Retrieve memories using composite scoring.
AI agents call recall to retrieve information from ThoughtMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and queries stored memory data. It performs a search/retrieval operation with composite scoring logic but does not create, modify, delete, or execute external code. The action is non-destructive and non-reversible reads fit the Read category. Severity is low because memory retrieval poses minimal risk even if misused by an agent—it cannot alter state, trigger external operations, or cause data loss.
From the tool's definition Tool description states 'Retrieve memories using composite scoring' — the verb 'retrieve' indicates data retrieval with no side effects. No modification, deletion, or execution implied.
Attacks that exploit this kind of access
Retrieve memories using composite scoring. It is categorised as a Read tool in the ThoughtMCP MCP Server, which means it retrieves data without modifying state.
Register the Thought 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 ThoughtMCP. 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 Thought MCP server (keyurgolani/thoughtmcp). 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 →