A curated, opinionated list of high-quality remote Model Context Protocol (MCP) servers. This repository focuses on listing official and well-maintained MCP servers that can be accessed over the internet, helping developers discover reliable and production-ready services for their AI applications.
Model Context Protocol (MCP) is a protocol that enables AI models to interact with external tools and resources. Remote MCP servers allow clients to securely connect to these services over the internet.
This is not an exhaustive list of all remote MCP servers. We maintain high standards for inclusion:
Name | Category | URL | Authentication | Maintainer |
---|---|---|---|---|
Neon | Software Development | https://mcp.neon.tech/see | OAuth2.1 | Neon |
OneContext | RAG-as-a-Service | https://rag-mcp-2.whatsmcp.workers.dev/sse | OAuth2.1 | OneContext |
PayPal | Payments | https://mcp.paypal.com/sse | OAuth2.1 | PayPal |
LLM Text | Data Analysis | https://mcp.llmtxt.dev/sse | Open | LLM Text |
YepCode | Software Development | https://cloud.yepcode.io/mcp/{API_KEY}/sse | API Key | YepCode |
GitMCP | Software Development | https://gitmcp.io/docs | Open | GitMCP |
APIFY | Software Development | https://actors-mcp-server.apify.actor/sse?token=<YOUR_API_TOKEN>&actors=<ACTOR_NAMES> | API Key | Apify |
Sentry | Software Development | https://mcp.sentry.dev/sse | OAuth2.1 | Sentry |
Semgrep | Software Development | https://mcp.semgrep.ai/sse | Open | Semgrep |
To use MCP, you'll need to use a client that supports the MCP spec. A list of MCP clients can be found here.
The best place to start is with Cloudflare's MCP playground here. Simply copy and paste the server URL into the playground, authenticate with the service if required, and you're away!
Note: As the MCP spec is still in development, not all clients may support all features. In particular client support of OAUTH is not yet widespread.
For desktop clients the configuration you need to add to your client's config file will be
{
"mcpServers": {
"<REMOTE_MCP_SERVER_NAME>": {
"command": "npx",
"args": [
"mcp-remote",
"<REMOTE_MCP_SERVER_URL>"
]
}
}
}
We welcome contributions! Please follow these guidelines:
Join the MCP community to stay updated and connect with other developers:
This project is licensed under the MIT License - see the LICENSE file for details.
{
"mcpServers": {
"<REMOTE_MCP_SERVER_NAME>": {
"args": [
"mcp-remote",
"<REMOTE_MCP_SERVER_URL>"
],
"command": "npx"
}
}
}
Seamless access to top MCP servers powering the future of AI integration.