Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.
1
Prepare the server locally
Run this once before adding it to Claude Code.
pip install mcp>=1.26.0 uvicorn pydantic
python main.py2
Register it in Claude Code
claude mcp add benchmark-mcp -- python /path/to/claude-mcp-app/main.pyReplace any placeholder paths in the command with the real path on your machine.
3
Make your agent remember this setup
benchmark-mcp's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Industry Benchmarking Tool for comparing company metrics
- Interactive bar chart widget for visual data comparison
- Dual transport support for SSE and Streamable HTTP
- Cross-platform compatibility with Claude and ChatGPT
Tools 2
benchmarking_toolCompares company metrics against industry averagesbenchmarking_widgetGenerates an interactive bar chart for metric comparisonTry it
→How does my restaurant's $45,000 yearly profit compare to the industry average in California?
→Compare my retail business revenue of $500,000 against industry benchmarks in Texas
→Benchmark my healthcare company's monthly income of $80,000 against regional averages
→How does my construction company in NY with $600,000 annual revenue compare?
Original README from dganesh5/claude-mcp-app
Benchmark MCP Server
MCP Server with Industry Benchmarking Tool - Compatible with both Claude and ChatGPT.
Features
- 📊 Industry Benchmarking Tool: Compare company metrics against industry averages
- 🎨 Interactive Widget: Visual bar chart comparison (MCP Apps)
- 🔄 Dual Transport: Supports both SSE and Streamable HTTP
- ✅ Cross-Platform: Works with Claude.ai and ChatGPT
Quick Start
With Poetry (Recommended)
# Install dependencies
poetry install
# Start server
poetry run python main.py
With pip
# Create virtual environment
python -m venv venv
source venv/bin/activate # or `venv\Scripts\activate` on Windows
# Install dependencies
pip install mcp>=1.26.0 uvicorn pydantic
# Start server
python main.py
Endpoints
| Endpoint | Transport | Use For |
|---|---|---|
/sse |
SSE | Claude, ChatGPT (via ngrok) |
/v1/mcp |
Streamable HTTP | ChatGPT native |
/mcp |
Streamable HTTP | Alias |
Usage with ngrok
# Start ngrok
ngrok http 8000
# Use the ngrok URL in Claude/ChatGPT:
# https://your-ngrok-url/sse
Project Structure
claude-mcp-app/
├── app/
│ ├── service/
│ │ ├── mcp_server.py # FastMCP instance
│ │ ├── data/ # Mock benchmark data
│ │ ├── tools/ # MCP tools
│ │ │ ├── benchmarking_tool.py
│ │ │ └── benchmarking_widget.py
│ │ └── widgets/ # HTML widgets
│ │ └── benchmarking_widget.html
├── common/
│ └── config.py # Configuration
├── main.py # Entry point
├── pyproject.toml # Poetry config
└── README.md
Example Prompts
- "How does my restaurant's $45,000 yearly profit compare to the industry average in California?"
- "Compare my retail business revenue of $500,000 against industry benchmarks in Texas"
- "Benchmark my healthcare company's monthly income of $80,000 against regional averages"
- "How does my construction company in NY with $600,000 annual revenue compare?"
License
MIT