Semantic search over verified memory. Returns ranked assertions with their active receipts.
AI agents call memory_query to retrieve information from Verifiedstate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
memory_query retrieves and searches existing verified memory assertions without side effects. It does not create, modify, delete, or execute external operations. The read-only nature is unambiguous, making this a straightforward Read classification.
From the tool's definition Tool performs 'Semantic search over verified memory' and 'Returns ranked assertions' — pure retrieval with no modification, creation, or destruction of data. The description explicitly frames this as a query operation.
Attacks that exploit this kind of access
Semantic search over verified memory. Returns ranked assertions with their active receipts. It is categorised as a Read tool in the Verifiedstate MCP Server, which means it retrieves data without modifying state.
Register the Verifiedstate MCP server in PolicyLayer and add a rule for memory_query: 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 Verifiedstate. Nothing to install.
memory_query 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_query 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_query. 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_query is provided by the Verifiedstate MCP server (verifiedstate/verifiedstate-mcp). 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 →