AgentReacher

AgentReacher

Connect your AI to social media. Open-source platform for AI agents.

Category
访问服务器

README

AgentReacher

agentreacher.com

AgentReacher connects your AI to social media. Open-source platform for AI agents.

The product is intentionally split into two layers:

  • the fully open-source product in this repository
  • a hosted service layer for managed execution, connected accounts, analytics, and convenience

Social Integrations

Platform Status
X (Twitter)
LinkedIn
Bluesky
Instagram
TikTok
YouTube
Facebook
Threads
Pinterest

What is in this repo

  • TanStack Start app for AgentReacher
  • auth, billing, onboarding, workspace, and dashboard flows
  • MCP server and CLI
  • multi-platform social connection and publishing flows
  • post creation, scheduling, and publishing APIs
  • basic analytics and calendar views

Open Source vs Hosted

Everything in AgentReacher is open source in this repository.

The hosted service exists for users who want the completed product experience without assembling the infrastructure themselves.

The hosted layer primarily adds:

  • managed deployment and operations
  • connected account setup in a ready-to-use product
  • managed credentials and third-party service configuration
  • convenience, reliability, and reduced setup time

You can self-host the full product, but you will need your own accounts, credentials, and infrastructure for the third-party services AgentReacher integrates with.

Stack

  • React 19
  • TanStack Start
  • Cloudflare Workers
  • InstantDB
  • Better Auth
  • Stripe
  • MCP SDK

Getting started

Prerequisites

  • Node.js 22+
  • pnpm
  • an InstantDB app and admin token

Local development

  1. Install dependencies:
pnpm install
  1. Copy the environment template:
cp .env.example .env.local
  1. Fill in the required values in .env.local.

At minimum, local development expects:

  • VITE_INSTANT_APP_ID
  • INSTANT_APP_ADMIN_TOKEN
  • BETTER_AUTH_SECRET
  • BETTER_AUTH_URL
  • VITE_BETTER_AUTH_URL
  1. Start the app:
pnpm dev

MCP CLI

The package exposes an agentreacher CLI for MCP setup.

Initialize MCP config

npx -y agentreacher@latest init

If you install AgentReacher directly from an MCP registry, you can usually skip manual API key setup. On first use, the server opens a browser and walks you through sign-in automatically.

For local development inside this repository:

node bin/agentreacher.mjs init

There is a sanitized example config at .mcp.json.example.

Available MCP tools

  • list_connected_social_accounts
  • get_social_connection_oauth_url
  • connect_bluesky_account
  • instagram_publish_media
  • create_text_post
  • create_image_post
  • upload_media
  • schedule_post
  • publish_post_now
  • list_posts
  • submit_feedback

The tool schema is defined in src/lib/agent-mcp-spec.json.

Current limitations and notes

  • some providers have provider-specific media and OAuth constraints
  • self-hosting requires your own platform app credentials and API configuration
  • media publishing flows depend on publicly reachable assets where the provider requires them
  • media must be reachable at a public http or https URL
  • Instagram video publishing uses the Reels flow
  • Bluesky uses direct account connection instead of OAuth

Deployment

For self-hosting:

  • set Cloudflare Worker secrets separately from wrangler.jsonc
  • replace placeholder vars and routes in wrangler.jsonc
  • configure your own InstantDB, Stripe, Better Auth providers, Resend, Upstash, OpenAI, Runware, and social platform apps as needed

Project policy

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选