Get all available categories for Chuck Norris jokes
AI agents call get-chuck-categories to retrieve information from Microsoft Copilot Studio ❤️ MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries a list of available joke categories. It performs a simple read operation without modifying, executing code, deleting data, or affecting any financial systems. The blast radius of misuse is minimal—an AI agent could only retrieve category data.
From the tool's definition Tool name 'get-chuck-categories' and description 'Get all available categories for Chuck Norris jokes' indicate a retrieval operation with no side effects or data modification.
Attacks that exploit this kind of access
Get all available categories for Chuck Norris jokes. It is categorised as a Read tool in the Microsoft Copilot Studio ❤️ MCP MCP Server, which means it retrieves data without modifying state.
Register the Microsoft Copilot Studio ❤️ MCP server in PolicyLayer and add a rule for get-chuck-categories: 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 Microsoft Copilot Studio ❤️ MCP. Nothing to install.
get-chuck-categories 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-chuck-categories 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-chuck-categories. 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-chuck-categories is provided by the Microsoft Copilot Studio ❤️ MCP server (xiruatms/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 →