AI agents call random-pokemon to retrieve information from Poke-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves Pokémon information from PokeAPI and returns a single random result. It performs a query operation that fetches existing data without creating, modifying, deleting, or executing any code. The action is read-only with no side effects, placing it firmly in the Read category. Severity is low because misuse poses no risk to data integrity or system state.
From the tool's definition Tool name 'random-pokemon' and description 'Get a random Pokémon' indicate data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access random-pokemon gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Poke-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for random-pokemon:
{
"version": "1",
"default": "deny",
"tools": {
"random-pokemon": {}
}
}random-pokemon is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a random Pokémon. It is categorised as a Read tool in the Poke-MCP MCP Server, which means it retrieves data without modifying state.
Register the Poke- MCP server in PolicyLayer and add a rule for random-pokemon: 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 Poke-MCP. Nothing to install.
random-pokemon 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 random-pokemon 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 random-pokemon. 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.
random-pokemon is provided by the Poke- MCP server (naveenbandarage/poke-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Poke-MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Poke-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.