// SCAN REPORT

GCP MCP

9 tools. 2 can modify or destroy data without limits.

2 write tools that can modify data. Rate limits recommended.

Last updated: 4 Jul 2026

2 can modify or destroy data

7 read-only

9 tools total

Community server · catalogue entry verified 04/07/2026

How to control GCP MCP ↓

TOOL MAP

What GCP MCP exposes to your agents

Read (7) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous GCP MCP tools

Execute · Critical run-gcp-code The tool executes code in a GCP environment with implicit access to multiple high-impact services (compute, storage, databases). Write · Medium select-project While the tool does not create, modify, or delete actual GCP resources, it alters the execution context for subsequent interactions.

2 of GCP MCP's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control GCP MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and GCP MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "select-project": {
    "limits": [
      {
        "counter": "select-project_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get-billing-budget": {
    "limits": [
      {
        "counter": "get-billing-budget_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register GCP MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON GCP →

Instant setup, no code required.

FULL CATALOGUE

All 9 GCP MCP tools

EXECUTE 1 tools

Execute run-gcp-code Run GCP code

WRITE 1 tools

Write select-project Selects GCP project to use for subsequent interactions

READ 7 tools

Read get-billing-budget Get billing budgets for the current project Read get-billing-info Get billing information for the current project Read get-cost-forecast Get cost forecast for the current project Read get-logs Get Cloud Logging entries for the current project Read list-gke-clusters List all GKE clusters in the current project Read list-projects List all GCP projects accessible with current credentials Read list-sql-instances List all Cloud SQL instances in the current project

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about GCP MCP

How do I prevent bulk modifications through GCP MCP? +

The GCP MCP server has 1 write tools including select-project. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach GCP MCP.

How many tools does the GCP MCP server expose? +

9 tools across 3 categories: Execute, Read, Write. 7 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on GCP MCP? +

Register the GCP MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every GCP MCP tool call.

Deterministic rules across all 9 GCP MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON GCP →

Instant setup, no code required.

9 GCP MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.