Click on "Install 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 installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
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.
