Qonye/MCP-server
If you are the rightful owner of 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 lightweight, efficient server implementation for handling context operations with large language models.
The Model Context Protocol (MCP) server provides a robust API for managing documents and contexts used by language models. It features automatic task queuing, rate limiting, and error handling to ensure reliable operation even under high load or when encountering errors. The server is designed to handle document and context management efficiently, with built-in support for asynchronous task processing and simple authentication mechanisms. It also includes auto-generated API documentation for ease of use.
Features
- Document Management: Create, retrieve, and delete document objects
- Context Management: Create, update, retrieve, and delete context collections
- Async Task Processing: Background processing of tasks with error isolation
- Rate Limiting: Built-in request throttling to prevent overload
- Error Handling: Failed tasks are stored for later review and retry
Usages
usage with local integration stdio
python mcp.run(transport='stdio') # Tools defined via @mcp.tool() decorator
usage with local integration ide plugin
{
"mcpServers": {
"weather": {
"command": "python",
"args": ["weather.py"]
}
}
}usage with remote integration sse
python mcp.run(transport='sse', host="0.0.0.0", port=8000) # Specify SSE endpoint
usage with remote integration streamable http
yaml
paths:
/mcp:
post:
x-ms-agentic-protocol: mcp-streamable-1.0 # Copilot Studio integrationusage with platform integration github
{"command": "docker", "args": ["run", "-e", "GITHUB_PERSONAL_ACCESS_TOKEN", "ghcr.io/github/github-mcp-server"]}usage with platform integration atlassian
{
"mcpServers": {
"jira": {
"command": "python",
"args": ["jira_integration.py"]
}
}
}usage with development framework fastmcp
python
from mcp.server import FastMCP
app = FastMCP('demo')
@app.tool()
async def query(): ...
