广告合作
MCP.so
登录

Meta Business MCP Server

@metabusiness-mcp

代码仓库主页

基本信息

分类

沟通协作

传输方式

stdio

作者

metabusiness-mcp

提交者

Meta Business MCP

关于 Meta Business MCP Server

Production-validated MCP server for WhatsApp Business Cloud API — compliance engine, error intelligence & message orchestration for AI agents. 24 tools, sub-2ms decisions, 85.6% test coverage.

#metabusinessmcp#whatsapp-mcp#whatsappbusinessmcp#whatsapp#mcp

Meta Business MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "meta-business-mcp": {
      "command": "/path/to/meta-business-mcp",
      "args": [],
      "env": {
        "CONFIG_PATH": "/path/to/config.yaml"
      }
    }
  }
}

Meta Business MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Meta Business MCP?

A WhatsApp compliance intelligence platform that ensures every AI Agent can operate WhatsApp Business safely, compliantly, and production-ready — without understanding Meta's rule complexity. It sits between the AI Agent and Meta's API, enforcing every rule automatically. It is built for AI Agent developers, digital agencies, and WhatsApp automation teams.

How to use Meta Business MCP?

Clone the repository and run docker compose up -d --build. Access the dashboard at http://localhost:8080 using the auto‑generated password printed in the terminal. Then configure your AI client (e.g. Claude Desktop, Cursor) to point to the Meta Business MCP binary as a stdio MCP server. No Meta API keys are required for local development—mock credentials are used by default.

Key features of Meta Business MCP

  • 24 structured MCP tools for AI Agents
  • Compliance gate evaluating every outbound message
  • Async message delivery via NATS JetStream with retries
  • Per‑customer rate limiting via Redis token bucket
  • Error intelligence translating Meta API error codes
  • Campaign management with scheduling and audience filters
  • Template lifecycle management with Meta API sync

Use cases of Meta Business MCP

  • AI agents sending WhatsApp messages with compliance enforcement
  • Automating customer service with 24‑hour care window management
  • Running marketing campaigns with template approval and audience segmentation
  • Monitoring and debugging WhatsApp Business API errors
  • Ensuring opt‑out mandates and frequency caps are respected

常见问题

1

What programming language is Meta Business MCP built with?

Go 1.21+.

2

How many tools are available for AI agents?

24 structured tools — 21 are free forever, and 3 campaign tools are on the Pro tier.

3

What are the infrastructure dependencies?

PostgreSQL 16, Redis 7, NATS JetStream, and the Meta Cloud API (or its built‑in mock).

4

How does the compliance engine work?

It evaluates every outbound message against Meta’s care window rules, opt‑out lists, and frequency caps, and enforces custom business policies from a YAML‑seeded database.

5

Can I run Meta Business MCP locally without Meta API keys?

Yes, mock credentials are used by default, so no Meta API keys are required for local development.

评论

沟通协作 分类下的更多 MCP 服务器

JooVoice

JooVoice

Give your AI agent a phone. JooVoice makes real calls for you in 80+ languages, with local accents, across 67 countries, like booking a table, moving an appointment or chasing a refund, and sends back what happened. Call

Atomic Mail Agentic

Atomic-Mail

Let your agents read, send and react to email autonomously, without human involvement

255

Tactiq

Search, read, and summarise meeting transcripts and summaries from Google Meet, Zoom, and Microsoft Teams - directly from Claude. Meetings as context: ask what was decided, who you spoke with, or what’s come up across an

SomaCheck Vibecheck

Sensie-agents

Body language for AI agents, on your terms. A consented three-second phone gesture gives your agent an Aligned or Unaligned signal with confidence. You remain the authority.

1

ARVX

Centric AI, Inc.

Email for long-term client relationships: ARVX reads each person first and remembers every pair.

广告合作