Facet

io.github.halfspacelabsPublished by GitHub account halfspacelabsv1.5.0Updated Nov 7, 2026

Ask for a model and Facet does the rest: it builds, checks and serves a model for one task.

The publisher's own server: Facet UCP Shopping

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

Facet builds, evaluates and serves a small model for one narrow task from a plain-language request, with repo-aware plugin skills.

What you can do
  • Ask for a model for one task and have it built, checked and served
  • Find LLM calls in a repository that a model could take over
  • Create a model from a specific call using real inputs from the repo
  • Compare a model against the repo's examples and swap the call over
  • Check which models a repo calls, their evals and any change in flight
When to use it
Useful when you want to replace or narrow a general LLM call in your codebase with a purpose-built model, or to track the models a repository already depends on. It suits teams working in Claude Code, Cursor, Codex or another MCP client that want evaluation-driven model changes.
Requirements
A remote MCP endpoint reached over streamable HTTP; sign-in is by OAuth. Access is invite-only: you must join a waitlist and sign in with the invited email. Plugin skills are installed through the Claude Code plugin marketplace, the Cursor marketplace or the Codex/ChatGPT plugin directory.
Before you install
The service is invite-only and account-based, so an invited email is required. Repo content such as tests, fixtures and samples can be sent to Facet, though the README says nothing leaves your machine until you approve it and that credential files are never opened. Wiring a model swaps out existing LLM calls in your code, so review those changes.

Installation

In SourceWeft

  1. Open Facet in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.halfspacelabs%2Ffacet/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "facet": {
      "type": "http",
      "url": "https://facet.halfspacelabs.com/mcp"
    }
  }
}

README

Facet 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:

  1. Restart Claude Code so it loads the plugin.
  2. Run /mcp, choose facet, then Authenticate.
  3. 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.

Source: README.md at commit 7a8aec2

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

4
  1. v1.5.0LatestNov 7, 2026
  2. v1.4.0Nov 3, 2026
  3. v1.0.2Nov 1, 2026
  4. v1.0.0Oct 25, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Facet integrations

Facet UCP Shopping

llc.facetOfficial publisher

Facet UCP Shopping lets an AI assistant search merchant catalogs, get quotes, build carts and complete agent-paid checkouts on Facet-enabled online stores.

Streamable HTTPWeb executable
Finance23 toolsOct 24, 2026

Facet

Published by GitHub account chndr-prksh

Facet checks a web page for responsive design problems and screenshots it across emulated phone, tablet and desktop devices.

STDIODesktop only
Browser AutomationNot validated yetOct 24, 2026