What it does

Queries Cloud Logging and Monitoring so an agent can answer 'what changed at 14:02' with actual log lines instead of a hypothesis. On an incident this is the difference between a plausible story and a real one. Expect to iterate on the query — the first filter the model writes is usually too broad.

Install

Terminal

npx -y @google-cloud/observability-mcp

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "gcp-observability": {
      "command": "npx",
      "args": [
        "-y",
        "@google-cloud/observability-mcp"
      ]
    }
  }
}

Use it for

Debugging an incident by querying logs and metrics in plain language

Skip it if

Replacing dashboards for routine monitoring

When to use it

Reach for this when the task needs gcp inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

Cloud Observability MCP