Skip to main content
Metaview supports the Model Context Protocol (MCP), an open standard for connecting AI tools to data sources. With MCP, you can connect AI-powered tools like Claude Desktop, Claude Code, Cursor, Windsurf, and other MCP-compatible clients to your Metaview workspace. The AI client will query your sessions, pull summaries, and give you a structured answer. Most MCP-compatible clients support OAuth authentication. This is the simplest way to connect — no API key needed. 1. Add the Metaview MCP server URL to your client Add the following to your MCP client configuration: 
{
  "metaview": {
    "type": "http",
    "url": "https://mcp.metaview.ai/mcp"
  }
}
For example, in Claude Desktop, add this to your claude_desktop_config.json under the "mcpServers" key. In Cursor, add it to your MCP settings. Refer to your client’s documentation for the exact location of MCP server configuration. 2. Sign in with your Metaview account When your MCP client connects, it will open a browser window prompting you to sign in with your Metaview account. Once authenticated, your client can access your Metaview data. 3. Start using Metaview data in your AI tools Once connected, your AI tool can access your Metaview interview data, summaries, and reports through the MCP integration.

​
Using an API key

If your MCP client does not support OAuth, you can authenticate using an API key instead 1. Navigate to the MCP integration settings in the Metaview app You can navigate to the MCP settings directly with this link, or navigate through the Integrations page. Toggle on “Use API Key instead of OAuth?” to access the API key management section. 2. Generate a new API key Click the Generate API Key button. Give your key a descriptive name (e.g. “Claude Desktop” or “Cursor”) so you can identify it later. Copy the generated key immediately - you won’t be able to see the full key again. 3. Configure your MCP client Setup varies depending on which MCP client you are using. Follow the instructions for your client below.
Claude Desktop does not yet support the HTTP transport format for MCP servers, so you will need to use the mcp-remote bridge via Node.js.Prerequisites: Download and install Node.js if you don’t already have it.
  1. Open Claude Desktop and go to Settings > Developer > Edit Config.
  2. Paste the following into the configuration file, replacing YOUR_API_KEY with the key you copied in step 2:
{
  "mcpServers": {
    "metaview": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.metaview.ai/mcp",
        "--header",
        "Authorization: Bearer YOUR_API_KEY"
      ]
    }
  }
}
  1. Quit Claude Desktop completely and reopen it.
4. Start using Metaview data in your AI tools Once connected, your AI tool can access your Metaview interview data, summaries, and reports through the MCP integration.

​
Managing API keys

You can create multiple API keys, one for each tool or client you want to connect. Each key is named so you can easily identify which tool it belongs to. To revoke access for a specific tool, delete the corresponding API key from the MCP settings page. This immediately prevents that tool from accessing your Metaview data.

​
Security

  • OAuth sign-in uses your existing Metaview account credentials — no extra secrets to manage
  • API keys are scoped to your personal Metaview account
  • Both methods can only access data you have permission to view
  • You can revoke any API key at any time

​
Help and troubleshooting

If you have any issues connecting your MCP client to Metaview, please reach out to us.