fpf-memory MCP

ChatGPT

Create a custom app or connector and use the hosted MCP endpoint as the connector URL.

1. Open Settings > Apps & Connectors.
2. Enable developer mode under Advanced settings when your plan or workspace requires it.
3. Create a custom app or connector, set the Connector URL to the hosted endpoint, then confirm the advertised tools.
4. Open a new chat and add fpf-memory from the composer tools menu.

Claude

Add a custom connector from Claude settings and point it at the public MCP endpoint.

1. Open Customize > Connectors.
2. Click the + button next to Connectors and choose Add custom connector.
3. Use fpf-memory as the name and the hosted endpoint as the URL.
4. Connect it, then ask Claude to use fpf_memory for bounded FPF retrieval.

VS Code

Use MCP: Add Server or commit a workspace .vscode/mcp.json file.

1. Open Command Palette > MCP: Add Server for the guided flow, or add this workspace file.
2. Start or restart the server from the MCP code lens and confirm trust when VS Code asks.

{
  "servers": {
    "fpf_memory": {
      "type": "http",
      "url": "https://fpf-memory.server.mastra.cloud/api/mcp/fpf_memory/mcp"
    }
  }
}

Zed

Add fpf-memory as a custom remote context server in Agent Panel settings.

1. Open Agent Panel settings with agent: open settings.
2. Add a custom server using the url-only remote server shape.
3. Check the indicator next to fpf-memory; green means the server is active.

{
  "context_servers": {
    "fpf-memory": {
      "url": "https://fpf-memory.server.mastra.cloud/api/mcp/fpf_memory/mcp"
    }
  }
}

Codex CLI

Register the remote streamable HTTP server with codex mcp add.

1. Run the command, then ask Codex to call get_fpf_index_status before route work.

codex mcp add fpf_memory --url https://fpf-memory.server.mastra.cloud/api/mcp/fpf_memory/mcp

[mcp_servers.fpf_memory]
url = "https://fpf-memory.server.mastra.cloud/api/mcp/fpf_memory/mcp"

Claude Code

Use the HTTP MCP transport and verify status with /mcp inside Claude Code.

1. Run the command, then use /mcp inside Claude Code to check connection status.

claude mcp add --transport http fpf_memory https://fpf-memory.server.mastra.cloud/api/mcp/fpf_memory/mcp

Pi

Install an MCP extension, then configure fpf-memory as a streamable HTTP server.

1. Install pi-mcp-extension or another Pi MCP extension.
2. Add the server to ~/.pi/agent/mcp.json for global use or .pi/mcp.json for one project.
3. Start Pi and use /mcp to check status.

pi install npm:pi-mcp-extension

{
  "mcpServers": {
    "fpf_memory": {
      "transport": "streamable-http",
      "url": "https://fpf-memory.server.mastra.cloud/api/mcp/fpf_memory/mcp",
      "lifecycle": "eager"
    }
  }
}