Click on "Deploy 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., "@MCPServerDemo multiply 12 by 8"
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.
This project implements a simple JSON-RPC server using FastAPI, Uvicorn, and jsonrpcserver in Python. It exposes add and multiply methods.
Clone the repository:
git clone <your-repo-url>
cd json-rpc-serverCreate a virtual environment and install dependencies using uv:
uv venv
.\.venv\Scripts\activate # On Windows
# source .venv/bin/activate # On Linux/macOS
uv pip install fastapi uvicorn jsonrpcserverRelated MCP server: FastAPI MCP Demo Server
To start the development server with auto-reloading:
.\.venv\Scripts\activate # On Windows
# source .venv/bin/activate # On Linux/macOS
uv run python -m uvicorn main:app --reloadThe server will run at http://127.0.0.1:8000/.
A simple test endpoint to confirm the server is running.
Request:
# Using curl (Linux/macOS/Git Bash)
curl http://127.0.0.1:8000/
# Using Invoke-RestMethod (PowerShell)
Invoke-RestMethod -Uri "http://127.0.0.1:8000/" -Method GetResponse:
{
"message": "FastAPI is running!"
}This is the main JSON-RPC endpoint for add and multiply methods.
Request:
# Using curl
curl -X POST -H "Content-Type: application/json" -d '{"jsonrpc": "2.0", "method": "add", "params": [2, 3], "id": 1}' http://127.0.0.1:8000/
# Using Invoke-RestMethod (PowerShell)
Invoke-RestMethod -Uri "http://127.0.0.1:8000/" -Method Post -Headers @{ "Content-Type" = "application/json" } -Body '{"jsonrpc":"2.0","method":"add","params":[2,3],"id":1}'Response (Example):
{"jsonrpc": "2.0", "result": 5, "id": 1}Request:
# Using curl
curl -X POST -H "Content-Type: application/json" -d '{"jsonrpc": "2.0", "method": "multiply", "params": [4, 5], "id": 1}' http://127.0.0.1:8000/
# Using Invoke-RestMethod (PowerShell)
Invoke-RestMethod -Uri "http://127.0.0.1:8000/" -Method Post -Headers @{ "Content-Type" = "application/json" } -Body '{"jsonrpc":"2.0","method":"multiply","params":[4,5],"id":1}'Response (Example):
{"jsonrpc": "2.0", "result": 20, "id": 1}curl -X POST -H "Content-Type: application/json" -d '[{"jsonrpc": "2.0", "method": "add", "params": [2, 3], "id": 1},{"jsonrpc": "2.0", "method": "multiply", "params": [2, 30], "id": 2}]' http://127.0.0.1:8000/
Invoke-RestMethod -Uri "http://127.0.0.1:8000/" -Method Post -Headers @{ "Content-Type" = "application/json" } -Body '[{"jsonrpc":"2.0","method":"add","params":[2,3],"id":1},{"jsonrpc":"2.0","method":"multiply","params":[2,30],"id":2}]'uv add fastmcpuv run fastmcp dev inspector TestMPCserver.py uv run fastmcp run TestMPCserver.pyuv run fastmcp install claude-desktop TestMPCserver.pyuv run fastmcp run DataprovidersMCPServer.pyuv run fastmcp install claude-desktop DataprovidersMCPServer.pyuv add langchain langchain-openai langchain-mcp-adapters python-dotenv streamlit logging pandas fastmcp python-dotenv jsonrpcserver uvicorn streamlit langchain-ollama fastapi uvicorn serversendevent:app uvicorn Streamable:appThis project includes a streaming HTTP endpoint demonstration using FastAPI's StreamingResponse.
uv run uvicorn Streamable:app --reloadThe server will run at http://127.0.0.1:8000/stream and sends 10 chunks with 1-second intervals.
python StreamableClient.pyThe client demonstrates both async and synchronous methods to consume the streaming response.
# Using curl (Linux/macOS/Git Bash)
curl http://127.0.0.1:8000/stream
# Using Invoke-RestMethod (PowerShell)
Invoke-RestMethod -Uri "http://127.0.0.1:8000/stream" -Method GetA launch.json file is provided in the .vscode directory to enable debugging with VS Code. You can set breakpoints in main.py and run the "Python: FastAPI" configuration.
add two numbers
Inputs: a (required), b (required). Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'add' has a clear and distinct purpose of adding two numbers, leaving no room for confusion or misselection by an agent.
Since there is only one tool named 'add', naming consistency is inherently perfect. There are no other tools to compare against, so no inconsistencies in patterns, styles, or conventions can arise.
A single tool is too few for most server purposes, as it severely limits functionality and scope. For a server named 'MCPServerDemo', which suggests a broader demonstration or utility set, one tool feels thin and inadequate, indicating a likely mismatch with the intended scope.
The tool surface is severely incomplete, as it only covers a basic arithmetic operation (adding two numbers) with no other related operations like subtraction, multiplication, or division. This leaves significant gaps for any practical use case, making it impossible to handle a full range of tasks in the implied domain of mathematical or utility functions.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
