claude-ia-mcp-tools
Exposes MCP tools for user CRUD operations (get, list, create, update, delete) by routing requests through shared business logic and an API client, using JSONPlaceholder as the demo backend.
README
API Client → Business Logic → MCP Tools
Small Python example showing how to reuse an API client and business logic from both normal application code and MCP tools.
Structure
src/example/
├── api/
│ └── api_client.py
├── business/
│ └── service.py
├── mcp/
│ └── server.py
└── main.py
The example exposes 5 operations:
get_userlist_userscreate_userupdate_userdelete_user
The MCP layer is deliberately thin: it validates MCP inputs and delegates to the business service. The business service delegates HTTP work to the API client.
Install
python -m venv .venv
# Windows:
.venv\Scripts\activate
# Linux/macOS:
source .venv/bin/activate
pip install -r requirements.txt
Run the MCP server
python -m src.example.mcp.server
Or configure the MCP client to launch:
python -m src.example.mcp.server
Use MCP server
Via terminal
{"jsonrpc":"2.0","method":"tools/list","id":1}
Or Claude
{
"mcpServers": {
"example-users": {
"command": "python",
"args": ["-m", "src.example.mcp.server"]
}
}
}
Or vía WebSocket (Railway deployment)
Live on Railway:
wss://claude-ia-mcp-tools-staging.up.railway.app
Connect with Python:
import asyncio
import json
import websockets
async def call_mcp():
uri = "wss://claude-ia-mcp-tools-staging.up.railway.app"
async with websockets.connect(uri) as ws:
# Call get_user
request = {
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "get_user",
"arguments": {"user_id": 1}
},
"id": 1
}
await ws.send(json.dumps(request))
response = await ws.recv()
print(json.loads(response))
asyncio.run(call_mcp())
Configure in Claude Desktop:
{
"mcpServers": {
"claude-ia-mcp-tools": {
"command": "uvx",
"args": ["mcp-websocket-client", "wss://claude-ia-mcp-tools-staging.up.railway.app"]
}
}
}
Available Tools:
get_user- Get one user by IDlist_users- List all userscreate_user- Create a new userupdate_user- Update user name/emaildelete_user- Delete a user
Important
This is a self-contained architectural example. The API client uses
https://jsonplaceholder.typicode.com as a public demo API.
For a real API, replace ApiClient implementation and keep the business/MCP
interfaces essentially unchanged.
Test workflow execution
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.