Find semantically related memories via embedding similarity. Returns titles only.
AI agents call memory_related to retrieve information from Claude Crowed without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
memory_related performs a semantic search query against stored memories and returns read-only results (titles). There are no side effects, data modifications, destructive operations, or external executions. This is a standard Read operation analogous to search or query functionality.
From the tool's definition Tool description states it 'Find[s] semantically related memories' and 'Returns titles only.' This is a retrieval operation with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Find semantically related memories via embedding similarity. Returns titles only. It is categorised as a Read tool in the Claude Crowed MCP Server, which means it retrieves data without modifying state.
Register the Claude Crowed MCP server in PolicyLayer and add a rule for memory_related: 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 Claude Crowed. Nothing to install.
memory_related 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 memory_related 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 memory_related. 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.
memory_related is provided by the Claude Crowed MCP server (thenewjavaman/claude-crowed). 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 →