MCP servers · askloci

Loci: local model tools for AI assistants on Apple silicon Macs

An MCP server that lets AI assistants run tasks on local models on an Apple silicon Mac, with optional file and audio tools.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

The server gives AI assistants access to models running on your Mac for summaries, rewriting, classification, structured output and batch processing. With compatible versions of the Loci app, it also adds file processing, document extraction, folder search and audio transcription. Which tools are available depends on the app version.

It suits people who want assistant tasks handled by models on their own machine, so that model inference stays on the Mac. Setup is documented for Codex, Claude Code, Cursor, Gemini CLI, Antigravity and Hermes Agent, and for other local MCP clients through an MCP bundle or a signed local stdio connector.

Setup starts in the Loci app, where Agent Access is enabled under Settings, Advanced, and the app must stay running while the plugin is used. In your client, you install the plugin or extension and ask the setup tool to help. It checks the connection and helps you pick an installed model or a compatible download, and existing models are shared with the app. App and plugin updates are separate, and each client can run a different plugin version.

Limitations and requirements

Requires an Apple silicon Mac running macOS 26.2 or later, and the Loci direct-download app. Available tools depend on the app version. Claude Code and Gemini CLI require Node.js 22 or later; Hermes Agent must run on the same Mac as Loci. Loci must stay running while the plugin is used. In Gemini CLI, a manually configured server named loci takes precedence over the extension and must be removed to switch. File tools can read paths you authorise, and summaries, extracted values, quotes and search passages can reveal information from those files. Prompts and results shared in an assistant conversation follow that assistant's data policies. The MCP bundle needs no Node.js or Python runtime.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    Loci

    Run local models on your Apple silicon Mac with Loci. Requires macOS 26.2 or later.

    v0.1.7
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 17 Nov 2026
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026