// MCP TOOL REFERENCE

GEMINI CLOUD ASSIST TOOLS

4 tools from the Gemini Cloud Assist MCP Server, categorised by risk level.

READ TOOLS

fetch_investigation /** * Fetches Gemini Cloud Assist Investigations. * * This function serves as a versatile entry point for retrieving investigation data. * It c...

WRITE TOOLS

add_observation /** * Adds a new user observation to an existing investigation. * * Prerequisites: * Argument Resolution: Before invoking this tool, you **MUST... 2/5 create_investigation /** * Creates a new Gemini Cloud Assist Investigation. This tool is the primary entry point for initiating any new troubleshooting analysis. * *... 3/5

EXECUTE TOOLS

run_investigation /** * Triggers the Gemini analysis, waits for completion, and returns the final report. * * This is a **synchronous, blocking call** that runs t... 4/5

// FAQ

How many tools does the Gemini Cloud Assist MCP server have? +

The Gemini Cloud Assist MCP server exposes 4 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Gemini Cloud Assist tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Gemini Cloud Assist server.

What risk categories do Gemini Cloud Assist tools fall into? +

Gemini Cloud Assist tools are categorised as Read (1), Write (2), Execute (1). Each category has a recommended default policy.

Enforce policies on Gemini Cloud Assist

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept

github.com/policylayer/intercept →