Forge MCP server

@voxell/forge-mcp

An MCP server for Forge — Voxell's hosted text-embedding API. It exposes Forge to any MCP client (Claude, Cursor, Cline, Windsurf, VS Code, …) as two tools:

• embed — turn text into vectors
• listmodels** — list available models and their dimensions

You bring a Forge API key. The server is stateless, and Voxell does not store the text you send or the vectors it returns — only usage metadata (token counts) is recorded, for billing. It does embeddings only — no storage, no search, no RAG. Those are different products.

Quick install

One-click install in your editor (then replace your-key-here with a real key from dash.voxell.ai):

Claude Code — one command:

claude mcp add forge -e FORGE_API_KEY=your-key-here -- npx -y @voxell/forge-mcp

Any other client (Claude Desktop, Cline, Windsurf, Zed, …) uses the standard mcpServers block — see Use it below.

Why Forge

ultra (4096d, highest quality). Pick your point on the quality and cost curve.

• Quality you can dial. Three tiers: turbo (1024d, fast, the default), pro (2560d) and

(English v2), with a 75.98 mean task score across 41 tasks: the top usable English embedding model. See the model card.

• Benchmark-leading. Voxell's Ingot-8B-R3 ranks #1 for English on the public MTEB leaderboard

start** (turbo is free forever, no card: dash.voxell.ai; more at voxell.ai/forge).

• Matryoshka (MRL). Set dim to truncate (re-normalized) for ~4× smaller, cheaper vectors.
• Low latency (Go + CUDA engine), zero-trust (per-key auth; mTLS available), and **free to

What you can do with it

with input_type: "query", then rank by cosine similarity.

• Add semantic search — embed your documents with input_type: "document" and each query

ground an LLM.

• Build RAG — embed a knowledge base, store the vectors, and retrieve the closest chunks to

for smaller, cheaper vectors.

• Find similar or duplicate text — embed two texts and compare their vectors.
• Cluster or classify — embed a batch, then cluster or train a classifier on the vectors.
• Shrink vector storage — set dim to truncate (Matryoshka) and trade a little accuracy

batch, or a file via the embed tool — no separate script.

• Straight from your editor — ask your AI agent (Cursor, Claude, …) to embed a snippet, a

Requirements

tokens, no credit card.

• Node.js ≥ 18 (tested on 20)
• A Forge API key — create one at https://dash.voxell.ai. New accounts start with 10M free

Use it

Most MCP clients run it on demand with npx. Add this to your client's MCP config:

{
  "mcpServers": {
    "forge": {
      "command": "npx",
      "args": ["-y", "@voxell/forge-mcp"],
      "env": { "FORGE_API_KEY": "your-key-here" }
    }
  }
}

(Cursor, Claude Desktop, Cline, Windsurf, and VS Code all use this mcpServers shape.)

Tools

embed

Shortened. The full README is on GitHub.