search_memory
Search memories using semantic similarity. Use default (detailed=false) for quick exploration or when context is sufficient; it shows previews with IDs and saves input tokens. Use detailed=true only when you need the full text of results. For a specific item, use get_memory(id) after getting the ...
This record as markdown: /tools/0xrelogic-cognio/search-memory.md
What search_memory does on Cognio
AI agents call search_memory to retrieve information from Cognio without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why search_memory is rated Low
This is a query/search operation that retrieves and examines stored data without side effects. The tool returns memory previews or full text based on parameters, but does not create, modify, delete, or execute any operations. Even with detailed=true, it only increases verbosity of read results. Severity is low because unauthorized memory search poses informational risk but limited operational danger in isolation.
From the tool's definition Tool performs 'search memories using semantic similarity' with options for preview or detailed viewing. Description explicitly contrasts with get_memory(id) for retrieval and recommends filtering by project.
Attacks that exploit this kind of access
The rule that runs search_memory safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cognio, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For search_memory, this is the rule to start with:
search_memory is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Cognio, apply this rule, and every search_memory call is checked against it from then on.
Questions about search_memory
Search memories using semantic similarity. Use default (detailed=false) for quick exploration or when context is sufficient; it shows previews with IDs and saves input tokens. Use detailed=true only when you need the full text of results. For a specific item, use get_memory(id) after getting the ID from search. TIP: Filter by project to avoid mixing contexts from different workspaces. It is categorised as a Read tool in the Cognio MCP Server, which means it retrieves data without modifying state.
Register the Cognio MCP server in PolicyLayer and add a rule for search_memory: 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 Cognio. Nothing to install.
search_memory 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 search_memory 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 search_memory. 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.
search_memory is provided by the Cognio MCP server (0xrelogic/cognio). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cognio, and thousands of servers like it.
This server
Across the catalogue