Low Risk

crow_recall_by_context

Retrieve memories relevant to a given context. Uses full-text search across content, context, and tags. Memories tagged source=

How to control crow_recall_by_context ↓

What crow_recall_by_context does on Crow

AI agents call crow_recall_by_context 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_recall_by_context needs a policy

This tool performs read-only operations on stored memories using search functionality. It retrieves data based on context matching without creating, modifying, deleting, or executing any actions. The blast radius of misuse is minimal—an adversary could only discover what memories exist, not alter system state or cause irreversible harm.

From the tool's definition Tool description states 'Retrieve memories' and 'full-text search across content, context, and tags' — these are query/retrieval operations with no modification, deletion, or execution capabilities.

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

How to control crow_recall_by_context

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_recall_by_context:

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

crow_recall_by_context 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_recall_by_context

What does the crow_recall_by_context tool do? +

Retrieve memories relevant to a given context. Uses full-text search across content, context, and tags. Memories tagged source=. 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_recall_by_context? +

Register the Crow MCP server in PolicyLayer and add a rule for crow_recall_by_context: 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_recall_by_context? +

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

Can I rate-limit crow_recall_by_context? +

Yes. Add a rate_limit block to the crow_recall_by_context 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_recall_by_context completely? +

Set action: deny in the PolicyLayer policy for crow_recall_by_context. 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_recall_by_context? +

crow_recall_by_context 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.