Metricool MCP server

The Metricool MCP server enables AI agents to interact with the Metricool API, allowing them to access social media metrics, analyze campaign data, and schedule posts to your Metricool account. This server implements the Multi-Agent Collaboration Protocol (MCP) to provide a seamless interface between AI agents and your social media management tools.

Prerequisites

Before installing the Metricool MCP server, ensure you have:

• Python 3.8 or higher
• A Metricool account with API access (Advanced Tier)
• Claude Desktop (or any other MCP Client)
• uv package manager
• git

It's recommended to familiarize yourself with the MCP documentation as the protocol is still evolving.

Installation and Configuration

Set Up Claude Desktop Configuration

Create a configuration file with your Metricool credentials in the appropriate location for your operating system:

On MacOS:

~/Library/Application Support/Claude/claude_desktop_config.json

On Windows:

%APPDATA%/Claude/claude_desktop_config.json

Add the following configuration, replacing the placeholder values with your actual Metricool API credentials:

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

Available Tools

The Metricool MCP server provides several tools to interact with the Metricool API:

Brand Management

• get_brands(state: str) - Retrieve the list of brands from your Metricool account

Instagram Analytics

• get_Instagram_Reels(init_date: str, end_date: str, blog_id: int) - Get Instagram Reels data
• get_Instagram_Posts(init_date: str, end_date: str, blog_id: int) - Get Instagram Posts data
• get_Instagram_Stories(init_date: str, end_date: str, blog_id: int) - Get Instagram Stories data

TikTok Analytics

• get_Tiktok_Videos(init_date: str, end_date: str, blog_id: int) - Get TikTok Videos data

Facebook Analytics

• get_Facebook_Reels(init_date: str, end_date: str, blog_id: int) - Get Facebook Reels data
• get_Facebook_Posts(init_date: str, end_date: str, blog_id: int) - Get Facebook Posts data
• get_Facebook_Stories(init_date: str, end_date: str, blog_id: int) - Get Facebook Stories data

Other Social Media Analytics

• get_Thread_Posts(init_date: str, end_date: str, blog_id: int) - Get Threads Posts data
• get_X_Posts(init_date: str, end_date: str, blog_id: int) - Get X (Twitter) Posts data
• get_Bluesky_Posts(init_date: str, end_date: str, blog_id: int) - Get Bluesky Posts data
• get_Linkedin_Posts(init_date: str, end_date: str, blog_id: int) - Get LinkedIn Posts data
• get_Pinterest_Pins(init_date: str, end_date: str, blog_id: int) - Get Pinterest Pins data
• get_Youtube_Videos(init_date: str, end_date: str, blog_id: int) - Get YouTube Videos data
• get_Twitch_Videos(init_date: str, end_date: str, blog_id: int) - Get Twitch Videos data

Ad Campaign Analytics

• get_FacebookAds_Campaigns(init_date: str, end_date: str, blog_id: int) - Get Facebook Ads Campaigns data
• get_GoogleAds_Campaigns(init_date: str, end_date: str, blog_id: int) - Get Google Ads Campaigns data
• get_TiktokAds_Campaigns(init_date: str, end_date: str, blog_id: int) - Get TikTok Ads Campaigns data

Competitive Analysis

• get_Network_Competitors - Get competitors' data across platforms (Instagram, Facebook, X, Bluesky, YouTube and Twitch)

Post Management

• post_Schedule_Post - Schedule a post (or multipost) to your brands in Metricool
• get_Best_Time_To_Post - Get the optimal times to post for specific social networks
• update_Schedule_Post - Update a scheduled post within the same conversation

Usage Examples

To use the Metricool MCP server with Claude, simply ask Claude to perform tasks related to social media analytics or post scheduling. For example:

• "Show me my Instagram reels performance from last month"
• "What are the best times to post on LinkedIn for my account?"
• "Schedule a post about our new product launch across all platforms"
• "Compare our Facebook engagement with our top competitors"

Claude will use the appropriate Metricool MCP tools to retrieve the requested information or perform the requested actions.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "mcp-metricool" '{"command":"uvx","args":["mcp-metricool"],"env":{"METRICOOL_USER_TOKEN":"<METRICOOL_USER_TOKEN>","METRICOOL_USER_ID":"<METRICOOL_USER_ID>"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

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

3. Restart Claude Desktop for the changes to take effect