Cortex RMCP MCP Server

by jmagarai.dinglebear/cortex-rmcpv3.9.1

Rust MCP server for homelab logs, syslog, Docker logs, FTS search, and AI transcript correlation.

3Dockerstdioremoteofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Active8d ago

Install Cortex RMCP MCP server

claude mcp add cortex-r -e CORTEX_RECEIVER_HOST='<cortex-receiver-host>' -e CORTEX_TOKEN='<cortex-token>' -- docker run -i --rm -e CORTEX_RECEIVER_HOST -e CORTEX_TOKEN ghcr.io/jmagar/cortex:v3.9.0

{
  "mcpServers": {
    "cortex-r": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "CORTEX_RECEIVER_HOST",
        "-e",
        "CORTEX_TOKEN",
        "ghcr.io/jmagar/cortex:v3.9.0"
      ],
      "env": {
        "CORTEX_RECEIVER_HOST": "<cortex-receiver-host>",
        "CORTEX_TOKEN": "<cortex-token>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "cortex-r": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "CORTEX_RECEIVER_HOST",
        "-e",
        "CORTEX_TOKEN",
        "ghcr.io/jmagar/cortex:v3.9.0"
      ],
      "env": {
        "CORTEX_RECEIVER_HOST": "<cortex-receiver-host>",
        "CORTEX_TOKEN": "<cortex-token>"
      }
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "cortex-r": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "CORTEX_RECEIVER_HOST",
        "-e",
        "CORTEX_TOKEN",
        "ghcr.io/jmagar/cortex:v3.9.0"
      ],
      "env": {
        "CORTEX_RECEIVER_HOST": "<cortex-receiver-host>",
        "CORTEX_TOKEN": "<cortex-token>"
      }
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "cortex-r": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "CORTEX_RECEIVER_HOST",
        "-e",
        "CORTEX_TOKEN",
        "ghcr.io/jmagar/cortex:v3.9.0"
      ],
      "env": {
        "CORTEX_RECEIVER_HOST": "<cortex-receiver-host>",
        "CORTEX_TOKEN": "<cortex-token>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
CORTEX_RECEIVER_HOST	yes	—	Hostname or IP of the syslog listener.
CORTEX_TOKEN	—	yes	Bearer token for MCP endpoint authentication.
CORTEX_RECEIVER_PORT	—	—	Syslog listener port (UDP + TCP). Default: 1514.

Remote endpoints

streamable-httphttps://cortex.tootie.tv/mcp

Freshness

Active — last maintenance signal 8d ago. The newest of the signals below sets the band.

Last commit (default branch)
2026-10-01 · 8d ago · GitHub
Latest release
2026-10-01 · 8d ago · GitHub · v3.18.1
Package published
no data · npm/PyPI
Registry entry updated
2026-07-12 · 3mo ago · official registry · v3.9.1

FAQ

›How do I install the Cortex RMCP MCP server in Claude Code?

Run: claude mcp add cortex-r -e CORTEX_RECEIVER_HOST='<cortex-receiver-host>' -e CORTEX_TOKEN='<cortex-token>' -- docker run -i --rm -e CORTEX_RECEIVER_HOST -e CORTEX_TOKEN ghcr.io/jmagar/cortex:v3.9.0. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does Cortex RMCP require an API key?

Yes. It expects CORTEX_RECEIVER_HOST, CORTEX_TOKEN, of which 1 is a secret.

›Can I use Cortex RMCP as a remote (hosted) MCP server?

Yes — it offers both a hosted endpoint and a local stdio package.

›Is Cortex RMCP in the official MCP registry?

Yes, as ai.dinglebear/cortex-rmcp.