The part nobody else has: agents need zero setup

Native MCP means editing a JSON file for every agent, in every format, and restarting. Proxy tools mean running a service and pointing each agent at it.

mcptoon needs neither. It is a program your agent already knows how to run:

You:    "What tools do we have? Then fetch https://example.com and summarize."
Agent:  $ mcptoon manifest --compact        ← gets a name index, not schemas
Agent:  $ mcptoon call fetch fetch '{"url":"https://example.com"}'

No mcpServers entry. No plugin API. Nothing to register, nothing to restart. Want it automatic? One line in your agent's instruction file (CLAUDE.md / AGENTS.md / system prompt) is enough — that is prompting, not configuration.

This is also why mcptoon reaches where MCP cannot: shell scripts, CI pipelines, cron jobs, aider, terminal-only environments — anything that can execute a command.

Why mcptoon exists

If you run more than one AI coding agent, you have both of these problems today:

1. Every agent keeps its own MCP config, in its own file, in its own format.

Add a server in Cursor, forget Claude. Fix a path in Claude, break Cursor. Repeat weekly.

2. Tool discovery burns your context window before any work starts. A listing of 255 tools costs 71,929 tokens as raw JSON schemas (measured with tiktoken cl100k_base). On a 128K context, that is more than half the window spent on syntax — before the model has answered anything.

mcptoon fixes both with one file and one binary.

Try it in 60 seconds

pip install mcptoon        # pure stdlib, ~250KB, no deps

mcptoon quickstart         # finds servers you already configured, lists their tools
mcptoon demo               # live side-by-side: JSON vs mcptoon, real token counts

quickstart detects existing configs, imports them, and shows what you have. demo spins up a sample fetch server and prints the before/after numbers on your machine — no trust required, measure it yourself.

Runs on Windows, macOS and Linux. Being pure Python makes Windows a first-class citizen — no node-gyp builds, no POSIX-only scripts.

The three moves

1 · Configure once — sync

mcptoon add fetch --stdio npx -y @modelcontextprotocol/server-fetch
mcptoon sync               # writes native config to every detected agent

mcptoon merges instead of overwriting — servers you configured manually stay put. One command gives you cross-agent tool management: a single source of truth for MCP servers across every agent on the machine, no copy-pasting JSON between Cursor, Claude and friends.

mcptoon sync --dry           # preview the writes
mcptoon sync --agent cursor  # target one agent

2 · Pay for names, not schemas — manifest

Your agent asks "what tools exist?" mcptoon answers with a name index. Schemas stay on disk in ~/.mcptoon/config.json and never enter the context.

$ mcptoon manifest --compact
fetch: fetch(url) · github: search_repos(q), get_file(repo, path) · sqlite: query(sql) · ...

In human terms: 71,929 tokens is roughly a 300-page book. 123 tokens is a sticky note.

Choosing between approaches? docs/comparison.md breaks down setup cost, token cost and safety, category by category.

It is a dial, not a switch: --json is always available when you want zero ambiguity, and call results default to plain text, security-checked.

3 · One door in front of every server — serve

Point your agent at a single entry instead of N servers:

"mcptoon": { "command": "mcptoon", "args": ["serve"] }

mcptoon serve                  # stdio — one agent
mcptoon serve --listen :8080   # HTTP — multiple agents, remote machines

Parallel manifest loading (20 workers, 100 servers ≈ 5s), a 5-minute schema cache, and a 30s timeout per call so one hung server cannot stall your session.

Everything else in the box

Why health matters: a 2026 community audit found 52% of published MCP servers unreachable. Configured ≠ alive.

── mcptoon health: 3/5 alive ──────────────
  ✓ fetch     [stdio]  1 tool     120ms  ok
  ✗ brave     [stdio]  0 tools  10002ms  timeout → Timed out after 10s
  ✓ github    [http]  12 tools    340ms  ok

Under the hood

• Errors that agents can act on — every failure returns a structured envelope with a fix suggestion ("server fetchh not found — did you mean fetch?"), so your agent self-corrects instead of stalling until you rescue it.
• Cross-server fuzzy search — mcptoon search star finds the right tool across every configured server, with relevance scoring.
• call --auto — give just the tool name; mcptoon finds the server that provides it.
• Shell completions — bash, zsh, fish and PowerShell.
• JSON or TOML config — whichever reads better for you, both live in ~/.mcptoon/.
• Local usage log — see which tools you called and when. The record never leaves your machine.

Security, applied to every call

Supply-chain safety comes free with zero dependencies: no npm subtree, no postinstall scripts, nothing to audit but ~6,800 lines of readable Python.

MCP servers run code on your machine and return arbitrary text into your agent's context. mcptoon inspects every result before it gets there:

No telemetry. No analytics. No phone-home. API keys pass through from your config or environment and are never stored by mcptoon.

Works with

Claude Desktop · Claude Code · Cursor · Cline · Windsurf · VS Code Copilot · Codex · Gemini CLI · OpenCode — plus aider, shell scripts, CI jobs and anything else that executes commands, including environments with no MCP support at all. That is what being a CLI first means.

For developers

from mcptoon.client import MCPClient

with MCPClient(stdio=["npx", "-y", "@modelcontextprotocol/server-fetch"]) as c:
    tools = c.list_tools()
    result = c.call_tool("fetch", {"url": "https://example.com"})

git clone https://github.com/activeing123/mcptoon.git && cd mcptoon
pip install -e . --no-build-isolation && pip install pytest
python -m pytest tests/ -v          # 531 tests, green expected
docker run --rm -v ~/.mcptoon:/root/.mcptoon mcptoon manifest --compact

Zero third-party imports is a hard rule enforced in review. New features need tests. ~6,800 lines of Python across 14 modules — see CONTRIBUTING.md.

License

Apache 2.0 — see LICENSE and NOTICE.