原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Openrouter Multimodal

作者:stabgan版本 4.5.1i★ –i在你的电脑上运行
注册名称io.github.stabgan/openrouter-multimodal

安装

概览

作者提供的说明(英文原文)

Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP.

PopNx MCP 的三大支柱

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。

它能帮你做什么

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。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 设计、图片与音频
  • 你需要填写:OPENROUTER_API_KEY

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 需要你自己填写: OPENROUTER_API_KEY, OPENROUTER_DEFAULT_MODEL, OPENROUTER_OUTPUT_DIR, OPENROUTER_MAX_TOKENS, OPENROUTER_PROVIDER_SORT, OPENROUTER_PROVIDER_IGNORE, OPENROUTER_PROVIDER_ORDER, OPENROUTER_PROVIDER_QUANTIZATIONS, OPENROUTER_PROVIDER_REQUIRE_PARAMETERS, OPENROUTER_PROVIDER_DATA_COLLECTION, OPENROUTER_PROVIDER_ALLOW_FALLBACKS, OPENROUTER_CACHE_RESPONSES, OPENROUTER_INCLUDE_REASONING

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

  • npm已安装 Node.js(用于 npx 命令)

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-multimodal": {
      "command": "npx",
      "args": [
        "-y",
        "@stabgan/openrouter-mcp-multimodal"
      ],
      "env": {
        "OPENROUTER_API_KEY": "your-value",
        "OPENROUTER_DEFAULT_MODEL": "your-value",
        "OPENROUTER_OUTPUT_DIR": "your-value",
        "OPENROUTER_MAX_TOKENS": "your-value",
        "OPENROUTER_PROVIDER_SORT": "your-value",
        "OPENROUTER_PROVIDER_IGNORE": "your-value",
        "OPENROUTER_PROVIDER_ORDER": "your-value",
        "OPENROUTER_PROVIDER_QUANTIZATIONS": "your-value",
        "OPENROUTER_PROVIDER_REQUIRE_PARAMETERS": "your-value",
        "OPENROUTER_PROVIDER_DATA_COLLECTION": "your-value",
        "OPENROUTER_PROVIDER_ALLOW_FALLBACKS": "your-value",
        "OPENROUTER_CACHE_RESPONSES": "your-value",
        "OPENROUTER_INCLUDE_REASONING": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add openrouter-multimodal --env OPENROUTER_API_KEY=your-value --env OPENROUTER_DEFAULT_MODEL=your-value --env OPENROUTER_OUTPUT_DIR=your-value --env OPENROUTER_MAX_TOKENS=your-value --env OPENROUTER_PROVIDER_SORT=your-value --env OPENROUTER_PROVIDER_IGNORE=your-value --env OPENROUTER_PROVIDER_ORDER=your-value --env OPENROUTER_PROVIDER_QUANTIZATIONS=your-value --env OPENROUTER_PROVIDER_REQUIRE_PARAMETERS=your-value --env OPENROUTER_PROVIDER_DATA_COLLECTION=your-value --env OPENROUTER_PROVIDER_ALLOW_FALLBACKS=your-value --env OPENROUTER_CACHE_RESPONSES=your-value --env OPENROUTER_INCLUDE_REASONING=your-value -- npx -y @stabgan/openrouter-mcp-multimodal

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "openrouter-multimodal": {
      "command": "npx",
      "args": [
        "-y",
        "@stabgan/openrouter-mcp-multimodal"
      ],
      "env": {
        "OPENROUTER_API_KEY": "your-value",
        "OPENROUTER_DEFAULT_MODEL": "your-value",
        "OPENROUTER_OUTPUT_DIR": "your-value",
        "OPENROUTER_MAX_TOKENS": "your-value",
        "OPENROUTER_PROVIDER_SORT": "your-value",
        "OPENROUTER_PROVIDER_IGNORE": "your-value",
        "OPENROUTER_PROVIDER_ORDER": "your-value",
        "OPENROUTER_PROVIDER_QUANTIZATIONS": "your-value",
        "OPENROUTER_PROVIDER_REQUIRE_PARAMETERS": "your-value",
        "OPENROUTER_PROVIDER_DATA_COLLECTION": "your-value",
        "OPENROUTER_PROVIDER_ALLOW_FALLBACKS": "your-value",
        "OPENROUTER_CACHE_RESPONSES": "your-value",
        "OPENROUTER_INCLUDE_REASONING": "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。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "openrouter-multimodal": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@stabgan/openrouter-mcp-multimodal"
      ],
      "env": {
        "OPENROUTER_API_KEY": "your-value",
        "OPENROUTER_DEFAULT_MODEL": "your-value",
        "OPENROUTER_OUTPUT_DIR": "your-value",
        "OPENROUTER_MAX_TOKENS": "your-value",
        "OPENROUTER_PROVIDER_SORT": "your-value",
        "OPENROUTER_PROVIDER_IGNORE": "your-value",
        "OPENROUTER_PROVIDER_ORDER": "your-value",
        "OPENROUTER_PROVIDER_QUANTIZATIONS": "your-value",
        "OPENROUTER_PROVIDER_REQUIRE_PARAMETERS": "your-value",
        "OPENROUTER_PROVIDER_DATA_COLLECTION": "your-value",
        "OPENROUTER_PROVIDER_ALLOW_FALLBACKS": "your-value",
        "OPENROUTER_CACHE_RESPONSES": "your-value",
        "OPENROUTER_INCLUDE_REASONING": "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。

需要你填写的值

  • OPENROUTER_API_KEY 机密 必填 env
    OpenRouter API key. Get one free at https://openrouter.ai/keys
  • OPENROUTER_DEFAULT_MODEL env
    Default model for chat + analyze tools. Defaults to nvidia/nemotron-nano-12b-v2-vl:free.
  • OPENROUTER_OUTPUT_DIR env
    Sandbox root for save_path on generate_* tools. Defaults to the current working directory.
  • OPENROUTER_MAX_TOKENS env
    Default max_tokens for chat_completion when unset in the request.
  • OPENROUTER_PROVIDER_SORT env
    price / throughput / latency
  • OPENROUTER_PROVIDER_IGNORE env
    CSV of provider slugs to exclude.
  • OPENROUTER_PROVIDER_ORDER env
    JSON array or CSV of preferred provider IDs.
  • OPENROUTER_PROVIDER_QUANTIZATIONS env
    CSV of quantization levels (fp16,int8).
  • OPENROUTER_PROVIDER_REQUIRE_PARAMETERS env
    true/false. Require providers to support all request params.
  • OPENROUTER_PROVIDER_DATA_COLLECTION env
    allow/deny
  • OPENROUTER_PROVIDER_ALLOW_FALLBACKS env
    true/false
  • OPENROUTER_CACHE_RESPONSES env
    Enable response caching server-wide. Sends X-OpenRouter-Cache: true on every chat/analyze call unless overridden per-request. Zero tokens billed on cache hits.
  • OPENROUTER_INCLUDE_REASONING env
    Enable reasoning tokens passthrough server-wide. Adds _meta.reasoning to chat_completion responses for DeepSeek R1 / Gemini Thinking / Opus 4.7.

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。

它能做什么

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。

基础检查i

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

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 stabgan 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    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“设计、图片与音频”中的其他服务器比较i

  • 星标数多于此分类中其他 2204 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 2204 个服务器的 7% 更新
  • 基础检查结果等于或优于此分类中其他 2204 个服务器的 100%

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。

常见问题

Openrouter Multimodal 安全吗?

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。

它需要哪些密钥或代码?

你需要填写:OPENROUTER_API_KEY

它在我的电脑上运行还是在云端?

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)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(4.5.1)于6个月前进入注册中心。

哪些应用可以使用它?

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 Node.js, Docker。

有什么可以替代它?

同一分类中有:Figma Context MCP, Claude Real Video, Figma MCP Server

替代选择

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

Figma Context MCP

作者:GLips

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

在你的电脑上运行★ 16,165MIT5个月前更新
安装

Claude Real Video

作者:HUANGCHIHHUNGLeo

Let any LLM watch a video locally — and search everything it has ever watched.

在你的电脑上运行★ 2,284MIT2个月前更新
安装

Figma MCP Server

作者:figma

The Figma MCP server brings Figma design context directly into your AI workflow.

在云端运行★ 2,15213个月前更新
安装

作者的 README

打开 README

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。

OpenRouter MCP Multimodal

The MCP server for multimodal AI agents.

One install · 21 tools · 300+ OpenRouter models · text, vision, audio & video — analysis and generation.

Quick start · Tools · Examples · Security · Troubleshooting · Development · Releasing · FAQ


What is this?

OpenRouter MCP Multimodal is a production-grade Model Context Protocol (MCP) server — listed on the official MCP Registry as io.github.stabgan/openrouter-multimodal. It connects AI coding agents (Cursor, Claude Desktop, VS Code, Windsurf, Cline, and others) to OpenRouter's unified LLM API over stdio.

Unlike text-only MCP servers, one install covers the full multimodal surface:

CapabilityToolsHighlights
Chatchat_completion, start_chat_completion, get_chat_completion_status300+ models, :nitro / :floor / :free / :online / :exacto suffixes, provider routing, web search, response caching, reasoning tokens, reasoning effort control, structured output (JSON Schema), async jobs, multi-model fusion, subagent delegation, response healing
Visionanalyze_image, generate_image, generate_image_dedicatedOCR, captioning, VQA, image generation with reference inputs, dedicated Image API with resolution/quality/format control
Audioanalyze_audio, generate_audio, text_to_speech, speech_to_textTranscription, speech/music generation, dedicated TTS (Deepgram, ElevenLabs, OpenAI; free Deepgram default, voices, mp3/pcm), dedicated STT (Whisper, GPT-4o Transcribe, Voxtral, ElevenLabs Scribe)
Videoanalyze_video, generate_video, generate_video_from_image, get_video_statusClip understanding, Veo 3.1 / Seedance 2.5 / Kling v3.0 / Wan 2.7 / Grok Imagine Video generation with progress notifications
Embeddingembed_text37+ embedding models (text-embedding-3-small/large, Nomic, Jina, Voyage, etc.)
DecisionsdecideStructured yes/no, choice, or score decisions with calibrated probabilities (System One models)
Catalogsearch_models, get_model_info, validate_model, rerank_documents, health_checkModel discovery, validation, reranking, ops health

Production hardening: input/output path sandboxes (including analyze\_\* local files as of v4.5.2), SSRF guards, structured errors with _meta.code, MCP 2025-11-25 structured outputs + tool icons, async video progress notifications, and 3929 automated tests (3905 unit/mock + 7 regression + 17 live integration).

Quick start

1. Get an API key (free tier works) → openrouter.ai/keys

2. Run the server

export OPENROUTER_API_KEY=sk-or-v1-...

npx -y @stabgan/openrouter-mcp-multimodal

3. Add to your MCP client — copy one JSON block from Install into your client config:

ClientConfig location
CursorProject: .cursor/mcp.json · User: Cursor Settings → MCP
Claude DesktopmacOS: ~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json
VS Code.vscode/mcp.json (workspace) or User Settings → MCP
WindsurfWindsurf Settings → MCP (same mcpServers JSON shape as Cursor)

Use the mcpServers object from Manual config below.

No credits required to start. Free models such as google/gemma-4-26b-a4b-it:free work for chat and vision. Video/audio generation typically needs credits.

Install

MCP servers are distributed through several packaging models. This server is implemented in Node.js/TypeScript; the table below maps each ecosystem method to how you run it here.

MethodRuntimeBest forThis server
[npx](#manual-config)Node.js 22+Most MCP clients (default)✅ @stabgan/openrouter-mcp-multimodal
[uvx / pipx](#manual-config)Python 3.10+ and Node.js 22+Python-first workflows, same pattern as PyPI MCP servers✅ mcp-server-openrouter-multimodal
[npm global](#manual-config)Node.js 22+Pin a version without re-downloading✅
[node (local)](#manual-config)Node.js 22+Contributors / air-gapped builds✅
[Docker Hub](#manual-config)DockerIsolation, no Node on host✅ stabgan/openrouter-mcp-multimodal
[GHCR](#manual-config)DockerGitHub-native OCI pulls✅ ghcr.io/stabgan/openrouter-mcp-multimodal
[Smithery CLI](#smithery)Node.js (via installer)Interactive install into Claude/Cursor/etc.✅
[MCP Registry](#mcp-registry)npm or OCIOfficial discovery (io.github.stabgan/openrouter-multimodal)✅ listing
[One-click deeplinks](#one-click)Node.jsCursor, VS Code, Kiro✅
[Claude Code CLI](#claude-code-cli)Node.jsTerminal-first Claude Code users✅
[MCP Inspector](#mcp-inspector)Node.jsDebug / list tools locally✅

| **Windows cmd /c npx*

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx