AI agents call get_colors to retrieve information from Gcalendar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static color data without modifying, executing, or destroying anything. It is informational only and poses minimal risk if misused by an AI agent.
From the tool's definition Tool name 'get_colors' and description 'Get available colors' indicate a retrieval operation with no side effects. This is a simple query to fetch color metadata available in Google Calendar.
Attacks that exploit this kind of access
Get available colors. It is categorised as a Read tool in the Gcalendar MCP Server, which means it retrieves data without modifying state.
Register the Gcalendar MCP server in PolicyLayer and add a rule for get_colors: 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 Gcalendar. Nothing to install.
get_colors 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 get_colors 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 get_colors. 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.
get_colors is provided by the Gcalendar MCP server (sandeepmallareddy/gcalendar-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 →