MCP Streamable HTTP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Streamable HTTP Serversearch the web for latest AI news"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Servers over Streamable HTTP β Step-by-Step Guide
π Read the full article here: MCP Servers over Streamable HTTP (Step-by-Step)
This repository contains a complete, working example of how to build and run an MCP (Model Context Protocol) server using Python, mcp, and FastAPI. Youβll learn how to:
Expose tools and functions over HTTP using the MCP protocol
Connect those tools to AI assistants like Cursor
Use streamable HTTP as the transport
Mount multiple MCP servers in a FastAPI app
π Folder Structure
.
βββ docs/ # Diagrams and assets (e.g., mcp-client-server.png)
βββ fastapi_example/ # Example mounting multiple MCP servers in FastAPI
β βββ echo_server.py # A server exposing a simple echo tool
β βββ math_server.py # A server exposing a math tool
β βββ server.py # FastAPI app that mounts both echo and math servers
βββ .gitignore
βββ .python-version # Python version (for tools like pyenv or uv)
βββ pyproject.toml # Project config and dependencies
βββ readme.md # You're here!
βββ runtime.txt # Python runtime for platforms like Render
βββ server.py # Basic standalone MCP server using Tavily search
βββ uv.lock # Lockfile for uv dependency managerβΈ»
π Quickstart
Install uv (recommended Python package manager)
curl -LsSf https://astral.sh/uv/install.sh | shInstall dependencies and set up environment
uv venv && source .venv/bin/activate
uv pip install -r pyproject.tomlRun the basic MCP server This uses the Tavily API to expose a simple web_search tool.
uv run server.pyRun the FastAPI app with multiple MCP servers
uv run fastapi_example/server.pyThis will mount:
βΈ»
π§ͺ Debug with MCP Inspector
Install CLI support
uv add 'mcp[cli]'Launch the inspector
uv run mcp dev server.pyThen go to: http://localhost:6274/?MCP_PROXY_AUTH_TOKEN=...
βΈ»
π Connect to Cursor
In Cursor, add your MCP server under Chat Settings > MCP Servers:
{
"mcpServers": {
"tavily": {
"url": "http://localhost:8000/mcp/"
}
}
}β Note: You must include the trailing / in the URL.
βΈ»
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceAutomatically converts Python web backends (FastAPI, Flask, Django) into MCP servers by exposing API routes as MCP tools with near-zero boilerplate.Last updatedMIT
- Flicense-qualityDmaintenanceEnables deployment of MCP servers over HTTP, providing ready-to-use tools for text processing, math calculations, and social media content generation, accessible to AI assistants like GitHub Copilot and Claude.Last updated
- Flicense-qualityDmaintenanceA step-by-step guide and complete working example for building and running an MCP server with streamable HTTP transport using Python, mcp, and FastAPI, enabling AI assistants to access tools over HTTP.Last updated31
- Flicense-qualityDmaintenanceEnables building and running MCP servers over streamable HTTP, exposing tools to AI assistants like Cursor, with examples of mounting multiple servers in FastAPI.Last updated
Related MCP Connectors
MCP server exposing the Backtest360 engine API as tools for AI agents.
Self-hosted MCP gateway: turn any API, database or MCP server into AI connectors β no code.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yoβ¦
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/RuhamaCopilot/mcp-streamable-http'
If you have feedback or need assistance with the MCP directory API, please join our Discord server