
FastAPI MCP-Style Server
A minimal FastAPI implementation that mimics Model Context Protocol functionality with JSON-RPC 2.0 support. Provides basic tools like echo and text transformation through both REST and RPC endpoints for testing MCP-style interactions.
README
FastAPI MCP-Style Server
Minimal FastAPI implementation that mimics a subset of Model Context Protocol (MCP) functionality.
Features
- Echo-style POST
/mcp
endpoint returning structured response (id, status, outputs) - JSON-RPC 2.0 endpoint
/mcp/rpc
supporting:mcp.list_tools
mcp.call_tool
(tools:echo
,uppercase
,query_manse
,calc_daewoon
)
- GET usage helper
/mcp
- Pydantic models for request/response
- Basic logging
- Tests (pytest) for REST + RPC
Quick Start
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
uvicorn main:app --reload
REST Usage
curl -X POST http://127.0.0.1:8000/mcp \
-H 'Content-Type: application/json' \
-d '{"inputs": {"text": "hello"}}'
JSON-RPC Examples
List tools:
curl -X POST http://127.0.0.1:8000/mcp/rpc \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"mcp.list_tools"}'
Call echo:
curl -X POST http://127.0.0.1:8000/mcp/rpc \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":"abc","method":"mcp.call_tool","params":{"name":"echo","arguments":{"text":"hello"}}}'
Call query_manse (first 5 rows):
curl -X POST http://127.0.0.1:8000/mcp/rpc \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":2,"method":"mcp.call_tool","params":{"name":"query_manse","arguments":{"limit":5}}}'
Call calc_daewoon (example date):
curl -X POST http://127.0.0.1:8000/mcp/rpc \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":3,"method":"mcp.call_tool","params":{"name":"calc_daewoon","arguments":{"yyyymmdd":"20250115"}}}'
Response example:
{
"jsonrpc": "2.0",
"id": 3,
"result": {
"outputs": [
{"type": "json", "content": {"asc_diff_days": 3, "desc_diff_days": 2}}
]
}
}
Meaning:
- asc_diff_days: 기준일 이후 다음 절기까지 (일수 / 3 반올림)
- desc_diff_days: 기준일 이전 직전 절기까지 (일수 / 3 반올림)
- 없으면 null
Environment Variables (DB)
Variable | Default | Description |
---|---|---|
MCP_DB_HOST | 192.168.31.136 | MariaDB host |
MCP_DB_PORT | 3306 | MariaDB port |
MCP_DB_USER | DB user | |
MCP_DB_PASSWORD | DB password | |
MCP_DB_NAME | manse | Database name |
Example run with overrides:
MCP_DB_HOST=127.0.0.1 MCP_DB_USER=app MCP_DB_PASSWORD=secret uvicorn main:app --reload
Run Tests
pytest -q
Next Ideas
- Streaming (SSE) outputs
- Prompts/resources primitives
- Auth layer (OAuth / API key)
- Tool change events
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.