Fetch the full content of a specific memory. This is the only tool that returns
AI agents call memory_read 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.
The tool retrieves stored memory content without modifying, deleting, or executing any operations. It is a straightforward query/fetch operation that falls squarely within the Read category. The severity is low because reading memory data poses minimal risk—the tool cannot alter state, execute code, or affect external systems.
From the tool's definition Tool name 'memory_read' and description 'Fetch the full content of a specific memory' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Fetch the full content of a specific memory. This is the only tool that returns. 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_read: 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_read 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_read 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_read. 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_read 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 →