io.github.stabgan/openrouter-multimodal

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

这个条目提供什么？

io.github.stabgan/openrouter-multimodal 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 67/100。作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。在将 io.github.stabgan/openrouter-multimodal 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。

事实快照

来源: Official MCP Registry
质量: 67/100
安装方式: npm
仓库: stabgan/openrouter-mcp-multimodal
仓库更新: 2026年5月4日

安装命令

npx -y @stabgan/openrouter-mcp-multimodal@4.5.1

安装方式: npm

运行此命令前，请先核对上游源码。

GitHub 项目

质量

仓库 Stars

仓库更新

2026年5月4日

质量分如何计算？

由六个维度加权得出，满分 100。
来源可信度（25）：是否收录于官方或精选 registry。
可安装性（25）：可直接运行的命令 > 已声明传输方式 > 仅源码。
维护活跃度（20）：最近推送时间；已归档条目此项为 0。
采用度（20）：仓库 star 数，按对数曲线计分。
文档完整性（10）与描述质量（10）：是否有已解析的 manifest 或 SKILL.md frontmatter，以及是否为真实描述而非占位文本。
某个来源结构上无法提供的维度（registry 不提供 star 和许可证）不计入该条目的平均分，而不是记为 0 分，因此不同来源的条目仍可横向比较。

MCP manifest

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-05-04T21:17:51.510662Z",
      "publishedAt": "2026-05-04T21:17:51.510662Z",
      "statusChangedAt": "2026-05-04T21:17:51.510662Z"
    }
  },
  "server": {
    "name": "io.github.stabgan/openrouter-multimodal",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "version": "4.5.1",
    "packages": [
      {
        "version": "4.5.1",
        "transport": {
          "type": "stdio"
        },
        "identifier": "@stabgan/openrouter-mcp-multimodal",
        "registryType": "npm",
        "environmentVariables": [
          {
            "name": "OPENROUTER_API_KEY",
            "format": "string",
            "isSecret": true,
            "isRequired": true,
            "description": "OpenRouter API key. Get one free at https://openrouter.ai/keys"
          },
          {
            "name": "OPENROUTER_DEFAULT_MODEL",
            "format": "string",
            "description": "Default model for chat + analyze tools. Defaults to nvidia/nemotron-nano-12b-v2-vl:free."
          },
          {
            "name": "OPENROUTER_OUTPUT_DIR",
            "format": "string",
            "description": "Sandbox root for save_path on generate_* tools. Defaults to the current working directory."
          },
          {
            "name": "OPENROUTER_MAX_TOKENS",
            "format": "string",
            "description": "Default max_tokens for chat_completion when unset in the request."
          },
          {
            "name": "OPENROUTER_PROVIDER_SORT",
            "format": "string",
            "description": "price / throughput / latency"
          },
          {
            "name": "OPENROUTER_PROVIDER_IGNORE",
            "format": "string",
            "description": "CSV of provider slugs to exclude."
          },
          {
            "name": "OPENROUTER_PROVIDER_ORDER",
            "format": "string",
            "description": "JSON array or CSV of preferred provider IDs."
          },
          {
            "name": "OPENROUTER_PROVIDER_QUANTIZATIONS",
            "format": "string",
            "description": "CSV of quantization levels (fp16,int8)."
          },
          {
            "name": "OPENROUTER_PROVIDER_REQUIRE_PARAMETERS",
            "format": "string",
            "description": "true/false. Require providers to support all request params."
          },
          {
            "name": "OPENROUTER_PROVIDER_DATA_COLLECTION",
            "format": "string",
            "description": "allow/deny"
          },
          {
            "name": "OPENROUTER_PROVIDER_ALLOW_FALLBACKS",
            "format": "string",
            "description": "true/false"
          },
          {
            "name": "OPENROUTER_CACHE_RESPONSES",
            "format": "string",
            "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",
            "format": "string",
            "description": "Enable reasoning tokens passthrough server-wide. Adds _meta.reasoning to chat_completion responses for DeepSeek R1 / Gemini Thinking / Opus 4.7."
          }
        ]
      },
      {
        "transport": {
          "type": "stdio"
        },
        "identifier": "docker.io/stabgan/openrouter-mcp-multimodal:4.5.1",
        "registryType": "oci",
        "environmentVariables": [
          {
            "name": "OPENROUTER_API_KEY",
            "format": "string",
            "isSecret": true,
            "isRequired": true,
            "description": "OpenRouter API key. Get one free at https://openrouter.ai/keys"
          }
        ]
      }
    ],
    "repository": {
      "url": "https://github.com/stabgan/openrouter-mcp-multimodal",
      "source": "github"
    },
    "description": "Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP."
  }
}

报告此条目的问题