MCP.so
ログイン

Social MCP: Multi-Agent Social Media Automation

@kitadmin01

リポジトリ

Social MCP: Multi-Agent Social Media Automation について

Socail MCP Server

基本情報

カテゴリ

AI とエージェント

ランタイム

python

トランスポート

stdio

公開者

kitadmin01

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "social_mcp": {
      "command": "python3",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Social MCP: Multi-Agent Social Media Automation?

Social MCP is a multi‑agent system that automates content extraction, tweet generation, posting, and engagement on platforms like Twitter and Bluesky. It uses LLMs for content generation, Playwright for browser automation, and platform APIs for integration.

How to use Social MCP: Multi-Agent Social Media Automation?

Clone the repository, create a Python virtual environment, install dependencies (including Playwright), and configure a .env file with Twitter credentials, Playwright session directory, and Google Sheets API / OAuth settings. Start the MCP server from /social_mcp with python mcp_server/server.py, then run the MCP client with python mcp_client/client.py.

Key features of Social MCP: Multi-Agent Social Media Automation

  • Persistent Twitter session management with automatic login detection
  • Tweet posting with retry logic and navigation recovery
  • LLM‑powered tweet generation and content scheduling
  • Hashtag‑based content discovery and engagement automation
  • Robust browser automation with page state verification
  • Google Sheets integration and shared retry / secrets utilities

Use cases of Social MCP: Multi-Agent Social Media Automation

  • Automate content extraction, LLM‑driven tweet generation, and multi‑platform posting
  • Schedule and publish content across Twitter and Bluesky
  • Perform hashtag‑based search, liking, and general social engagement
  • Orchestrate multi‑agent workflows that coordinate content creation and publishing

FAQ from Social MCP: Multi-Agent Social Media Automation

What are the runtime dependencies?

Python 3, Playwright (installed via playwright install), and all packages in requirements.txt. A .env file with Twitter credentials and a Playwright session directory is required.

How do I configure authentication?

Store Twitter username/password, Playwright session directory, and any other secrets in the .env file. For Google Sheets and Bluesky, set up OAuth credentials separately.

Where is browser session data stored?

Persistent browser session data is stored in the directory specified by PLAYWRIGHT_SESSION_DIR in the .env file (default ./playwright_session).

Can Social MCP run in headless mode?

Yes. Set HEADLESS=true in the .env file to enable headless browser operation.

Which social media platforms are supported?

Twitter (via Playwright browser automation) and Bluesky (via API integration).

コメント

「AI とエージェント」の他のコンテンツ

21st.dev Magic AI Agent

21st-dev

It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic

5.3K

🔎 GPT Researcher

assafelovic

An autonomous agent that conducts deep research on any data using any LLM providers

28.1K

欢迎来到 智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

🛡️ A.I.G（AI-Infra-Guard）

Tencent

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

4.1K

Mcp Agent

lastmile-ai

Build effective agents using Model Context Protocol and simple workflow patterns

8.4K