AgentHubAgentHub

openrouter-multimodal

MCP ServerMCP Registry官方收录

io.github.stabgan/openrouter-multimodal · v4.5.1

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

源仓库 ↗

概览

openrouter-multimodal 是一个MCP Server，收录自 官方 MCP Registry。支持 stdio 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。

安装

选择你的平台查看安装方式

{
  "mcpServers": {
    "openrouter-multimodal": {
      "command": "npx",
      "args": [
        "-y",
        "@stabgan/openrouter-mcp-multimodal"
      ],
      "env": {
        "OPENROUTER_API_KEY": "<OPENROUTER_API_KEY>"
      }
    }
  }
}

环境变量

OPENROUTER_API_KEY必填secret

OpenRouter API key. Get one free at https://openrouter.ai/keys

OPENROUTER_DEFAULT_MODEL可选

Default model for chat + analyze tools. Defaults to nvidia/nemotron-nano-12b-v2-vl:free.

OPENROUTER_OUTPUT_DIR可选

Sandbox root for save_path on generate_* tools. Defaults to the current working directory.

OPENROUTER_MAX_TOKENS可选

Default max_tokens for chat_completion when unset in the request.

OPENROUTER_PROVIDER_SORT可选

price / throughput / latency

OPENROUTER_PROVIDER_IGNORE可选

CSV of provider slugs to exclude.

OPENROUTER_PROVIDER_ORDER可选

JSON array or CSV of preferred provider IDs.

OPENROUTER_PROVIDER_QUANTIZATIONS可选

CSV of quantization levels (fp16,int8).

OPENROUTER_PROVIDER_REQUIRE_PARAMETERS可选

true/false. Require providers to support all request params.

OPENROUTER_PROVIDER_DATA_COLLECTION可选

allow/deny

OPENROUTER_PROVIDER_ALLOW_FALLBACKS可选

true/false

OPENROUTER_CACHE_RESPONSES可选

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可选

Enable reasoning tokens passthrough server-wide. Adds _meta.reasoning to chat_completion responses for DeepSeek R1 / Gemini Thinking / Opus 4.7.

OPENROUTER_API_KEY必填secret

OpenRouter API key. Get one free at https://openrouter.ai/keys

相关资源

统一 Manifest

{
  "id": "io.github.stabgan/openrouter-multimodal",
  "type": "mcp-server",
  "version": "4.5.1",
  "displayName": "openrouter-multimodal",
  "description": "Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP.",
  "repository": {
    "url": "https://github.com/stabgan/openrouter-mcp-multimodal",
    "source": "github"
  },
  "distribution": {
    "packages": [
      {
        "registryType": "npm",
        "identifier": "@stabgan/openrouter-mcp-multimodal",
        "version": "4.5.1",
        "transport": "stdio",
        "environmentVariables": [
          {
            "name": "OPENROUTER_API_KEY",
            "description": "OpenRouter API key. Get one free at https://openrouter.ai/keys",
            "isRequired": true,
            "isSecret": true
          },
          {
            "name": "OPENROUTER_DEFAULT_MODEL",
            "description": "Default model for chat + analyze tools. Defaults to nvidia/nemotron-nano-12b-v2-vl:free."
          },
          {
            "name": "OPENROUTER_OUTPUT_DIR",
            "description": "Sandbox root for save_path on generate_* tools. Defaults to the current working directory."
          },
          {
            "name": "OPENROUTER_MAX_TOKENS",
            "description": "Default max_tokens for chat_completion when unset in the request."
          },
          {
            "name": "OPENROUTER_PROVIDER_SORT",
            "description": "price / throughput / latency"
          },
          {
            "name": "OPENROUTER_PROVIDER_IGNORE",
            "description": "CSV of provider slugs to exclude."
          },
          {
            "name": "OPENROUTER_PROVIDER_ORDER",
            "description": "JSON array or CSV of preferred provider IDs."
          },
          {
            "name": "OPENROUTER_PROVIDER_QUANTIZATIONS",
            "description": "CSV of quantization levels (fp16,int8)."
          },
          {
            "name": "OPENROUTER_PROVIDER_REQUIRE_PARAMETERS",
            "description": "true/false. Require providers to support all request params."
          },
          {
            "name": "OPENROUTER_PROVIDER_DATA_COLLECTION",
            "description": "allow/deny"
          },
          {
            "name": "OPENROUTER_PROVIDER_ALLOW_FALLBACKS",
            "description": "true/false"
          },
          {
            "name": "OPENROUTER_CACHE_RESPONSES",
            "description": "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."
          },
          {
            "name": "OPENROUTER_INCLUDE_REASONING",
            "description": "Enable reasoning tokens passthrough server-wide. Adds _meta.reasoning to chat_completion responses for DeepSeek R1 / Gemini Thinking / Opus 4.7."
          }
        ]
      },
      {
        "registryType": "oci",
        "identifier": "docker.io/stabgan/openrouter-mcp-multimodal:4.5.1",
        "transport": "stdio",
        "environmentVariables": [
          {
            "name": "OPENROUTER_API_KEY",
            "description": "OpenRouter API key. Get one free at https://openrouter.ai/keys",
            "isRequired": true,
            "isSecret": true
          }
        ]
      }
    ],
    "remotes": []
  },
  "dependencies": [],
  "installTargets": [
    "claude-code",
    "claude-desktop",
    "cursor",
    "vscode"
  ],
  "keywords": [],
  "provenance": {
    "origin": "official-mcp-registry",
    "originalId": "io.github.stabgan/openrouter-multimodal",
    "originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.stabgan%2Fopenrouter-multimodal/versions/latest",
    "isOfficial": true,
    "status": "active"
  }
}
openrouter-multimodal — MCP Server 安装与配置 · AgentHub