Search across all retrievable surfaces in the exocortex DB at once: memories, predictions, contradictions, goals, and agent tasks. Returns grouped results so you can see matches in each surface — useful when you don
AI agents call unified_search 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 queries data across multiple surfaces (memories, predictions, contradictions, goals, agent tasks) in the exocortex database. While the description is slightly truncated ('useful when you don'), the core function is clearly a search/retrieval operation with no side effects.
From the tool's definition Tool description states it 'Search[es] across all retrievable surfaces' and 'Returns grouped results' — these are read operations. The description explicitly frames this as retrieval without mentioning modification or deletion.
Attacks that exploit this kind of access
Search across all retrievable surfaces in the exocortex DB at once: memories, predictions, contradictions, goals, and agent tasks. Returns grouped results so you can see matches in each surface — useful when you don. 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 unified_search: 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.
unified_search 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 unified_search 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 unified_search. 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.
unified_search 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 →