NM

namdzmaso02/mcp-metricool

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

0 stars 15 forks 质量 60 趋势 0Apache-2.0

This is a Multi-Agent Collaboration Protocol (MCP) server for interacting with the Metricool API. It allows AI agents to access and analyze social media metrics and campaign data from your Metricool...

概览

This is a Multi-Agent Collaboration Protocol (MCP) server for interacting with the Metricool API. It allows AI agents to access and analyze social media metrics, campaign data and schedule posts to your Metricool account. MCP is still very new and evolving, we recommend following the MCP documentation to get the MCP basics up and running. - Python 3.8 or higher - A Metricool account with API access (Advanced Tier) - Claude Desktop (or Cursor, or any MCP Client) - uv - git 1. Configure Claude Desktop Create the following file depending on your OS: On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json Paste this template in the file and replace and with your Metricool API and ID information: The server implements several tools to interact with the Metricool API:

README

以下为原文 README 节选,完整内容请查看原文。

Metricool MCP Server

This is a Multi-Agent Collaboration Protocol (MCP) server for interacting with the Metricool API. It allows AI agents to access and analyze social media metrics, campaign data and schedule posts to your Metricool account.

Setup

Prerequisites

MCP is still very new and evolving, we recommend following the MCP documentation to get the MCP basics up and running.

Configuration

  1. Configure Claude Desktop Create the following file depending on your OS:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json

On Windows: %APPDATA%/Claude/claude_desktop_config.json

Paste this template in the file and replace and with your Metricool API and ID information:

{
    "mcpServers": {
        "mcp-metricool": {
            "command": "uvx",
            "args": [
                "mcp-metricool"
            ],
            "env": {
                "METRICOOL_USER_TOKEN": "",
                "METRICOOL_USER_ID": ""
            }
        }
    }
}

Tools

The server implements several tools to interact with the Metricool API:

  1. get_brands(state: str)

    • Get the list of brands from your Metricool account.
  2. get_instagram_reels(init_date: str, end_date: str, blog_id: int)

    • Get the list of Instagram Reels from your Metricool account.
  3. get_instagram_posts(init_date: str, end_date: str, blog_id: int)

    • Get the list of Instagram Posts from your Metricool account.
  4. get_instagram_stories(init_date: str, end_date: str, blog_id: int)

    • Get the list of Instagram Stories from your Metricool account.
  5. get_tiktok_videos(init_date: str, end_date: str, blog_id: int)

    • Get the list of Tiktok Videos from your Metricool account.
  6. get_facebook_reels(init_date: str, end_date: str, blog_id: int)

    • Get the list of Facebook Reels from your Metricool account.
  7. get_facebook_posts(init_date: str, end_date: str, blog_id: int)

    • Get the list of Facebook Posts from your Metricool brand account.
  8. get_facebook_stories(init_date: str, end_date: str, blog_id: int)

    • Get the list of Facebook Stories from your Metricool brand account.
  9. get_thread_posts(init_date: str, end_date: str, blog_id: int)

    • Get the list of Threads Posts from your Metricool brand account.
  10. get_x_posts(init_date: str, end_date: str, blog_id: int)

    • Get the list of X (Twitter) Posts from your Metricool account.
  11. get_bluesky_posts(init_date: str, end_date: str, blog_id: int)

    • Get the list of Bluesky Posts from your Metricool brand account.
在 GitHub 查看完整 README

安装

uvx mcp-metricool
新手?先看 mcpskill.org 教程 →

配置

{ "mcpServers": { "mcp-metricool": { "command": "uvx", "args": [ "mcp-metricool" ], "env": { "METRICOOL_USER_TOKEN": "<METRICOOL_USER_TOKEN>", "METRICOOL_USER_ID": "<METRICOOL_USER_ID>" } } } }