mcptoon
Token-efficient MCP CLI client. 99.87% less tokens on tool discovery. Zero deps. Cross-platform. Works with every AI agent.
mcptoon: Token-efficient MCP CLI client. 99.87% less tokens on tool discovery. Zero deps. Cross-platform. Works with every AI agent.
Token-efficient MCP CLI client. 99.87% less tokens on tool discovery.
What the project is
mcptoon is a Python project hosted on GitHub. Token-efficient MCP CLI client. 99.87% less tokens on tool discovery. Zero deps. Cross-platform. Works with every AI agent. Install 1,000 MCP tools locally. Schemas consume 0 tokens. Any agent, zero MCP config. The repository is maintained by activeing123 and tracks activity through its public issue tracker and commit history. Readers who want a working example rather than a bare library will find the documentation and the linked resources useful for getting a first build running.
What it offers
The mcptoon repository documents several concrete capabilities that shape how people use it. Cursor's mcpServers setting → unaffected (mcptoon is separate, not a server entry) Claude Desktop's claude desktop config.json → unaffected Mcptoon does not output MCP JSON-RPC protocol stream . it is a client, not a server --compact → tool names only: 99.9% savings (tiktoken cl100k base) --slim → tool schemas with params: 93% savings (tiktoken cl100k base) These points are taken from the project README, so they reflect what the maintainers actually ship rather than marketing claims. Checking the file list and the example directories gives a fuller picture of how each piece fits together.
How to set it up
Getting mcptoon running starts with cloning the source from https://github.com/activeing123/mcptoon. The README lists the commands needed to fetch the code and build or launch it. Representative steps from the documentation include: pip install mcptoon # zero deps, ~250KB docker build -t mcptoon . docker run --rm mcptoon help docker run --rm -v ~/.mcptoon:/root/.mcptoon mcptoon manifest --toon. After the code is on disk, the project instructions walk through configuration and any dependencies. Following the order shown in the README avoids the common setup mistakes that come from mixing steps.
License and project status
mcptoon is written primarily in Python and is released under the Apache-2.0 license, which sets the terms for reuse and redistribution. The project reports around 179 stars on GitHub, a signal of how many developers have bookmarked it. The source was last updated on 2026-08-21. The canonical location is https://github.com/activeing123/mcptoon, where the license file, the changelog and the open issues give the most current state of the work. Anyone planning to depend on it should read the license text directly before shipping it inside another product.
Editorial conclusion
The mcptoon source lives at https://github.com/activeing123/mcptoon under the Apache-2.0 license and is mainly written in Python. The README and the linked examples remain the place to confirm the current behaviour before adopting the project.
Community notes