ToolPiper MCP server
Commit Nov 6, 2026Turns a Mac into a local AI platform by exposing over 450 on-device tools for speech, vision, browser automation, and system control to MCP clients.
Also known as ModelPiper/toolpiper
- Stars
- 3
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.0.10-beta
- Last commit
- Nov 6, 2026
- License
- MIT
What is ToolPiper MCP?
ToolPiper turns a Mac into a local AI platform by exposing over 450 on-device tools for speech, vision, browser automation, and system control to MCP clients.
Summary generated from the project's README
About ToolPiper MCP server
ToolPiper transforms a Mac into a local AI platform by exposing over 450 on-device tools to MCP clients. It runs natively on macOS using Apple Silicon to provide capabilities for speech, vision, browser automation, and system control without requiring cloud services or API keys. The server uses llama.cpp on Metal, Apple Intelligence, and the Neural Engine to handle inference and speech tasks locally.
Developers can connect various clients like Claude Code, Cursor, or Codex via Streamable HTTP using a local loopback connection at localhost:9998. The setup is designed for privacy, ensuring prompts and files remain on the machine. Users can install the application via Homebrew or a direct disk image download. While the core local model runner is free and has no usage caps, certain parts of the tool catalog are available through paid plans.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work
- Source repository linked and reachablemodelpiper/toolpiper is public and reachablegithub.com/modelpiper/toolpiper ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-06github.com/modelpiper/toolpiper ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubToolPiper MCP Server for macOS
450+ Model Context Protocol tools, all running on-device. ToolPiper is a native macOS app that turns your Mac into a local AI platform: bundled inference (llama.cpp on Metal, Apple Intelligence, speech on the Neural Engine), an OpenAI-compatible API at localhost:9998, and a built-in MCP server that exposes the whole machine to any MCP client: Claude Code, Cursor, Codex, or your own scripts.
No cloud required for local models. No Docker. No Python. No API keys. Your prompts, files and outputs stay on your Mac, and you can check what ToolPiper connects to yourself: lsof -i -P | grep ToolPiper while it runs.
- Website: https://modelpiper.com/toolpiper
- Download: https://modelpiper.com/download (free; the full local model runner has no caps and needs no account)
- Docs: https://modelpiper.com/docs/toolpiper
- Tool catalog: https://modelpiper.com/mcp-tools
- Community: https://github.com/ModelPiper/modelpiper-community
This repository is the official home for ToolPiper's MCP server manifest (
server.json), the Claude Code plugin (plugins/toolpiper), and the setup guides. The ToolPiper app itself is not open source, but its privacy claims do not ask for trust: every byte of network traffic is observable on your own machine. Open-source siblings live in this org: PiperSR (ANE super-resolution model), FluidAudio, mlx-audio-swift.
Quick start
Install ToolPiper, launch it once, then connect any MCP client over Streamable HTTP. Loopback connections need no auth: no token, no OAuth step.
Download the disk image from modelpiper.com/download, or install with Homebrew:
brew tap modelpiper/tap
brew trust modelpiper/tap
brew install --cask toolpiper
The trust line is required once: Homebrew 6 refuses casks from taps outside its own until you trust them.
Claude Code, as a plugin (one server entry, nothing to configure by hand):
claude plugin marketplace add ModelPiper/toolpiper
claude plugin install toolpiper@modelpiper
Claude Code, as a manual server:
claude mcp add -s user --transport http toolpiper http://127.0.0.1:9998/mcp
Codex, as a plugin:
codex plugin marketplace add ModelPiper/toolpiper
codex plugin add toolpiper@modelpiper
Or as a manual server: codex mcp add toolpiper --url http://127.0.0.1:9998/mcp. Codex signs in to ToolPiper once; approve ToolPiper's consent page when it appears.
Any other MCP client, in its server configuration:
{
"mcpServers": {
"toolpiper": { "type": "http", "url": "http://127.0.0.1:9998/mcp" }
}
}
Claude Desktop, as a one-click extension: download toolpiper-1.0.1.mcpb from Releases and double-click it; Claude Desktop shows its install sheet. The JSON block above does not apply to Claude Desktop, whose config file runs local stdio servers only. Source, build script and privacy statement: desktop-extension/. It is a small Node.js forwarder that relays Claude Desktop's stdio to the same loopback server, and it serves the directory profile: the catalog minus every tool that uses an AI model to generate images, video or audio.
Installing with an AI agent? Point it at llms-install.md.
What's in the catalog
450+ tools, 5 resources, and 5 workflow prompts. Names follow <category>_<action> (vision_ocr, system_window_snap, browser_assert). The live catalog, with per-tool documentation, is at modelpiper.com/mcp-tools.
| Category | Examples | What it covers |
|---|---|---|
| Core AI | chat, audio_transcribe, audio_speak, text_embed |
Local LLM inference, speech-to-text and text-to-speech on the Neural Engine, embeddings |
| Apple frameworks + RAG | vision_ocr, image_analyze, text_analyze, rag_query |
Apple Vision OCR, image analysis, natural-language analysis, hybrid HNSW + BM25 document search |
| Browser automation | browser_snapshot, browser_action, browser_assert, browser_intercept |
Chrome via CDP: AX-tree snapshots, self-healing selectors, network mocking, Web Vitals, coverage |
| Testing | test_run, test_save, test_export |
Saved browser test sessions, fast replay, Playwright/Cypress export |
| System actions | system_* |
Windows, Spaces, clipboard (with OCR'd history), audio, displays, Finder, Calendar, Reminders, Contacts, notifications, processes, network, Bluetooth, Shortcuts, and more |
| Video creator | video_record, video_render, video_edit_timeline |
Screen-recorded screenplays, non-destructive timeline editing, OTIO/FCP XML/EDL export |
| Outreach | github_compare, queue_add, gsc_analytics |
GitHub, the content queue, Google Search Console |
| Model management | model_search, model_download, model_load |
Search HuggingFace, download GGUF/CoreML, load/unload |
| Routing + integrations | endpoint_set, endpoint_recommend, claude_code_status |
Switch inference endpoints per session, see how Claude Code connects |
Resources: toolpiper://status, toolpiper://models, toolpiper://backends, toolpiper://tests, toolpiper://categories
Prompts: setup-model, audit-page, create-test, voice-over, research-topic
Category and profile filtering
Don't want the whole catalog in context? Pass category or profile as a query parameter on the /mcp URL. Both the tool list and the server instructions trim to match:
# Just LLM inference (core category)
claude mcp add -s user --transport http toolpiper "http://127.0.0.1:9998/mcp?category=core"
# Web dev workflow (automation profile: core + browser + testing)
claude mcp add -s user --transport http toolpiper "http://127.0.0.1:9998/mcp?profile=automation"
Transport
| Transport | Endpoint | Auth |
|---|---|---|
| Streamable HTTP | POST http://127.0.0.1:9998/mcp (plus GET /mcp, the SSE channel for tools/list_changed) |
None for loopback peers, enforced at the kernel socket, so Host/Origin spoofing cannot widen it. LAN and remote peers present Authorization: Bearer. |
Streamable HTTP is the only transport. ToolPiper has no stdio server, and older guides that described one are obsolete.
Privacy
Your prompts, files and outputs stay on your Mac when you use local models. ToolPiper contacts our servers for update checks, a license check when you're signed in and a daily activity count, and it can send optional usage counts. You can turn the last two off in Settings, and none of them include your content. There are no crash uploads, and local use needs no account. Everything else is traffic you ask for: model downloads from HuggingFace, a cloud provider you add, and tools that explicitly target the web. You can watch it yourself:
lsof -i -P | grep ToolPiper
You will see update, license and activity requests to modelpiper.com hosts, optional usage counts to PostHog if you leave them on, plus any downloads or providers you chose, and none of them carry your content. Full policy: modelpiper.com/privacy.
Requirements and pricing
- macOS 26 or later on Apple Silicon
- Free: the full local model runner and every speech feature (transcription, text to speech, dictation). No caps, no account.
- Paid plans add more of the catalog. The current ladder is at modelpiper.com/pricing.
FAQ
Is this the same as "ToolPipe"? No. ToolPiper (this page, modelpiper.com) is the macOS MCP server by ModelPiper. Unrelated projects with similar names exist in some directories.
What does the MIT license in this repo cover? The contents of this repository: the server manifest, the Claude Code plugin, and the setup guides. The ToolPiper app itself is proprietary.
Does it work without an internet connection? Yes. Inference, speech, vision, RAG, and system tools are all on-device. You only need the network to download models.
Can other machines connect? Loopback is zero-config. LAN and remote access go through bearer-token auth.
I already added ToolPiper with claude mcp add. Do I need the plugin? No. Claude Code keeps your manual toolpiper server and skips the plugin's copy while the manual one exists, so nothing doubles up. The plugin is for a fresh setup, or if you remove the manual entry.
ToolPiper MCP questions
Does it work without an internet connection?
Yes, inference, speech, vision, RAG, and system tools all run on-device. Internet is only required for downloading models.
Is this the same as ToolPipe?
No, ToolPiper is the macOS MCP server by ModelPiper, distinct from unrelated projects with similar names.
Can other machines connect to the server?
Loopback connections are zero-config, while LAN and remote access require bearer-token authentication.
Do I need the plugin if I already added it via Claude Code?
No, Claude Code will skip the plugin if a manual server entry already exists.