servers
awesome-mcp-servers
| servers | awesome-mcp-servers | |
|---|---|---|
| 401 | 52 | |
| 87,066 | 83,722 | |
| 2.6% | - | |
| 9.8 | 9.9 | |
| 8 days ago | 3 months ago | |
| TypeScript | ||
| GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
servers
- Build a tiny MCP server in JavaScript -Claude, Codex friendly
-
Can you build a successful business in a Claude Code loop?
Most agents don't speak raw HTTP — they speak MCP. So the real distribution surface is a tiny MCP server that exposes each endpoint as a tool and does the paying under the hood. The agent calls web_search(query); the server hits the paid endpoint, handles the 402 with its operator's wallet, returns JSON. One line to install:
-
Building an MCP server with Node.js
The Model Context Protocol (MCP) is an open standard for connecting AI hosts (Claude, ChatGPT, Cursor, VS Code, and others) to external context and actions through a structured protocol instead of ad-hoc plugins.
-
Why Dremio's Value Is Unique to Apache Iceberg Lakehouses and Agentic Analytics
Model Context Protocol specification
-
How I Built an MCP Server for M-PESA — and Why It Matters for East Africa
That changed when I built mpesa-mcp — a Model Context Protocol server that wraps the Daraja API and makes it directly available to Claude, GPT-4, and Gemini.
-
Let your AI agent test your API: two-go's AI layer and MCP server
If you haven't run into it yet, MCP (Model Context Protocol) is an open standard for exposing tools to AI agents. two-go ships an MCP server that runs over stdio with no dependencies, no URL, no account, and no API key. It's all local.
-
Introducing LlamaStash: a zero-overhead, terminal-native llama.cpp launcher
MCP server surface. The CLI is already agent-friendly, so I'm double minded about whether a Model Context Protocol server would make integration smoother. I'm personally not a fan of MCP and prefer skills and CLIs.
-
How Claude Code's Skills System Actually Works
As noted in the Model Context Protocol (MCP) Introduction, this protocol allows Claude to interact with systems like GitHub and local databases through a standardized interface.
-
I got tired of re-explaining my codebase to every coding agent — so I made critical memory live in the repo next to code
Keep the project's living context: current task state, decisions, conventions, known footguns as plain Markdown committed to the repo, and expose it to the agent over MCP.
-
Best Claude Code MCP Servers in 2026 (Ranked)
The MCP ecosystem doubles every few months. Bookmark the official MCP servers repository for the canonical list.
awesome-mcp-servers
-
I built the npm audit for MCP servers
The MCP (Model Context Protocol) ecosystem has exploded. awesome-mcp-servers lists 200+ servers — but there was no way to know if any of them actually worked.
-
Shipping x402 USDC Payments to Base + Solana Mainnet for an MCP Server
✅ Merged into awesome-mcp-servers
-
Claude Code Skills vs MCP Servers — What to Use, How to Install, and the Best Ones in 2026
GitHub Awesome Lists — awesome-mcp-servers (84K+ stars) and awesome-claude-skills (52K+ stars).
-
HTTP 402 + USDC: Pay-per-use AI APIs for Autonomous Agents
Listed on: awesome-mcp-servers (PR #4364)
-
My AI Agent Finally Made Money. It Took 200+ Runs and 41 Days.
First it was MCP servers. The Model Context Protocol was getting popular, and the agent decided to build MCP-compatible tools. It even got listed in the awesome-mcp-servers repo (82K+ stars). Cool. But nobody was paying for MCP servers.
- 93% of a Claude Code Session Is Noise. Here's the Proof.
- My Claude Code Sessions Hit 70MB. So I Built a Distiller.
-
4,000 Runs in 7 Days: The Overnight Pattern That Proved Enterprise Demand for Korean Data
Korean Data MCP: The MCP server that lets AI assistants access all these scrapers directly. PR pending for awesome-mcp-servers listing.
-
Show HN: MCP Inspector – connect and test any MCP server
This project emerged out of frustration that the existing MCP inspectors either require to sign up, require to download something, or are not fully spec compliant. I just wanted something that I could rapidly access for testing.
Additionally, it was very important for me that the URL can capture the configuration of the MCP server. This allows me to save URLs to various MCPs that I am troubleshooting. Because the entire configuration is persisted in the URL, you can bookmark links to pre-configured MCP instances, e.g.,
https://glama.ai/mcp/inspector?servers=%5B%7B%22id%22%3A%22t...
In order to ensure that the MCP inspector is fully spec compliant, I also shipped an MCP test server which implements every MCP feature. The latter is useful on its own in case you are building an MCP client and need something to test against https://mcp-test.glama.ai/mcp
Finally, MCP Inspector is fully integrated in our MCP server (https://glama.ai/mcp/servers) and MCP connector (https://glama.ai/mcp/connectors) directories. At a click of a button, you can test any open-source/remote MCP.
If you are building anything MCP related, would love your feedback. What's missing that would make this your go-to tool?
-
Why M-Pesa, Africa's Talking, and USSD are missing from AI agent tooling — and what I did about it
It's submitted to punkpeye/awesome-mcp-servers — the first African fintech entry in that list (82k stars).
What are some alternatives?
claudebox - The Ultimate Claude Code Docker Development Environment - Run Claude AI's coding assistant in a fully containerized, reproducible environment with pre-configured development profiles.
AgentNetworkProtocol - AgentNetworkProtocol(ANP) is an open source protocol for agent communication. Our vision is to define how agents connect with each other, building an open, secure, and efficient collaboration network for billions of intelligent agents.
typescript-sdk - The official TypeScript SDK for Model Context Protocol servers and clients
GhidraMCP - MCP Server for Ghidra
goose - an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
fastmcp - A TypeScript framework for building MCP servers. [GET https://api.github.com/repos/punkpeye/fastmcp: 404 - Not Found // See: https://docs.github.com/rest]