Low Risk

crow_discover

Discover available actions and their parameter schemas. No args = list categories. category = list actions. category + action = full schema.

How to control crow_discover ↓

What crow_discover does on Crow

AI agents call crow_discover to retrieve information from Crow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why crow_discover needs a policy

The tool is purely informational, querying and returning metadata about available actions and their schemas. It does not execute any actions, modify data, delete anything, or trigger external operations. This is a straightforward Read operation with minimal risk if misused—an AI agent can only discover what actions exist, not invoke them.

From the tool's definition Tool description states it "Discover[s] available actions and their parameter schemas" with "No args = list categories", "category = list actions", and "category + action = full schema".

Documented attack patterns abuse exactly the kind of access crow_discover gives an agent:

How to control crow_discover

PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for crow_discover:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "crow_discover": {}
  }
}

crow_discover is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Crow — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about crow_discover

What does the crow_discover tool do? +

Discover available actions and their parameter schemas. No args = list categories. category = list actions. category + action = full schema. It is categorised as a Read tool in the Crow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on crow_discover? +

Register the Crow MCP server in PolicyLayer and add a rule for crow_discover: 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 Crow. Nothing to install.

What risk level is crow_discover? +

crow_discover is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit crow_discover? +

Yes. Add a rate_limit block to the crow_discover 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.

How do I block crow_discover completely? +

Set action: deny in the PolicyLayer policy for crow_discover. 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.

What MCP server provides crow_discover? +

crow_discover is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Crow tool call.

Start from Crow, 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.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.