mcp-openrouter
A Python MCP server that lets MCP hosts call OpenRouter models for chat, image generation, embeddings, and model search via FastMCP with .env support and retry handling.
README
<div align="center"> <img src="./logo.png" alt="mcp-openrouter" width="360" />
🚀 One MCP server for OpenRouter models 🚀 </div>
<!-- mcp-name: io.github.tsilva/mcp-openrouter -->
mcp-openrouter is a Python MCP server that lets Codex, Claude Code, opencode, and other MCP hosts call OpenRouter models from local stdio tools.
It exposes chat, image generation, embeddings, model listing, and model search through a small FastMCP server with .env support, retry handling, host-aware installation, and optional default model environment variables.
Install
Install the published server into every detected MCP client:
uvx mcp-openrouter install --yes
Install into selected clients:
uvx mcp-openrouter install --yes --clients codex,claude,opencode
Pass the OpenRouter key directly for non-interactive setup:
uvx mcp-openrouter install --yes --api-key sk-or-v1-...
Run from a local checkout:
git clone https://github.com/tsilva/mcp-openrouter.git
cd mcp-openrouter
uv sync --dev
OPENROUTER_API_KEY=your-key uv run mcp-openrouter
mcp-openrouter with no arguments starts the stdio server. The explicit command is uv run mcp-openrouter serve.
Commands
uvx mcp-openrouter install --yes # install into detected MCP clients
uvx mcp-openrouter install --yes --force # replace an existing openrouter config
uvx mcp-openrouter uninstall --yes # remove from detected MCP clients
uv run mcp-openrouter # run the local stdio server
uv run pytest tests/test_cli.py tests/test_client.py tests/test_config.py tests/test_installer.py tests/test_release_metadata.py tests/test_server.py
OPENROUTER_API_KEY=your-key uv run pytest tests/test_tools.py
uv run ruff check src/
uv run ruff format src/
Tools
| Tool | Purpose |
|---|---|
chat |
Send a prompt or message list to an OpenRouter chat model. |
generate_image |
Generate one image and optionally save it to an absolute local path. |
embed |
Generate embeddings for a string or list of strings. |
list_models |
List models, optionally filtered by vision, image_gen, embedding, tools, or long_context. |
find_models |
Search model names and slugs, returning up to 20 matches. |
Example MCP prompts:
Use openrouter chat with anthropic/claude-sonnet-4 to summarize this file
Use openrouter generate_image with google/gemini-3-pro-image-preview to create a square app icon
Use openrouter embed with mistralai/mistral-embed-2312 to embed "Hello world"
Use openrouter list_models with capability "image_gen"
Use openrouter find_models to search for "claude"
Configuration
OPENROUTER_API_KEY is required for all tool calls. Set it in your shell, pass it during installation, or put it in .env.
Optional defaults make the model parameter optional for matching tools:
OPENROUTER_API_KEY=sk-or-v1-your-key-here
DEFAULT_TEXT_MODEL=google/gemini-3-pro-image-preview
DEFAULT_IMAGE_MODEL=google/gemini-3-pro-image-preview
DEFAULT_CODE_MODEL=anthropic/claude-sonnet-4.5
DEFAULT_VISION_MODEL=google/gemini-3-pro-image-preview
DEFAULT_EMBEDDING_MODEL=mistralai/mistral-embed-2312
The current tools read DEFAULT_TEXT_MODEL, DEFAULT_IMAGE_MODEL, and DEFAULT_EMBEDDING_MODEL. DEFAULT_CODE_MODEL and DEFAULT_VISION_MODEL are available for client conventions. The server loads .env from the current working directory and from the repository root when running from a checkout.
Notes
- Python 3.10+ is required.
- The published runtime command installed into hosts is
uvx mcp-openrouter. - Supported installer targets are Codex, Claude Code, and opencode.
generate_image.output_pathmust be absolute, for example/Users/you/output.png.- Unit tests mock network calls.
tests/test_tools.pyrequires a liveOPENROUTER_API_KEY. - After changing server code, restart the MCP host so it launches a fresh server process.
- Keep
server.json,CHANGELOG.md, and the package version in sync before release. The Makefile release helper ismake release-x.y.z.
Local MCP Development
Register a local checkout when you want an MCP host to run your working tree instead of the published PyPI package.
Claude Code:
claude mcp add openrouter --scope user -- uv run --directory /path/to/mcp-openrouter mcp-openrouter
Codex:
codex mcp add openrouter --env OPENROUTER_API_KEY=your-key -- uv run --directory /path/to/mcp-openrouter mcp-openrouter
opencode:
{
"mcp": {
"openrouter": {
"type": "local",
"command": ["uv", "run", "--directory", "/path/to/mcp-openrouter", "mcp-openrouter"],
"environment": {
"OPENROUTER_API_KEY": "your-key"
},
"enabled": true
}
}
}
Architecture

License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。