AI agents call memory_browse to retrieve information from Exocortex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing memories with filtering options but does not create, modify, delete, or execute any operations. It is a pure read operation on a memory database with no side effects beyond data retrieval.
From the tool's definition Tool description states 'Browse memories without semantic search. Filter by tags, content type, or date range. Returns most recent first.' The verb 'browse' and 'filter' indicate data retrieval operations with no modification or deletion capability.
Attacks that exploit this kind of access
Browse memories without semantic search. Filter by tags, content type, or date range. Returns most recent first. It is categorised as a Read tool in the Exocortex MCP Server, which means it retrieves data without modifying state.
Register the Exocortex MCP server in PolicyLayer and add a rule for memory_browse: 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 Exocortex. Nothing to install.
memory_browse 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_browse 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_browse. 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_browse is provided by the Exocortex MCP server (shawnhack/exocortex). 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 →