Cathedral — Persistent Memory for AI Agents MCP Server

What the code does

We read the source, 21 h ago · rules 3dff92dd89df

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

        result = subprocess.run(

# Glama verification key - server starts and responds to MCP introspection
# Replace with your real key from cathedral-ai.com
ENV CATHEDRAL_API_KEY=glama-check

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

claude mcp add cathedral-mcp --transport http https://cathedral-ai.com/mcp

{
  "mcpServers": {
    "cathedral-mcp": {
      "url": "https://cathedral-ai.com/mcp"
    }
  }
}

[mcp_servers.cathedral-mcp]
url = "https://cathedral-ai.com/mcp"

{
  "mcpServers": {
    "cathedral-mcp": {
      "url": "https://cathedral-ai.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "cathedral-mcp": {
      "url": "https://cathedral-ai.com/mcp"
    }
  }
}

This one needs environment variables set before it will start: CATHEDRAL_API_KEY (Your Cathedral API key from cathedral-ai.com), CATHEDRAL_BASE_URL (Cathedral API base URL (for self-hosted instances)), CATHEDRAL_SANITISE (Set to 1 to enable prompt injection filtering on memory content). The author declared them in the registry entry; get the values from the project itself.

This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.

Endpoints