Skip to main content
Glama

unorouter-mcp

MCP server for UnoRouter, an open-source OpenAI-compatible gateway that serves models from every major provider (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, Qwen and more) behind a single API key. Models with a :free suffix cost nothing.

Gives any MCP client (Claude Desktop, Claude Code, Cursor, Windsurf, and friends) three tools:

  • search_models: filter the live catalog, optionally free models only

  • get_pricing: USD per-1M-token list prices from the public pricing endpoint

  • chat: send a prompt to any model and get the reply with token usage

Setup

Create an API key at unorouter.com/token (Discord or GitHub sign-in, no card required).

Claude Desktop / any MCP client

{
  "mcpServers": {
    "unorouter": {
      "command": "npx",
      "args": ["-y", "unorouter-mcp"],
      "env": {
        "UNOROUTER_API_KEY": "sk-your-key"
      }
    }
  }
}

Claude Code

claude mcp add unorouter -e UNOROUTER_API_KEY=sk-your-key -- npx -y unorouter-mcp

Related MCP server: mcp-consultant

Environment

Variable

Required

Default

UNOROUTER_API_KEY

yes

none

UNOROUTER_BASE_URL

no

https://api.unorouter.com

Notes

  • Free models run on shared pools with a light per-model rate limit (about 1 request per minute per model); rotate between free models or use paid ones for throughput.

  • The whole UnoRouter stack is open source: github.com/unorouter.

Development

bun install
bun run build
UNOROUTER_API_KEY=sk-... node dist/index.js

Available Tools

3 tools
chatChat with a UnoRouter modelAInspect

Send a single prompt to any UnoRouter model and return the reply. Use search_models to find model IDs; :free models cost nothing (light per-model rate limit, rotate models if you hit 429).

Inputs: model (required), prompt (required), system, max_tokens, +1 more.

get_pricingGet UnoRouter model pricingAInspect

Look up per-token pricing for UnoRouter models from the public pricing endpoint. Prices are USD list prices per 1M tokens before per-group discounts (the account dashboard shows the exact effective rate). :free models are always 0.

Inputs: limit, query.

search_modelsSearch UnoRouter modelsAInspect

Search the live UnoRouter model catalog (200+ models behind one OpenAI-compatible key). Models ending in :free cost nothing. Returns matching model IDs usable with the chat tool or any OpenAI-compatible client pointed at https://api.unorouter.com/v1.

Inputs: limit, query, free_only.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool targets a distinct concern: model discovery, pricing lookup, and chat completion. There is no overlap or ambiguity between them.

    Naming Consistency4/5

    Two tools follow the verb_noun pattern (search_models, get_pricing), while 'chat' is a bare verb. This is a minor deviation but the set remains readable and predictable.

    Tool Count5/5

    Three tools is appropriately scoped for a model-routing/chat API. Each tool has a clear purpose and none feel redundant or missing.

    Completeness4/5

    The surface covers the essential workflows: discover models, check pricing, and send chats. Minor gaps like streaming or detailed model metadata exist but are not critical for the core use case.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      A
      quality
      D
      maintenance
      An MCP server for discovering and querying over 300 AI models available on OpenRouter. It enables users to list, search, filter, compare, and get detailed information about models with pricing, context limits, and capabilities.
      5
      1
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      MCP server that interfaces with Gemini and OpenAI CLI tools to enable AI model interactions. It provides a bridge to external AI CLIs with predefined model configurations.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server that enables agents to dynamically switch between multiple AI models (OpenAI, Anthropic, Google, etc.) with unified protocol-driven configuration and capability discovery.
      Apache 2.0