Skip to main content

​
What is the Promptwatch MCP?

The Promptwatch MCP (Model Context Protocol) server lets AI assistants like Claude, Cursor, and other MCP-compatible clients query your Promptwatch data directly. Ask questions about your brand visibility, citations, AI traffic, and more without leaving your AI workflow. With the MCP server, you can:
  • Query brand visibility across ChatGPT, Claude, Gemini, Perplexity, and AI Overviews
  • Analyze citation sources to understand where LLMs get their information
  • Track AI-referred traffic to your website
  • Compare competitors in AI search results
  • Identify content gaps and get recommendations

​
Getting Started

​
Step 1: Get Your API Key

  1. Go to Settings → API Keys in your project dashboard
  2. Click Create API Key
  3. Copy and securely store your API key
Store your API key securely. Never commit it to version control or share it publicly.

​
Step 2: Connect Your MCP Client

The Promptwatch MCP server is remotely hosted, no installation required. Just add it to your client configuration.

Cursor

Click the button below to install automatically:Install MCP ServerCursor will open an install dialog. Before clicking Install, replace YOUR_API_KEY in the Authorization header value with the API key from Step 1.Or manually add to your .cursor/mcp.json:
{
  "mcpServers": {
    "promptwatch": {
      "url": "https://server.promptwatch.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
Replace YOUR_API_KEY with the API key from Step 1.
Run the following command in your terminal:
claude mcp add --transport http promptwatch https://server.promptwatch.com/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"
Replace YOUR_API_KEY with the API key from Step 1.Verify the server was added:
claude mcp list
Claude Desktop does not support remote MCP servers directly. Use the mcp-remote proxy as a workaround.Prerequisitesnpx is required to run the proxy. It comes with Node.js — install it from nodejs.org (LTS recommended) if you don’t have it. Verify with the following command in your terminal:
npx --version
1. Open your config fileIn Claude Desktop, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json. You can also find it manually at:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
2. Add the Promptwatch serverYour config file may already have other MCP servers or settings. Add the "promptwatch" entry inside the "mcpServers" object. If "mcpServers" doesn’t exist yet, add it.Here’s what a complete config file looks like with Promptwatch added:
{
  "mcpServers": {
    "promptwatch": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://server.promptwatch.com/mcp",
        "--header",
        "Authorization: Bearer YOUR_API_KEY"
      ]
    }
  }
}
If you already have other servers in "mcpServers", just add the "promptwatch" block alongside them:
{
  "mcpServers": {
    "some-other-server": { "..." : "..." },
    "promptwatch": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://server.promptwatch.com/mcp",
        "--header",
        "Authorization: Bearer YOUR_API_KEY"
      ]
    }
  }
}
Replace YOUR_API_KEY with the API key from Step 1.3. Restart Claude Desktop to pick up the new configuration.
Any MCP-compatible client can connect using the remote server URL:
URL: https://server.promptwatch.com/mcp
Transport: HTTP
Authorization: Bearer YOUR_API_KEY
If your client does not support remote MCP servers, use the mcp-remote proxy:
{
  "mcpServers": {
    "promptwatch": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://server.promptwatch.com/mcp",
        "--header",
        "Authorization: Bearer YOUR_API_KEY"
      ]
    }
  }
}
Replace YOUR_API_KEY with the API key from Step 1.

​
Step 3: Start Using It

Once configured, ask your AI assistant questions like:
  • “How visible is my brand in AI search results?”
  • “Which sources are LLMs citing when they mention us?”
  • “Compare our AI visibility against competitors”
  • “What content gaps should I address?”
  • “How much traffic are we getting from AI tools?”

​
Support

Need help? Contact us at team@promptwatch.com or visit promptwatch.com.