mcpField
F
Facet

Facet

Remote
facet.halfspacelabs.comAI & Agents0Updated 4d ago

About Facet

Facet is an agent plugin for building and checking specialized models for narrow tasks, then serving them through an OpenAI-compatible API. It includes a remote MCP server and a Skill for agents that support plugins.

Key features

  1. 01Builds specialized models for narrow tasks
  2. 02Checks changes against plain-language Expectations
  3. 03Serves models through an OpenAI-compatible API
  4. 04Includes the `use-facet` Skill

Use cases

  1. 01Create a model for a specific task
  2. 02Review model changes against Expectations
  3. 03Call a specialized model from an agent

MCP support

Provides a remote MCP server at `https://facet.halfspacelabs.com/mcp`; MCP clients authenticate with OAuth.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://facet.halfspacelabs.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Facet plugins

Facet builds a specialized model for one narrow task, checks every change against plain-language Expectations, and serves it through an OpenAI-compatible API. This repository is its agent plugin: the remote MCP server and the use-facet Skill, for every agent that takes plugins.

  • 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

Docs: facet.halfspacelabs.com/docs/agents

This repository is published from plugin/ in Facet's own repository; change it there.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.