linsun/simple-agent-and-mcp-server
If you are the rightful owner of simple-agent-and-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A simple implementation of a Model Context Protocol server that manages context data for AI models.
The Model Context Protocol (MCP) Server & Agent is designed to manage context data for AI models, facilitating efficient data handling and retrieval. It provides a straightforward setup process and a set of API endpoints to store, retrieve, and delete context data. The server runs locally and can be easily integrated with AI models to enhance their contextual understanding. Additionally, the agent can connect to the server and utilize tools like a calculator to perform operations based on the context provided.
Features
- Simple setup and installation process.
- API endpoints for storing, retrieving, and deleting context data.
- Local server running on localhost: 8080.
- Agent capable of connecting to the server and using tools.
- Sample output demonstrating tool usage and reasoning.
Usages
local integration stdio
uv run server.py
remote integration sse
mcp.run(transport='sse', host="0.0.0.0", port=8000)
remote integration streamable http
paths:
/mcp:
post:
x-ms-agentic-protocol: mcp-streamable-1.0platform integration github
{"command": "docker", "args": ["run", "-e", "GITHUB_PERSONAL_ACCESS_TOKEN", "ghcr.io/github/github-mcp-server"]}development framework fastmcp
from mcp.server import FastMCP
app = FastMCP('demo')
@app.tool()
async def query(): ...
