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., "@peekmcp Show me the schema and a sample from sales.csv"
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.
peekmcp
Trending repos show heavy investment in MCP, agent context pipelines, and token-efficient tooling, but most file MCP servers expose raw bytes or require databases. Developers frequently have quick CSV/JSON/JSONL artifacts that agents need to inspect without loading entire files into context. PeekMCP fills that gap with a zero-dependency stdio MCP server and CLI that provides schema, samples, and paginated filtered queries.
Target audience: AI agent developers, data engineers, and local LLM users who need safe, token-efficient access to flat files during coding, analysis, and automation.
Related MCP server: MCP Data Catalog
⨠Zero-dependency MCP stdio server with list_files, inspect_file, and query_table tools
⨠CLI for listing, inspecting, and querying CSV/TSV/JSON/JSONL files
⨠Token-saving pagination, column selection, substring filtering, and truncated cells
# Install
pip install peekmcp
# Run
peekmcp --helpgit clone https://github.com/YOUR_USERNAME/peekmcp.git
cd peekmcp# Create virtual environment
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
# Install in development mode
pip install -e ".[dev]"
# Run tests
pytest -vThe GIF above was recorded using Charm VHS:
vhs < demo.tape# Show help
peekmcp --help
# Common usage examples
peekmcp --examplegraph LR
A[Input] --> B[Core Engine]
B --> C[Output]
B --> D[Plugins]
D --> E[Extensions]Contributions are welcome! Please:
Fork the repo
Create a feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request
MIT Š 2026 â See LICENSE for details.
If this project helped you, please â star it!
This server cannot be deployed
Query, join, profile, clean and convert CSV/JSON/Parquet with server-side DuckDB over MCP.
Nifty's MCP server â exposes tasks, projects, messages, and files as tools for AI agents.
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
