Mention Me MCP Server - Mention Me Docs

Connect your AI assistant to real-time Mention Me reporting data. Query referral programme metrics, generate reports, and surface insights directly from your AI tool of choice.

Server URL

Use the following URL when adding the server to your AI client:

https://mcp.mention-me.com

Authentication

On first connect, your AI client opens a browser sign-in with your Mention Me account. No API keys or tokens are needed.

Connect your AI client

Select your AI client below for step-by-step instructions.

Claude Desktop

Open Claude Desktop
Click Customise
Go to Connectors
Click Add custom connector
Set the name to Mention Me
Paste the URL: https://mcp.mention-me.com

Claude Code

Run the following command in your terminal:

claude mcp add --transport http mention-me https://mcp.mention-me.com

Then run /mcp once you’ve opened a Claude Code session to go through the authentication flow.

Cursor

Open Cursor Settings → MCP
Click “Add new global MCP server”
Paste the following configuration:

{
  "mcpServers": {
    "mention-me": {
      "url": "https://mcp.mention-me.com"
    }
  }
}

Visual Studio Code

Open the Command Palette and search for “MCP: Add Server”
Choose “HTTP” as the server type
Paste the server URL: https://mcp.mention-me.com

Or add it manually to .vscode/mcp.json:

{
  "servers": {
    "mention-me": {
      "type": "http",
      "url": "https://mcp.mention-me.com"
    }
  }
}

Windsurf

Add the following to your Windsurf MCP configuration file at ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "mention-me": {
      "url": "https://mcp.mention-me.com"
    }
  }
}

Codex

The setup is the same whether you use the IDE extension or the CLI, since they share configuration.Run the following command in your terminal:

codex mcp add mention-me --url https://mcp.mention-me.com

This will automatically prompt you to sign in with your Mention Me account.If this is the first time you are using an MCP server in Codex, you will need to enable the rmcp feature. Add the following to your ~/.codex/config.toml:

[features]
experimental_use_rmcp_client = true

Or configure manually via ~/.codex/config.toml:

[features]
experimental_use_rmcp_client = true

[mcp_servers.mention-me]
url = "https://mcp.mention-me.com"

Then run codex mcp login mention-me to authenticate.

Other clients

Hundreds of AI tools now support MCP servers. You can configure them with the following settings:

Command: npx
Arguments: -y mcp-remote https://mcp.mention-me.com
Environment: None

Enhance with the agent skill

The MCP server gives your AI assistant the tools — the companion skill teaches it how to use them well: picking the right metric, resolving merchants, and building date comparisons correctly. We recommend installing it alongside the server.

Download mention-me-reporting.skill

Follows the open Agent Skills format, supported by most AI clients.

Claude & Claude Desktop

Download the skill file
Go to Settings → Capabilities → Skills
Click Upload skill and select the downloaded file

Skills are installed per user. On Claude for Work, an admin can enable the skill for the whole workspace.

Claude Code

Run the following command in your terminal:

curl -fsSL https://mcp.mention-me.com/mention-me-reporting.skill -o /tmp/mention-me-reporting.skill \
  && unzip -o /tmp/mention-me-reporting.skill -d ~/.claude/skills

To share the skill with your team via version control, extract it into .claude/skills/ in your repository instead.

Codex, Cursor, Copilot & other agents

Most agents — including Codex, Cursor, GitHub Copilot, Windsurf, Amp, and Goose — scan the shared ~/.agents/skills directory:

curl -fsSL https://mcp.mention-me.com/mention-me-reporting.skill -o /tmp/mention-me-reporting.skill \
  && unzip -o /tmp/mention-me-reporting.skill -d ~/.agents/skills

Gemini CLI uses ~/.gemini/skills instead. Restart or reload your agent after installing.

What you can do

Once connected, you can ask your AI assistant to:

Fetch any referral programme metric, with optional date comparison
Generate time-series reports broken down by day, week, or month
Split metrics by dimension, such as campaign, market, or locale
List the campaigns and organisations you have access to

Available tools

Tool	Description
`fetch_metric`	Fetch a single metric value (e.g. total referrals this month)
`fetch_metric_series`	Fetch a metric as a time series (e.g. daily referrals over 30 days)
`fetch_metric_by_dimension`	Fetch a metric split by dimension (campaign, market, locale)
`fetch_metric_series_by_dimension`	Fetch a metric over time, split by dimension
`fetch_campaigns`	List campaigns with status, type, locale, dates, and triggering rules
`list_organizations`	List organisations the authenticated user can access

The catalog of available metrics is exposed as the mentionme://metrics resource.

Example prompts

Try asking your AI assistant something like:

“Show me a weekly breakdown of new Mention Me referrals over the last 3 months”
“How many successful Mention Me referrals did we get last quarter?”
“Compare our Mention Me conversion rate this year vs last year”
“Give me a monthly trend of Mention Me referral revenue for the past 6 months”

Where to get help

If you need help connecting or using the MCP server, contact our support team.

​Server URL

​Authentication

​Connect your AI client

​Enhance with the agent skill

Download mention-me-reporting.skill

​What you can do

​Available tools

​Example prompts

​Where to get help

Server URL

Authentication

Connect your AI client

Enhance with the agent skill

What you can do

Available tools

Example prompts

Where to get help