loopsense

LoopSense is an open-source MCP server that closes the feedback loop for AI coding agents — giving them real-time visibility into CI results, deployments, test outcomes, and file system changes.

When an AI agent pushes code, runs tests, or triggers a deployment, LoopSense watches the downstream effects and surfaces them back to the agent. No more blind actions.

Supported sources:

• GitHub Actions CI runs (polling)
• Local processes (stdout/stderr capture, exit codes)
• File system changes (via chokidar)
• HTTP endpoints (polling, with status/body assertions)
• Incoming webhooks (lightweight HTTP server)

• Node.js 18+

npm install -g @loopsense/mcp

Or run directly with npx:

npx @loopsense/mcp

Claude Code (one-liner):

claude mcp add loopsense -e GITHUB_TOKEN=ghp_yourtoken -- npx -y @loopsense/mcp

Or add manually to your claude_desktop_config.json (or equivalent MCP host config):

{
  "mcpServers": {
    "loopsense": {
      "command": "npx",
      "args": ["-y", "@loopsense/mcp"],
      "env": {
        "GITHUB_TOKEN": "ghp_your_token_here"
      }
    }
  }
}

Or if installed globally:

{
  "mcpServers": {
    "loopsense": {
      "command": "loopsense",
      "env": {
        "GITHUB_TOKEN": "ghp_your_token_here"
      }
    }
  }
}

| Variable | Description | |---|---| | GITHUB_TOKEN | GitHub personal access token for CI polling |

Watch a GitHub Actions workflow run. Polls every 30 seconds and emits events on status changes.

{
  "owner": "acme",
  "repo": "api",
  "branch": "main",
  "action_id": "deploy-2024-01"
}

Spawn a local process and capture its output and exit code.

{
  "command": "npm",
  "args": ["test"],
  "cwd": "/path/to/project",
  "action_id": "run-tests"
}

W