PluginBench
MCP Server
Active
MIT

OpenRouter MCP Server

io.github.tsilva/mcp-openrouter

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the OpenRouter MCP server?

MCP server providing access to 300+ AI models via OpenRouter

How to install OpenRouter

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • OPENROUTER_API_KEY
    required
    secret

    OpenRouter API key used to authenticate tool requests.

  • DEFAULT_TEXT_MODEL

    Default model slug for chat tool calls when no model is provided.

  • DEFAULT_IMAGE_MODEL

    Default model slug for image generation tool calls.

  • DEFAULT_CODE_MODEL

    Default model slug for code-oriented tasks.

  • DEFAULT_VISION_MODEL

    Default model slug for vision-capable tool calls.

  • DEFAULT_EMBEDDING_MODEL

    Default model slug for embedding tool calls when no model is provided.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "mcp-openrouter": {
      "command": "uvx",
      "args": [
        "mcp-openrouter"
      ],
      "env": {
        "OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>",
        "DEFAULT_TEXT_MODEL": "<YOUR_DEFAULT_TEXT_MODEL>",
        "DEFAULT_IMAGE_MODEL": "<YOUR_DEFAULT_IMAGE_MODEL>",
        "DEFAULT_CODE_MODEL": "<YOUR_DEFAULT_CODE_MODEL>",
        "DEFAULT_VISION_MODEL": "<YOUR_DEFAULT_VISION_MODEL>",
        "DEFAULT_EMBEDDING_MODEL": "<YOUR_DEFAULT_EMBEDDING_MODEL>"
      }
    }
  }
}

Related MCP servers

Intelligent memory layer for AI agents with semantic search, knowledge graphs, and automatic consolidation.

46
TypeScript
MIT
View repository →

Exact symbolic math for LLMs: integrals, equations, matrices, and claim verification via Giac/Xcas

1
TypeScript
GPL-3.0
View repository →

Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation

View repository →

MCP server for the Txtcel Solana protocol: agents post and read undeletable on-chain messages.

1
TypeScript
MIT
View repository →

AI-powered Amazon Ads API management through Model Context Protocol with comprehensive campaign, reporting, and optimization tools.

56
Python
MIT
View repository →
RARail logo

Rail

Active

Budgets, propose-then-approve, and receipts for agents that buy for a human. Dry-run by default.

0
TypeScript
MIT
View repository →