Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
MCP server providing access to 300+ AI models via OpenRouter
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
OPENROUTER_API_KEY, DEFAULT_TEXT_MODEL, DEFAULT_IMAGE_MODEL, DEFAULT_CODE_MODEL, DEFAULT_VISION_MODEL, DEFAULT_EMBEDDING_MODEL标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"openrouter": {
"command": "uvx",
"args": [
"mcp-openrouter"
],
"env": {
"OPENROUTER_API_KEY": "your-value",
"DEFAULT_TEXT_MODEL": "your-value",
"DEFAULT_IMAGE_MODEL": "your-value",
"DEFAULT_CODE_MODEL": "your-value",
"DEFAULT_VISION_MODEL": "your-value",
"DEFAULT_EMBEDDING_MODEL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add openrouter --env OPENROUTER_API_KEY=your-value --env DEFAULT_TEXT_MODEL=your-value --env DEFAULT_IMAGE_MODEL=your-value --env DEFAULT_CODE_MODEL=your-value --env DEFAULT_VISION_MODEL=your-value --env DEFAULT_EMBEDDING_MODEL=your-value -- uvx mcp-openrouter运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"openrouter": {
"command": "uvx",
"args": [
"mcp-openrouter"
],
"env": {
"OPENROUTER_API_KEY": "your-value",
"DEFAULT_TEXT_MODEL": "your-value",
"DEFAULT_IMAGE_MODEL": "your-value",
"DEFAULT_CODE_MODEL": "your-value",
"DEFAULT_VISION_MODEL": "your-value",
"DEFAULT_EMBEDDING_MODEL": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"openrouter": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-openrouter"
],
"env": {
"OPENROUTER_API_KEY": "your-value",
"DEFAULT_TEXT_MODEL": "your-value",
"DEFAULT_IMAGE_MODEL": "your-value",
"DEFAULT_CODE_MODEL": "your-value",
"DEFAULT_VISION_MODEL": "your-value",
"DEFAULT_EMBEDDING_MODEL": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
DEFAULT_TEXT_MODEL envDEFAULT_IMAGE_MODEL envDEFAULT_CODE_MODEL envDEFAULT_VISION_MODEL envDEFAULT_EMBEDDING_MODEL env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 tsilva 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:OPENROUTER_API_KEY
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.1.8)于6个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
🚀 One MCP server for OpenRouter models 🚀
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 retry handling, host-aware installation, and optional default model environment variables.
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
Run from a local checkout:
git clone https://github.com/tsilva/mcp-openrouter.git
cd mcp-openrouter uv sync --dev uv run mcp-openrouter
mcp-openrouter with no arguments starts the stdio server. The explicit command is uv run mcp-openrouter serve.
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 uv run pytest tests/test_tools.py uv run ruff check src/ uv run ruff format src/
| 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"
AGENTBRIDGE_API_KEY is optional when a gateway requires authentication. The local gateway needs no application key. For an authenticated gateway, inject the token from Infisical using infisical run --projectId PROJECT_ID --env=prod -- uv run mcp-openrouter. Python reads it from the process environment.
Optional defaults make the model parameter optional for matching tools:
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. Non-secret defaults may remain in .env; the API key must not.
uvx mcp-openrouter.generate_image.output_path must be absolute, for example /Users/you/output.png.tests/test_tools.py requires a live AGENTBRIDGE_API_KEY.server.json and the package version in sync before release. Release notes are generated on GitHub. The Makefile release helper is make release-x.y.z.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 -- uv run --directory /path/to/mcp-openrouter mcp-openrouter
opencode:
{
"mcp": { "openrouter": { "type": "local", "command": ["uv", "run", "--directory", "/path/to/mcp-openrouter", "mcp-openrouter"], "enabled": true } } }
All model requests use AgentBridge as their sole endpoint. Set AGENTBRIDGE_BASE_URL to its API root (default http://127.0.0.1:8082/api/v1). AGENTBRIDGE_API_KEY is an optional gateway access token; upstream OpenRouter credentials are managed only by AgentBridge. Existing model choices are preserved and gain the gateway's openrouter/ namespace on requests. Image generation and embeddings require the gateway application routes; there is no direct-provider fallback.
MIT