Facet MCP server
Commit Nov 15, 2026Builds, evaluates, and serves specialized LLM models for specific tasks via an OpenAI-compatible API.
Also known as halfspacelabs/facet-plugins, facet-plugins
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.5.3
- Last commit
- Nov 15, 2026
- License
- MIT
What is Facet MCP?
Facet is an MCP server. Builds, evaluates, and serves specialized LLM models for specific tasks via an OpenAI-compatible API.
Summary generated from the project's README
About Facet MCP server
Facet provides a remote MCP server that allows developers to build, evaluate, and serve specialized LLM models through an OpenAI-compatible API. The agent automates the process of creating narrow models for specific tasks and runs plain-language evaluations on every modification. This tool is designed for developers using Claude Code, Cursor, Codex, or any MCP client that supports OAuth sign-in via the Facet URL.
Users interact with the server through specific commands like /facet:find to identify potential model replacements, /facet:new to create a model from a specific code call, /facet:wire to swap existing calls with new models, and /facet:status to monitor evaluations. The system prioritizes privacy by ensuring no data leaves the machine without permission. It specifically avoids reading credential files, masks personal details, and prevents LLM answers from being used as training data. The plugin operates without running any code on your local machine.
What you can do with it
- 1Create a specialized task modelGenerate a new model based on a specific function call using real inputs from your local files.
- 2Deploy and swap modelsCompare a new model against your existing examples and replace the original call with the new version.
Written from the project's README. Every use case is checked against a quote from it.
How to install Facet MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Facet MCP in Claude Code
$ claude mcp add --transport http facet-plugins https://facet.halfspacelabs.com/mcpInstall Facet MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"facet-plugins": {
"url": "https://facet.halfspacelabs.com/mcp"
}
}
}Install Facet MCP in VS Code
.vscode/mcp.json
{
"servers": {
"facet-plugins": {
"type": "http",
"url": "https://facet.halfspacelabs.com/mcp"
}
}
}Install Facet MCP in VS Code CLI
$ code --add-mcp '{"name":"facet-plugins","type":"http","url":"https://facet.halfspacelabs.com/mcp"}'Install Facet MCP in Codex
$ codex mcp add facet-plugins --url https://facet.halfspacelabs.com/mcpInstall Facet MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.facet-plugins] url = "https://facet.halfspacelabs.com/mcp"
Install Facet MCP in Gemini CLI
$ gemini mcp add -s user --transport http facet-plugins https://facet.halfspacelabs.com/mcpInstall Facet MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"facet-plugins": {
"url": "https://facet.halfspacelabs.com/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 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 · What to fix for more points
- Source repository linked and reachablehalfspacelabs/facet-plugins is public and reachablegithub.com/halfspacelabs/facet-plugins ↗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 2026-11-12github.com/halfspacelabs/facet-plugins ↗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 handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubFacet plugins
Facet takes a task from one plain-language ask to a live model: its agent builds a model for one narrow task, runs plain-language evals on every change, and serves it through an OpenAI-compatible API. This repository is its agent plugin: the remote MCP server and its Skills, for every agent that takes plugins.
In Claude Code the Skills are commands:
/facet:find: find the LLM calls in your repo a Model could take over. Sends nothing to Facet./facet:new <file:line>: make a Model from one call, with real inputs from your repo./facet:wire <model>: compare a Model on your repo's examples, then swap the call over./facet:status: the Models your repo calls, their evals and any Change in flight.
Nothing leaves your machine until you've seen it and said yes. Rows come only from your repo's tests, fixtures and samples; the agent never opens .env or credential files, drops rows that look like keys, offers to mask personal details, and never sends an LLM's answers as training data. The plugin runs no code on your machine.
- Claude Code:
/plugin marketplace add halfspacelabs/facet-plugins, then/plugin install facet@facet - Cursor: install Facet from the Cursor marketplace
- Codex and ChatGPT: install Facet from the plugin directory
- Any MCP client: add
https://facet.halfspacelabs.com/mcp; it signs you in with OAuth
Facet is invite-only for now: join the waitlist first, then sign in with the email we invite. If sign-in shows a waitlist form, that email isn't invited yet.
Sign in once in Claude Code:
- Restart Claude Code so it loads the plugin.
- Run
/mcp, choose facet, then Authenticate. - Sign in in the browser tab that opens.
Docs: facet.halfspacelabs.com/docs/agents
This repository is published from plugin/ in Facet's own repository; change it there.
Facet MCP questions
How do I add Facet MCP to Claude Code?
Run claude mcp add --transport http facet-plugins https://facet.halfspacelabs.com/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Facet MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Is my data safe when using Facet?
Yes, the agent does not open credential files, masks personal details, and never sends LLM answers as training data.