested and debugged by humans.
Here are two experimental exceptions:
https://github.com/vercel-labs/zerolang
https://github.com/sbhooley/ainativelang
-
mcp-client-for-ollama
Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved preferences.
Project mention: Meta Llama MCP Servers — AI Agents for Llama 4, Ollama, and the Open-Weight LLM Ecosystem | dev.to | 2026-03-25GitHub: jonigl/mcp-client-for-ollama — 577 stars, 85 forks
-
idea-reality-mcp
Pre-build reality check for AI coding agents. Scans GitHub, HN, npm, PyPI, Product Hunt. MCP server. 290+ stars.
Project mention: I Built an AI That Tells You If Your Idea Already Exists — And Syncs Results to Notion | dev.to | 2026-03-14Then I built idea-reality-mcp — a tool that scans actual platforms instead of relying on LLM knowledge. I ran my own idea through it.
-
stealth-browser-mcp
The only browser automation that bypasses anti-bot systems. AI writes network hooks, clones UIs pixel-perfect via simple chat.
Project mention: Show HN: Vibium – Browser automation for AI and humans, by Selenium's creator | news.ycombinator.com | 2025-12-24Maybe this is something: https://github.com/vibheksoni/stealth-browser-mcp
-
Project mention: Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP | news.ycombinator.com | 2026-03-08
-
Project mention: Beyond package management: How Nix refactored my digital life | news.ycombinator.com | 2025-09-11
-
-
bernstein
Audit-grade multi-agent orchestration for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). HMAC-chained audit log, signed agent cards, per-artefact lineage, air-gap deploy. The orchestrator your compliance team will sign off on. https://bernstein.run
Project mention: bernstein 2.x recap: lineage, ten trackers, A2A capability cards, and a CI that started fixing itself | dev.to | 2026-05-20#1720 — Skills end-to-end. The skill subsystem already has discovery, layered merge (BASE / TEAM / USER under XDG, above), and an injector for Claude Code. The operator never touches it because there is no install, no sync, no publish, no lint, no test, no init, no watch. If you have an opinion on the verb surface, the manifest shape, or whether a community index belongs in scope at all, the RFC is where to leave it.
-
mcp-server-code-execution-mode
An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.
Project mention: MCP Code Execution Server: Zero-Context Discovery for 100 MCP Tools | news.ycombinator.com | 2025-12-19 -
-
llm-context.py
Share code with LLMs via Model Context Protocol or clipboard. Rule-based customization enables easy switching between different tasks (like code review and documentation). Includes smart code outlining.
-
flyto-core
The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue, versioning, metering.
Project mention: Show HN: What if YAML was a programming language? (412 built-in modules) | news.ycombinator.com | 2026-02-24 -
pentest-ai
Offensive-security MCP server with 205 wrapped tools, 17 specialist agents, and 60 SPA-aware probes for OWASP Top 10. CLI + MCP, BYO LLM. No API key needed on MCP path.
Project mention: Show HN: Ptai – an MCP that chains low-sev findings into RCE | news.ycombinator.com | 2026-05-19 -
The Nextcloud MCP Server [0] supports Qdrant as a vectordb to store embeddings and provide semantic search across your personal documents. This enables any LLM & MCP client (e.g. claude code) into a RAG system that you can use to chat with your files.
For local deployments, Qdrant supports storing embeddings in memory and in a local directory - for larger deployments Qdrant supports running as a standalone service/sidecar and can be made available over the network.
[0] https://github.com/cbcoutinho/nextcloud-mcp-server
-
YourMemory
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
Project mention: Show HN: YourMemory, persistent memory layer with temporal reasoning for agents | news.ycombinator.com | 2026-05-25
Python model-context-protocol discussion
Python model-context-protocol related posts
-
From mock-only-works to real-world-works: 48 hours of reCAPTCHA debugging
-
When handoff.md Stops Being Enough for AI Agents
-
Build Your First MCP Server in Python in 10 Minutes
-
Supabase Auth and FastMCP Example
-
The 6-Layer Memory Architecture I Run for Claude Code
-
MCP Development with Python, Gemini CLI, and Amazon AWS ECS Express
-
A conversational time series forecasting assistant with Amazon Bedrock and LibreChat
-
A note from our sponsor - SaaSHub
www.saashub.com | 9 Jun 2026
Index
What are some of the best open-source model-context-protocol projects in Python? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | fastmcp | 25,469 |
| 2 | mcp-agent | 8,353 |
| 3 | Upsonic | 7,870 |
| 4 | mcp-context-forge | 3,814 |
| 5 | code-mode | 1,474 |
| 6 | minima | 1,048 |
| 7 | MCP-Bridge | 928 |
| 8 | arcade-mcp | 889 |
| 9 | ainativelang | 829 |
| 10 | mcp-client-for-ollama | 729 |
| 11 | idea-reality-mcp | 713 |
| 12 | stealth-browser-mcp | 682 |
| 13 | mcp-client-cli | 675 |
| 14 | mcp-nixos | 660 |
| 15 | dbt-mcp | 576 |
| 16 | bernstein | 547 |
| 17 | mcp-server-code-execution-mode | 334 |
| 18 | mcp-server-tree-sitter | 306 |
| 19 | llm-context.py | 301 |
| 20 | flyto-core | 273 |
| 21 | pentest-ai | 266 |
| 22 | nextcloud-mcp-server | 251 |
| 23 | YourMemory | 238 |