Skip to main content
Glama

Tomo Streaming MCP

使用 Tomo Streaming 从 Codex、Claude Code、Cursor、Windsurf、Antigravity 和其他 MCP 兼容的代理。

该服务器本地通过 stdio 运行,并通过 HTTP 调用 Tomo Streaming 控制面。它暴露了房间和运行时操作,无需将代理与社交网络耦合。

设置

npm install
npm run build

在 MCP 客户端的环境中设置控制面 URL 和 API 密钥:

{
  "mcpServers": {
    "tomo-streaming": {
      "command": "npx",
      "args": ["-y", "@tomo-social/streaming-mcp"],
      "env": {
        "TOMO_STREAM_URL": "https://stream.example.com",
        "TOMO_STREAM_API_KEY": "replace-with-a-secret"
      }
    }
  }
}

如果您的 npm 注册表镜像尚未传播该包,请改为安装固定的 GitHub 版本:

git clone --branch v0.1.0 https://github.com/Tomo-Social/tomo-streaming-mcp.git
cd tomo-streaming-mcp
npm install && npm run build

对于本地检出,请将 npx 替换为 node 以及 dist/index.js 的绝对路径。

Related MCP server: Local AI MCP

工具

Tool

Purpose

tomo_health

检查控制面可达性

tomo_list_stream_servers

发现摄像头、桌面和插件体验

tomo_list_rooms

列出房间和实时状态

tomo_create_room

为体验创建房间

tomo_get_room

检查状态和连接详情

tomo_control_room

暂停、恢复或重启房间

tomo_delete_room

停止并移除房间

安全性

API 密钥仅从进程环境读取,绝不会作为工具输出返回。以最小控制面权限运行 MCP 服务器,并将控制面置于 TLS 之后。删除房间作为显式工具暴露,以便代理可以在其自己的 UI 中请求确认。

兼容性

MCP 是集成边界。相同的服务器配置适用于 Codex、Claude Code、Cursor、Windsurf、Antigravity 以及任何支持 MCP stdio 服务器的客户端。控制面和流式 SDK 在无需 MCP 的情况下仍可使用。

许可证

根据 PolyForm Noncommercial License 提供源代码可用。商业代理集成需要从 Tomo 获得单独许可。

Install Server
F
license - not found
A
quality
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
1Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    A
    quality
    A
    maintenance
    Unified MCP server for managing local model runtimes (Ollama, LM Studio, etc.), enabling provider-agnostic discovery, lifecycle management, hardware-fit checks, and delegated inference.
    16
    224
    Creative Commons Attribution Non Commercial No Derivatives 4.0 International

View all related MCP servers

Related MCP Connectors

  • Manage SRG+ hubs, channels, content, assets, users, and workspaces from any MCP-aware AI agent.

  • Remote MCP server for RunComfy Serverless API (ComfyUI): deployments and async inference.

  • Read-only Dant3 MCP for public rooms, agents, jobs and provisional machine onboarding.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Tomo-Social/tomo-streaming-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server