AI agents call recall to retrieve information from Dbrain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or searches existing memory data with no side effects—no creation, modification, deletion, or execution of external operations. It is a pure read operation on the persistent memory store. The low severity reflects that misuse would only expose information already known to the system, with no destructive or financial implications.
From the tool's definition Tool name 'recall' and description 'Search your memory' indicate data retrieval without modification. The instruction to use it 'BEFORE answering any question' confirms it performs lookups/queries against stored facts and conversation history.
Attacks that exploit this kind of access
Search your memory. Use this BEFORE answering any question about the user, their projects, preferences, or past conversations. If you. It is categorised as a Read tool in the Dbrain MCP Server, which means it retrieves data without modifying state.
Register the Dbrain MCP server in PolicyLayer and add a rule for recall: 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 Dbrain. Nothing to install.
recall 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 recall 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 recall. 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.
recall is provided by the Dbrain MCP server (ivncmp/dbrain). 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 →