Browse memories chronologically with cursor-based pagination.
AI agents call memory_timeline 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.
This tool performs a query/retrieval operation on the memory store without side effects. It allows chronological browsing of existing memories using pagination, which is a classic Read category operation. The absence of any write, delete, execute, or financial keywords, combined with the explicit 'browse' verb (implying inspection only), confirms low severity and high confidence in the Read classification.
From the tool's definition Tool name 'memory_timeline' and description 'Browse memories chronologically with cursor-based pagination' indicate read-only retrieval of stored data with pagination controls. No modification, deletion, execution, or financial operations are involved.
Attacks that exploit this kind of access
Browse memories chronologically with cursor-based pagination. 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_timeline: 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_timeline 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_timeline 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_timeline. 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_timeline 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 →