Mcptoon

What is Mcptoon about?

Mcptoon provides a single, pure‑Python command‑line gateway that stores all your MCP tools, schemas, and agent skills locally. It replaces the traditional approach of injecting full JSON schemas into every LLM turn, shrinking tool descriptions from tens of thousands of tokens to a compact name index (‑99.2% token reduction) while keeping the full schema available on demand.

How to use Mcptoon?

1. Install – pip install mcptoon (only the Python standard library is required).
2. Quick start – mcptoon quickstart discovers existing MCP servers, writes the necessary configuration into every detected agent (Claude, Cursor, Codex, Windsurf, etc.), and registers the gateway.
3. View tools – mcptoon manifest shows the compact catalog (e.g., 255 tools = 581 tokens).
4. Call a tool – mcptoon call <server> <tool> '{"arg":"value"}' (add --toon to compress the result).
5. Sync agents – mcptoon sync propagates the catalog to all 103+ supported clients without manual JSON editing.
6. Discover & install – mcptoon discover scans installed tools, mcptoon install --search <keyword> finds new tools across 17k+ MCP servers, and mcptoon install <name> --npm <package> adds them.
7. Manage skills & docs – mcptoon skills sync, mcptoon docs index <dir>, mcptoon docs resolve "query".
8. Upgrade – mcptoon upgrade updates the CLI to the latest version.

Key Features

• Zero‑dependency, offline‑first (565 KB install, pure stdlib).
• Token optimization: compact name index (‑99.2%) and optional result compression (--toon, ~5‑6% saving).
• One‑click configuration for 103+ agents (CLI‑leg or MCP‑serve leg).
• On‑demand schema retrieval – full tool definition fetched only when needed.
• Tool discovery across 17 000+ MCP servers; plain‑language search and select.
• Native CLI with over 70 commands (manifest, call, install, sync, openapi, graphql, OAuth, bake, docs, kb, etc.).
• Skill management – single 39‑token pointer plus lookup, eliminating duplicated SKILL.md files.
• Docs & knowledge base – markdown indexing, chapter‑level retrieval, passage search.
• Safety guards: destructive‑action block, prompt‑injection detection, credential‑leak prevention.
• Extensible – supports OpenAPI, GraphQL, OAuth flows, saved connections, and custom code sandbox (exec).

Use Cases

• Agent developers who need hundreds of tools without blowing the LLM context window.
• Teams sharing a unified catalog of tools and skills across IDEs, terminals, and GUI agents.
• Offline environments where no external service or telemetry is allowed.
• Rapid prototyping of new MCP integrations; discover and install tools in seconds.
• Cost‑sensitive workloads where token usage directly impacts expense.

FAQ

Q: Do I need any external libraries? A: No. Mcptoon runs on the Python standard library only.

Q: How does the token saving work? A: It replaces full JSON schemas with a tiny name index (≈2.2 tokens per tool) and fetches the full schema only when a tool is actually called.

Q: What if my agent cannot run a shell? A: Mcptoon can run as an MCP server (mcptoon serve) and agents can connect to the single mcptoon entry.

Q: Is any data sent to a remote service? A: No telemetry or analytics are transmitted. Only tool discovery queries public registries.

Q: How do I update Mcptoon? A: Run mcptoon upgrade – it checks PyPI and updates in one command.

Q: Can I revert the configuration changes? A: Yes. mcptoon restore removes the gateway entry, and mcptoon off disables it without deleting your original servers.

https://github.com/user-attachments/assets/0272d3a8-c74f-428d-8559-fbf804ce0685

---

🚀 Quick Start (Choose Your Way)

When installed, mcptoon automatically injects its own official skill (/mcptoon) into your agents. You never need to memorize terminal commands — just ask directly in Cursor, Claude Code, Windsurf, or DSH:

# Ask the built-in skill anytime:
"Load /mcptoon skill and check what MCP tools I currently have."
"Help me find an MCP tool that converts HTML to PDF and call it."
"The tool output was truncated, retrieve the full original copy."
"How many tokens did mcptoon save for me today?"
"Doctor self-check: are all my MCP servers connected properly?"

Your agent loads /mcptoon and drives everything behind the scenes!

# 1. Install (zero dependencies, 565KB)
pip install mcptoon

# 2. One command: detect MCP servers & auto-configure agents
# (Also self-installs `/mcptoon` skill into all detected agents)
mcptoon quickstart

# 3. View compact tool catalog (-99.2% tokens)
mcptoon manifest

# 4. Route tasks to skills or doc chapters (<5ms)
mcptoon skills resolve "write git commit message"
mcptoon docs resolve "how does release gating work"

Is it actually saving you anything? After a fresh install mcptoon can sit in direct mode — installed but not wired into the agent — and save nothing. See Which mode is cheapest?, or just run mcptoon mode.

⚡ Core Capabilities at a Glance

💥 Save context (why ①)

🧩 One config, every agent (why ②)

• ✅ Compact name index (−99.2%): 255 tools → 581 tokens, full schema fetched on demand• ✅ Lossless result compression: reversible, retrieve the original behind any handle• ✅ Session dedup: byte-identical output in one turn becomes a reference• ✅ Skills the same way: one 39-token pointer + one lookup replaces every SKILL.md• ✅ Docs too: docs feeds 1 chapter, not 19 — 40k → 17k tokens per question• ✅ Honest numbers: real tiktoken accounting via mcptoon bench

• ✅ Native CLI: any shell-capable agent runs mcptoon and gets every feature — no MCP server, no config• ✅ GUI clients too: sync writes the JSON for Claude, Cursor, Cline, Windsurf, VS Code, Claude Code — 6 here, 103+ supported• ✅ Verified list: 42 clients run the CLI directly, 61 mount one mcptoon serve entry• ✅ Skills too: one catalog distributed to every agent's folder (skills sync)• ✅ Import what you have: pull servers from Claude / Cursor / Cline / Windsurf• ✅ One-command setup: quickstart = discover + configure + show tools• ✅ Fine control: toggle on/off, policy sets each tool's output tier, --version-gate / --tombstone for skills

🔍 Find & call (why ③)

🔌 Drive any API, not just MCP

• ✅ Cross-registry search: plain-language search across 17,000+ MCP servers• ✅ Discover what's already installed: discover scans existing client configs — nothing to reinstall• ✅ Call anything: call headless, or call --auto to auto-find the server• ✅ On-demand schema: inspect only when a tool is actually used• ✅ Pick for a task: select "<task>" returns just the top few• ✅ Export anywhere: manifest --format openai|openapi|mcp

• ✅ OpenAPI / Swagger: any REST API as commands (openapi list|call)• ✅ GraphQL: any endpoint as commands (graphql list|call)• ✅ OAuth built in: PKCE login, client-credentials, Dynamic Client Registration• ✅ MCP resources & prompts: resources, prompts, complete• ✅ Saved connections: bake — secrets by reference only (env: / file:)• ✅ Code sandbox: exec — only stdout enters context

🛡️ Safe, small, private	📚 Docs & doctor
• ✅ Zero dependencies: pure standard library, pyproject.toml clean• ✅ 565KB, installs in 2s• ✅ 100% local & private: no cloud, no telemetry, air-gap ready• ✅ Guards: destructive-op + prompt-injection + credential-leak checks on every call• ✅ XDG compliant: sandbox-friendly --dir isolation	• ✅ Docs router: docs indexes a Markdown tree, feeds 1 chapter instead of 19 (40k → 17k tokens)• ✅ Search inside docs: kb returns passages, not whole files (95KB → 3 snippets)• ✅ Self-heal: doctor repairs stdio pipes & environments; health probes every server• ✅ Live proof: bench / demo show the real numbers on your machine• ✅ Transparent footer: footer-facts prints live savings after each turn

Every command, with flags, is in All commands.

---

Why mcptoon: Solving Context Window Bloat & Multi-Agent Config Fragmentation

mcptoon is a zero-dependency local tool gateway and skill manager for LLM agents. In vanilla MCP architecture, every agent (Claude Code, Cursor, Windsurf, Codex, etc.) must inject the full JSON Schema definitions of all installed tools into its context window, resending them on every single turn.

According to our real-machine benchmark data: mounting just 255 common MCP tools consumes 71,929 tokens in descriptions alone, eating over half of a standard 128K context window before the first user prompt is processed. This not only inflates token costs unnecessarily, but also dilutes the model's attention, causing severe tool confusion and parameter hallucinations. mcptoon compresses these 71,929 tokens down to 581 tokens (−99.2%) using a compact name index, fetching schemas on demand only when a tool is actually called.

How Token Optimization Works: On-Demand Tool Retrieval & Dynamic Schemas

mcptoon keeps those descriptions on disk, not in context, and hands the agent a compact view instead:

• A name index, not full schemas. Picking a tool only needs its name — 255 tools become 581 tokens (−99.2%). The full schema is fetched on demand with mcptoon inspect, only when a tool is actually called.
• Skills the same way. One resident pointer (39 tokens) plus one lookup (791 tokens) replaces loading every SKILL.md in full — 1,572,330 → 39 + 791 (−99.99%).
• Results too. --toon re-encodes a tool's result as standard TOON. Measured 5.7% smaller on a mixed result sample, ranging 1.8%-48.6% by result shape — a list of records barely shrinks, a single record halves. Not a flat 34%: see assets/benchmark_results.json.

Nothing is lost: the full schema and the full skill text stay one command away. Only the context window is spared.

mcptoon is a 565KB, zero-dependency native CLI that manages every MCP tool and agent skill on your computer — and shares them across all your agents with no config written by you.

This isn't just us talking

Those numbers are ours — but "loading every tool schema into context is expensive" is not a claim only we make:

• Anthropic's engineering write-up — tool schemas flooding the context window is a real cost; one example drops from 150,000 tokens to 2,000
• Firecrawl's benchmark — the same task cost 1,365 tokens via CLI vs 44,026 via MCP (32×)
• Scalekit's benchmark — CLI 10–32× cheaper, 100% reliable vs MCP's 72%
• MCP-Zero (arXiv:2506.01056) — on-demand tool retrieval, near-constant cost regardless of tool count

mcptoon is the one you can use today: it covers any agent that can run a shell, and writes a single hookup line into the mainstream GUI clients it knows.

---

Two ways in

Install once, and every AI you have — Claude Desktop, Claude Code, Codex, Cursor, Windsurf, Cline, VS Code Copilot, Gemini CLI, Qwen Code, Zed, Crush, opencode and any other agent — shares all the tools and skills you already have. You write nothing in any agent's config.

→ Install and go

Script it. mcptoon is a plain CLI with stable JSON output and an mcptoon serve MCP endpoint — wire it into your own agent, CI, or app.

→ Commands and formats

Measure your numbers: pip install mcptoon && mcptoon bench — it reports your own catalog, not the fixed 255-tool sample below (that sample's method is in docs/tiktoken-benchmarks.md).

	Without mcptoon	With mcptoon
Descriptions in context	full description of every tool + skill, re-sent every turn	a compact view — 581 tokens for 255 tools (−99.2%, lossless)
Adding a tool or skill	hand-write JSON in every agent	one command — no agent config touched
Which agents get it	only the ones you configured	every agent on the machine — they just run mcptoon
Finding tools & skills	hunt GitHub by hand	install --search (17,000+ MCP servers) + skills search
Starting from scratch	wire tools one by one	4 built-in starter packs — one command to a working set

Skills work the same way: 1,572,330 tokens of SKILL.md text → 39 resident + 791 per lookup (−99.99%). Call results shrink a further ~6% with --toon (shape-dependent).

---

Path 1 · I just use AI tools

You have a desktop AI — Claude, Codex, Cursor, Windsurf, Cline, VS Code Copilot, and 97 more (full list of 103 →). Today, adding a tool or a skill means hand-editing that agent's JSON. mcptoon removes that step:

1. Install once.

   pip install mcptoon && mcptoon quickstart
   

   quickstart finds your MCP servers, writes your config, and registers mcptoon in every agent it detects. (Skip quickstart and the first command you run still self-heals: it installs mcptoon's own skill into each agent and builds the skill index, once per machine.)

2. Add tools and skills in one place — here, not in each agent.

   mcptoon install --search github     # find and install any MCP server
   mcptoon skills search "make a PDF"  # find a skill by what it does
   

3. Use them from any agent. Your agent runs mcptoon like any other command — no config, no restart. See Works with every AI agent.

Want a head start? Four built-in starter packs — essentials, web-research, code-review, docs — stand up a working toolset in one command:

mcptoon install --pack essentials

---

Path 2 · I build with MCP / agents

mcptoon is a plain CLI with scriptable output, plus an MCP endpoint when you want one.

mcptoon manifest --format json      # machine-readable tool index
mcptoon call <server> <tool> '{}'   # call any tool, JSON or --toon output
mcptoon serve                       # expose every configured server behind one MCP endpoint

• Stable output — JSON by default, --toon for smaller results (shape-dependent, 5.7% on a mixed sample), --format mcp to export standard MCP JSON.
• mcptoon serve — stdio or HTTP, connection pooling, per-agent keys, for clients that insist on a proxy.
• Zero dependencies — pure Python standard library, so it drops into any environment (CI, containers, air-gapped).

Full reference: DEVELOPERS.md and All commands.

---

Contents

• Why mcptoon
• How the token saving works
• This isn't just us talking
• Two ways in
• Path 1 · I just use AI tools
• Path 2 · I build with MCP / agents
• 30 seconds up and running
• What it does
• Where the tools come from
• The three bills
• Install
• Works with every AI agent — 103 clients (42 CLI · 61 serve)
• Why a CLI, not a proxy
• Which mode is cheapest?
• All commands
• Trust and safety
• Credits and references
• Contributing
• Troubleshooting & FAQ
• License

---

30 seconds up and running

pip install mcptoon                          # pure stdlib, 565KB, zero dependencies

# One command: find your MCP servers, write your config, register the gateway
# in every agent you have, and show you what it found:
mcptoon quickstart

# See every tool available (names-only by default; 255 tools cost 581 tokens):
mcptoon manifest

# Call a tool (JSON output by default; add --toon to save more).
# `everything` is only present if you already had it; otherwise add the built-in
# zero-dependency demo server first (no Node, no network) and call that:
mcptoon add demo --stdio python -m mcptoon demo-server
mcptoon call demo echo_message '{"message":"hi"}'

quickstart is also what makes mcptoon visible: it writes mcptoon serve into each agent's config as the reserved server mcptoon, so your agent can see mcptoon itself. Already synced? Re-register with mcptoon sync --self (plain mcptoon sync only writes your servers); check the state any time with mcptoon status.

Two ways in — and you don't pick one. mcptoon is a CLI first: a shell-capable agent runs mcptoon commands, and that is the cheapest path — the schemas never enter context. quickstart also registers mcptoon's own MCP entry (mcptoon serve) with each agent that takes one, so a client that can only see MCP servers still reaches your tools. The MCP entry ships in compact mode: it keeps your upstream tool list out of the model's context and sends it to mcptoon_manifest → inspect → call instead. mcptoon status shows both ledgers.

And it is fully reversible. The install registers the gateway, and by default quickstart also takes over — it routes your existing servers through the gateway and removes their direct entries (without that step your agent sees the same tools twice, once direct and once through the gateway, which costs more, not less). It is a listed, confirmed step, and it is undoable: mcptoon restore drops the gateway entry and puts your servers back exactly where they were. Anything you added to a config afterwards is left untouched. mcptoon off is the lighter switch — it removes only the gateway entry and leaves your servers where they are. Preview either with --dry, and preview the complete removal plan with mcptoon uninstall --dry (it prints exactly what it will remove first).

Don't want to install yet? Watch it work instead (needs Node):

uvx mcptoon demo --quick

It boots the official "everything" reference server, calls one tool, and prints the token math on your screen — no API key, none of your servers, nothing written to disk.

---

What it does

Tools: schema on demand

The full schema is compressed to a name index. When you need one, mcptoon inspect fetches its real parameters, then call runs it. You pay for a listing, not for every turn.

Skills: one resident pointer

No more loading the whole catalog. A single pointer line stays resident (39 tokens) and one lookup returns the most relevant skills (791 tokens). Views are links (a junction on Windows, no admin needed), so one edit at the source is live everywhere and there is no second copy to drift.

Install once, share everywhere

Install mcptoon once and every AI on the machine gets all your tools and skills. Add more later and it is live immediately — no agent restart, no per-agent JSON.

Add tools your way

mcptoon install brave-search --npm @modelcontextprotocol/server-brave-search
mcptoon install my-tool --pip mcp-my-tool
mcptoon install remote-api --url https://example.com/mcp
mcptoon add my-server --stdio npx -y @any/mcp-package
mcptoon install --list                       # see what's installed
mcptoon install --remove brave-search        # uninstall one

One command per server, from npm / pip / HTTP. Or let mcptoon scan what you already have: mcptoon discover.

A remote server that needs a token reads it from the environment, so no credential is ever written to disk:

mcptoon install remote-api --url https://example.com/mcp \
  --header 'Authorization: Bearer ${BAIZHI_TOKEN}'   # BAIZHI_TOKEN set in your environment

${NAME} is resolved at request time, so the config, the generated handler and every log keep the template — rotate the variable and the next call uses the new value, with no reinstall. A missing or empty variable fails loudly, naming it, never as an empty header.

---

Where tools come from — search across 17,000+ MCP servers with one command

On a new machine the first question isn't "how do I save tokens", it's "which tools do I even want". The old answer is to hunt GitHub for mcpServers snippets and hand-copy them into JSON.

mcptoon ships no tools and bundles no catalog. It queries the upstream registries, so you search for exactly what you need:

mcptoon install --search github     # search, list only — nothing installed
mcptoon install --search postgres
mcptoon install github              # search and install

Results carry a ✓ (registry-verified), a type tag (npm / pypi / hosted / remote) and a call count. Data comes from two upstreams, queried live and never stored:

Source	What it is	Scale
Smithery	the largest MCP registry	17,000+ entries
Official MCP Registry	the official meta-registry	installable npm / pypi packages

Why nothing is bundled: a built-in list would need a release to update and would pull someone else's source into your supply chain. mcptoon stores only a pointer — the search writes one line into your own ~/.mcptoon/config.json; third-party source never lands inside mcptoon.

Then distribute to every agent:

mcptoon sync          # push the new tools to every detected agent
mcptoon manifest      # see every tool (name index, the cheapest view)

How to read a result: the index mixes official @modelcontextprotocol/* servers with packages individuals publish. A ✓ means the registry verified the entry — your cue to read the source before you hand it credentials.

The skills half: skills search <query> queries the open skills index (skills.sh) — find a skill by what it does, then install it with skills add <git-url>. mcptoon installs the repos you point it at — the catalog is the open ecosystem itself.

Starter packs: if you'd rather not pick tool-by-tool, four built-in packs — essentials, web-research, code-review, docs — each bundle a few tools plus a ready-made prompt. mcptoon install --packs lists them; mcptoon install --pack essentials installs one. The two research packs need no API key.

---

The three bills, and why you must not mix them

mcptoon saves tokens in three separate places. Comparing the numbers across them is meaningless.

The figures below come from catalogs of three different sizes — a 255-tool synthetic sample (the fixed headline benchmark), a 1,109-tool machine, and whatever your own machine has. Do not compare a percentage from one against a token count from another; each table states which catalog it measures.

There are two ways to read "how much does this save?", and they answer different questions. The gateway figure — full schemas versus what the agent actually loads under the default compact exposure — is what installing mcptoon buys, and it is the honest headline (it scales with catalog size: the more tools you have, the larger it gets). The slim-schema figure (same tools, terser descriptions) is the smaller, secondary claim (88.5%), and it is what manifest --slim buys. mcptoon status prints both, side by side, from one measurement, so the two can never drift apart.

Bill 1 · Tool discovery (manifest): 99.2% smaller by default

mcptoon manifest with no flags is this tier. Want more? --slim (names plus param types, 8,282 tokens, −88.5%) or --full (the complete schema).

Bill 2 · Call results (call): optional, --toon saves ~6%

This bill comes due after a tool returns. mcptoon call prints JSON by default and saves nothing by default. Add --toon to shrink the result.

Bill 3 · Skill catalog (skills): 1,572,330 → 39 resident + 791 per lookup

mcptoon skills manifest                      # 39 tokens, resident
mcptoon skills resolve "make a PDF" --k 5    # 791 tokens, the 5 most relevant

One table, all three, on the machine this README was written on:

Path	What the agent loads	Tokens	vs native
Tool schemas (212)	every full schema	640,787	—
	manifest (name index)	914	99.85%
	manifest --slim	3,056	99.52%
Skill files (480)	every SKILL.md, full text	1,572,330	—
	skills manifest (pointer)	39	99.99%
	skills resolve --k 5	791	99.94%

The fixed headline benchmark — a synthetic sample of 255 tools across 50 servers, tiktoken cl100k_base. It is not your catalog; run mcptoon status to see your own numbers:

Format	Tokens	Savings
JSON	71,929	—
TOON	47,438	34%
SLIM	8,282	88.5%
Compact	581	99.2%

Measure your own catalog with mcptoon bench (it reports your tools, not this fixed sample). The exact three-format table above is reproducible too — no clone needed:

mcptoon manifest                 # populate the schema cache
python -m mcptoon.bench_tokens   # the same JSON / --slim / --compact counts, your tools

Method and caliber: docs/tiktoken-benchmarks.md.

---

Install

pip install mcptoon

Linux (Debian/Ubuntu 23.04+, and any distro that follows PEP 668), and Homebrew Python on macOS. A plain pip install into the system Python is refused there with error: externally-managed-environment. That is the distro protecting itself, not a problem with mcptoon. Install it the clean way instead:

pipx install mcptoon     # isolates the CLI; recommended
# or, into a virtualenv you control:
python3 -m venv ~/.mcptoon-venv && ~/.mcptoon-venv/bin/pip install mcptoon

pip install --break-system-packages mcptoon also works, but it writes into the system Python — prefer pipx or a venv. On Windows, pip install mcptoon just works.

# Run without installing (needs Node)
uvx mcptoon demo --quick

# Isolated CLI install (avoids the PEP 668 error on Linux / Homebrew Python)
pipx install mcptoon

# From source (for development)
git clone https://github.com/activeing123/mcptoon.git
cd mcptoon
pip install -e . --no-build-isolation

# Claude Code plugin
/plugin marketplace add activeing123/mcptoon

Nix

Packaged by numtide/llm-agents.nix — a bot follows every PyPI release, so the flake is never a version behind by hand:

# Run straight from the flake, no install step
nix run github:numtide/llm-agents.nix#mcptoon -- --help

The plugin and the skill are both surfaced through sudosubin/agents.nix as pkgs.agent-plugins.github.activeing123.mcptoon.<plugin-name> and pkgs.agent-skills.github.activeing123.mcptoon.<skill-name>.

---

Cross-Agent Support: Works with Cursor, Claude Code, Windsurf & 103+ Clients

mcptoon reaches an agent one of two ways, and every client below falls into one of them. You don't pick — quickstart registers both, and each host takes whichever it can:

• CLI leg — the agent runs mcptoon itself. Anything with a shell (a CLI agent, or a coding IDE with a terminal) needs zero config: it runs mcptoon call, mcptoon search, mcptoon skills resolve. Nothing is written into it at all.
• serve leg — the client can't run a shell. A chat app or GUI mounts MCP instead, so it gets one entry: mcptoon serve as a single MCP server. One line, one place.

The market, covered. 103 clients, taken from awesome-mcp-clients plus vendor docs for the coding agents that postdate it; developer libraries (mcp-agent, mcp-client-go) are excluded because a user does not run them. Evidence is per client — we name what we verified, not what we assumed.

CLI leg — 42 clients, zero config (they run mcptoon themselves):

AdaL · Aider · Amazon Q Developer · auggie · Autohand Code CLI · Claude Code · Claude Code Open · ClaudeMind · Cline · Codex · ContextKit · Continue · Copilot CLI · Copilot-MCP · Crush · Cursor · Dexto · Dolphin-MCP · Enola · Gemini CLI · Goose · JDBCX · Junie · KiloCode · Kiro · McPico · MCPOmni Connect · mistral-vibe · Nerve · Octomind · opencode · OpenHands · PraisonAI · Qwen Code · Roo Code · Slack MCP Client · SwarmClaw · Trae · VS Code GitHub Copilot · Warp · Windsurf · Zed

serve leg — 61 clients, one mcptoon serve entry (no shell, so they mount MCP):

5ire · Agent Bridge · Agent-cli · AgentOne · AIaW · Ano · AnythingLLM · Argo-LocalAI · askit-mcp · AstrBot · BoltAI · BrowseWiz · Canvas MCP Client · CarrotAI · Chainlit · ChatMCP · Cherry Studio · Claude Desktop · console-chat-gpt · DeepChat · DocsGPT · eechat · Enconvo · Fastchat MCP · FLUJO · Glue · HyperChat · kibitz · Klavis AI · LangBot · LibreChat · LobeHub · Lutra · MCP Chatbot · MCP CLI client · MCP Playground · MCP Simple Slackbot · MCP SuperAssistant · MCPCLIHost · MCPHost · Memex · MindPal · NextChat · OpenClaw · oterm · Qordinate · Runbear · SeekChat · Simple AI · Superinterface · Tambo · Taskade · Tester MCP Client · Tiles Notebook · Tome · Vercade · WhatsMCP · Witsy · y-cli · Yume · Zin-MCP-Client

Evidence status — sync --self writes a hookup line into the 12 hosts we have verified against their own docs; every other host above is reached by the CLI or by mcptoon serve without a host-specific file, so there is nothing to verify per host.

What mcptoon writes, host by host

mcptoon is a CLI tool — a manager, not a resident proxy or service, and not a client library. Your agent never talks to your upstream MCP servers directly: it either runs mcptoon commands, or reaches them through mcptoon's own MCP entry (mcptoon serve). For the hosts that take a file, this is exactly what lands where:

Agent	How it hooks up
Claude Desktop	mcptoon sync --self adds one mcptoon entry to claude_desktop_config.json
Claude Code	mcptoon sync --self writes its config and a pointer into ~/.claude/CLAUDE.md
Codex	mcptoon sync --self writes a pointer into ~/.codex/AGENTS.md
Gemini CLI	mcptoon sync --self writes a pointer into ~/.gemini/GEMINI.md
Qwen Code	mcptoon sync --self writes a pointer into ~/.qwen/QWEN.md
Zed	mcptoon sync --self writes a pointer into Zed's AGENTS.md
Crush	mcptoon sync --self writes a pointer into ~/.config/crush/CRUSH.md
opencode	mcptoon sync --self writes a pointer into ~/.config/opencode/AGENTS.md
DSH	mcptoon sync --self writes a pointer into $DSH_HOME/AGENTS.md
Cursor	mcptoon sync --self adds it to Cursor's MCP config; or put it in AGENTS.md
Windsurf	mcptoon sync --self writes mcp_config.json
Cline	mcptoon sync --self writes Cline's MCP config
VS Code Copilot	mcptoon sync --self writes VS Code's MCP config
Any agent that can run a shell	call mcptoon directly — zero config

# Agent needs GitHub access mid-task? It just runs:
mcptoon add github --url https://api.githubcopilot.com/mcp/
# Done. No JSON editing. No restart. No lost context.

mcptoon serve is the other direction: run all your configured servers behind one MCP endpoint, with connection pooling and per-agent keys, for clients that insist on a proxy. You don't have to choose between the two — the CLI stays the primary way in, and the bridge is wired alongside it wherever the host can take one.

---

Why a CLI, not a proxy

MCP's premise is that every capability is a server your agent must be configured to reach — which is why one new tool means editing per-agent JSON in a different format for each, restarting everything, and re-paying the full schema cost in every agent.

A command line is the one interface every agent already has. And the form factor is measurably cheaper on its own, before mcptoon does anything:

• Firecrawl: the same task cost 1,365 tokens via CLI vs 44,026 via MCP — 32×
• Scalekit: CLI 10–32× cheaper, 100% reliable vs MCP's 72%

The proxy form exists too — mcptoon serve puts all configured servers behind one MCP endpoint — and quickstart wires it alongside the CLI, so you never have to choose. This section is about the shape mcptoon is built around, not a switch you have to flip.

---

Which mode is cheapest?

There are three ways mcptoon can hand tools to an agent, and they cost very differently. Only one is the cheapest, and it is not the state a fresh install starts in. (The token figures below are from the 255-tool sample; your own catalog differs — mcptoon mode prints your numbers.)

Mode	What the agent loads	Fixed cost every turn	When to use
CLI (cheapest)	nothing until it runs a command — then a name index (581 tokens for 255 tools) plus the one schema it needs	0	any agent that can run a shell
serve	mcptoon's own gateway tools instead of every upstream schema (the gateway figure — scales with catalog size)	small, fixed	a client that can only see MCP servers
direct	every full schema of every tool (71,929 tokens on the 255-tool sample)	largest	never, once mcptoon is installed

CLI is cheapest because it is idle at zero. It costs nothing on a turn that uses no tool, and a few hundred tokens only on the turn it does. serve is a close second — a small fixed bill every turn. direct is what you pay when mcptoon is installed but not wired into the agent, and it is where a fresh install sits, which is why mcptoon can feel invisible until you run mcptoon quickstart.

The "99%" in this README is the definition-side saving — from not loading every schema. CLI and serve both get it; direct does not. Result compression is a separate, much smaller bill (Bill 2 above) and is never the reason to install.

Find out which mode you are in — and what each costs on your catalog — with mcptoon mode; print a one-line badge with mcptoon statusline.

---

All commands

mcptoon quickstart              # one-shot start (discover + configure + register the gateway)
mcptoon discover                # scan this machine for MCP servers (--write to keep, --health to probe)
mcptoon import                  # import servers from Claude Desktop / Cursor / Cline / Windsurf
mcptoon init                    # create a sample config (--auto to discover and fill it)
mcptoon list                    # show configured servers
mcptoon manifest                # all tool names (compact by default; 255 tools = 581 tokens)
mcptoon manifest --sort alpha|usage|recent       # order the list (usage = your most-called first)
mcptoon manifest --top 3 --verbose              # cap to N tools per server; --verbose adds descriptions
mcptoon inspect <server> <tool> # inspect one tool's schema
mcptoon search <query>          # search tools across servers
mcptoon select "<task>"         # top 3 tools for a task (past ~40 tools, models pick wrong)
mcptoon select "<task>" --top 5 # ...or how many you want
mcptoon call <server> <tool> '{"args":"here"}'   # call a tool
mcptoon call <server> <tool> ... --transport sse|streamable  # HTTP transport preference (default auto)
mcptoon exec python "print(len(open('big.log').readlines()))"  # run code; only stdout enters context
mcptoon exec python --file analyze.py            # same, from a script file
mcptoon exec --langs                             # what this machine can actually run
mcptoon openapi list <spec>                      # any OpenAPI/Swagger REST API as commands
mcptoon openapi call <spec> <cmd> pet-id=2       # call one operation (params: name=value)
mcptoon openapi call <spec> <cmd> --base-url U   # override the server (prod vs staging)
mcptoon openapi call <spec> <cmd> --cache-ttl 0 --cache-key v2  # re-fetch the spec; keep versions apart
mcptoon graphql list <endpoint>                  # any GraphQL endpoint as commands
mcptoon graphql call <endpoint> <cmd> --fields "name id"  # one query/mutation
mcptoon auth login <name> --auth-url U --token-url U --client-id ID  # OAuth (PKCE)
mcptoon auth creds <name> --token-url U --client-id ID  # OAuth client credentials
mcptoon auth login <name> ... --register REG_URL --client-name mine  # DCR (RFC 7591) — no client-id needed
mcptoon openapi call <spec> <cmd> --auth oauth:<name>   # use a stored token
mcptoon resources list [server]                  # list a server's MCP resources
mcptoon resources read <server> <uri>            # read one resource by URI
mcptoon prompts list [server]                    # list a server's prompt templates
mcptoon prompts get <server> <name> a=1          # render a prompt with arguments
mcptoon complete <server> <ref>:<arg>=<prefix>   # ask the server to finish a value
mcptoon bake create <name> --openapi <spec>      # save a connection under a name
mcptoon bake create <name> --openapi <spec> --auth-header 'K: env:VAR'  # secret by reference only (env:/file:)
mcptoon bake run <name> <action> ...             # reuse a saved connection
mcptoon bake install <name> --bin ~/.local/bin   # write a launcher that only carries the bake name
mcptoon add <name> --stdio|--http <cmd|url>     # add any MCP server
mcptoon remove <name>           # remove a server
mcptoon install <name> --npm|--pip|--url <pkg>  # install + auto-generate handler
mcptoon install --search <kw>   # search the live registries (nothing installed)
mcptoon update                  # refresh each server's cached tool surface; report what moved
mcptoon upgrade                 # update mcptoon itself to the latest PyPI release
mcptoon plugin install <dir>    # install an Agent Plugins 1.0.0 plugin
mcptoon sync                    # sync native config to every detected agent
mcptoon health                  # health-check every MCP server
mcptoon serve                   # run as an MCP server (stdio/HTTP)
mcptoon skills list             # list the skill catalog (--usage adds hit counts)
mcptoon skills sync <src>       # distribute a skill catalog to every agent's folder
mcptoon skills resolve "<task>" # BM25 shortlist of skills (offline, no LLM)
mcptoon docs index <dir>        # index a Markdown tree so agents stop reading it whole
mcptoon docs resolve "<query>"  # best files for a query — returns paths (offline)
mcptoon docs list               # every indexed document, by slug
mcptoon docs doctor             # check the docs index against the disk
mcptoon kb index <path>         # index documents so you can search INSIDE them
mcptoon kb fetch <url>          # fetch a URL and index it (24h TTL cache)
mcptoon kb search "<query>"     # ranked passages, not whole files (porter + trigram, RRF)
mcptoon kb list                 # indexed sources with size and age
mcptoon kb stats                # chunks, DB size, trigram support
mcptoon session                 # what happened this session (catch up after a compaction)
mcptoon bench                   # prove the savings on this machine (tools + skills, one table)
mcptoon demo                    # one command, live demo on your machine
mcptoon demo-server             # the same proof with zero downloads (11 stdlib tools)
mcptoon doctor                  # self-check: Python, config, connectivity
mcptoon status                  # one screen: what's configured, gateway wired, tokens saved
mcptoon stats                   # token-savings dashboard (vs raw JSON)
mcptoon report                  # the whole savings account: tools + skills + cumulative
mcptoon savings                 # milestones you've crossed (1B? ~12,000 novels?)
mcptoon credit                  # one screen: your mode, what it really saves, one action
mcptoon mode                    # which delivery mode you're in (cli/serve/direct) and what each costs
mcptoon statusline              # one-line savings badge for a status bar or turn header
mcptoon usage                   # local call statistics
mcptoon activity                # who used mcptoon, when, on what (last 20 calls)
mcptoon footer-facts            # one line of savings for a chat footer (never blocks)
mcptoon retrieve <handle>       # get back the original behind any --smart handle
mcptoon config                  # show gateway settings (footer, welcome, lang)
mcptoon toggle <server> <tool>  # enable/disable a single tool (--list to show all)
mcptoon policy                  # per-tool compression policy (raw / toon / slim)
mcptoon completion ps           # shell completion (bash/zsh/fish/powershell)
mcptoon off                     # remove the gateway entry from your agents (reversible)
mcptoon restore                 # drop the gateway and put your servers back
mcptoon uninstall               # full cleanup — prints the plan first (--dry to preview)

Full reference in DEVELOPERS.md.

Format family: four tiers, compact by default

All optional; the default is already the leanest tier.

Tier	Output	vs native schema	Origin
compact (default)	names only search_web	99.2% smaller	common design
slim	name + param types search_web|query:s*	88.5% smaller	mcptoon original
full	full schema with params	baseline	native MCP
toon (results)	reversible structured encoding	5.7% on a mixed sample (1.8-48.6% by shape)	open TOON standard

Why compact by default? Choosing which tool to use only needs names (581 tokens for 255 tools); parameter detail matters at call time and is fetched on demand. Defaulting to full schemas would hand the 99.2% right back.

The rule for agents: use manifest to choose, inspect before you call. Measured on 41 live tools: an agent guessing arguments from names alone lands ~10% valid calls, while one that runs inspect once for the 2–3 tools a turn actually uses hits 100% — identical to injecting every schema, at a fraction of the cost.

---

Trust and safety

It's just a 565KB native CLI — delete it anytime; keep it, and you never have to configure tools or skills for any agent again. mcptoon touches your agent configs, so it is built to be transparent — and easy to walk away from.

Three guards run on every tool result before your agent sees it:

Guard (on by default)	What it does
Destructive-action block	a dangerous call is refused unless you pass --destructive
Prompt-injection guard	results are scanned for injection patterns like "ignore previous instructions" and blocked
Credential-leak detection	a result carrying an API key or token is blocked before it enters context

• Reversible. mcptoon restore undoes a takeover (drops the gateway and returns your servers); mcptoon off removes only the gateway entry; mcptoon uninstall --dry prints the full removal plan first. Your servers are never deleted unless you ask.
• No telemetry. No analytics, no crash reports, nothing phoned home.
• Local-first. Your tools, skills and files stay on your machine. The only thing that leaves is install --search, which asks the registries for a catalog listing — it never sends your data.
• No stored credentials. API keys pass straight from your config or environment.
• No dependencies. Pure Python standard library — nothing in the supply chain to audit. CI enforces it with scripts/check_zero_deps.py.
• No daemon. Pure CLI — no resident process, no listening port.
• Formats don't break compatibility. The wire protocol is always standard JSON-RPC; compact/slim/toon only affect mcptoon's output to the agent. If --toon decoding ever fails it falls back to JSON, and one --full restores the native schema. No lock-in.

Scope, in one line: mcptoon is an index and a config manager — it points you to each tool's own source, which you can review on its own terms.

---

Credits and references

• TOON standard — v4.1 (MIT), vendored from python-toon and credited in NOTICE
• ToonDeck — a GUI console for mcptoon (pre-alpha): same engine, point and click instead of typing commands

Who builds this: mcptoon is an independent third-party project maintained by @activeing123. It is not affiliated with Anthropic.

---

Contributing

git clone https://github.com/activeing123/mcptoon.git
cd mcptoon
pip install -e . --no-build-isolation
pip install pytest pytest-cov
python -m pytest tests/ -v   # 3072 passed, 2 skipped

Three hard rules: zero dependencies (CI-enforced), new behavior ships with tests, Windows is a first-class target. New here? Start with CONTRIBUTING.md and DEVELOPERS.md.

The codebase: 41,568 lines of Python across 57 modules, zero third-party dependencies.

---

Support

Hitting an error? Troubleshooting & FAQ covers the common ones (Server 'X' not configured, the skills sync mis-delete gate, unknown command/option exit codes, why a saving reads 99% not 100%, and a stale skills count).

mcptoon is a one-person side project and stays free for individuals. If it cut your context bill:

• Sponsor it on GitHub — one-off or monthly.
• Star the repo — that's how other builders find small tools.

Team features are not built yet. One shared server list synced to every teammate's machine; a log of what got hydrated when. No pricing and no waitlist page — mail activeing123@gmail.com and it moves up the list.

---

License

Apache 2.0. See LICENSE and NOTICE.

---

mcptoon is an independent third-party MCP client, not affiliated with Anthropic.

If mcptoon cut your context bill, star it — that's how other builders find small tools.