AI agents call list-projects to retrieve information from GCP MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about GCP projects without modifying, executing, or deleting anything. The blast radius is limited to information disclosure about available projects. While listing projects could reveal organizational structure, this is a fundamental read operation that is typically low-risk unless the project list itself is considered highly sensitive.
From the tool's definition Tool name 'list-projects' and description 'List all GCP projects accessible with current credentials' indicate a pure read/query operation with no side effects.
Attacks that exploit this kind of access
List all GCP projects accessible with current credentials. It is categorised as a Read tool in the GCP MCP MCP Server, which means it retrieves data without modifying state.
Register the GCP MCP server in PolicyLayer and add a rule for list-projects: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches GCP MCP. Nothing to install.
list-projects is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list-projects rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list-projects. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list-projects is provided by the GCP MCP server (radiumgu/gcp-ops-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →