Retrieve memories and causal chains most relevant to query and
AI agents call retrieve to retrieve information from State Trace 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 existing data from the working memory system without modifying, deleting, or executing operations. It is purely informational in nature, accessing causal memory chains relevant to a query. The 'retrieve' operation is a standard read operation with minimal blast radius—an agent cannot misuse it to cause harm beyond possibly accessing internal state information.
From the tool's definition Tool name 'retrieve' combined with description indicating it 'Retrieve[s] memories and causal chains most relevant to `query`' describes a read-only query operation with no side effects.
Attacks that exploit this kind of access
Retrieve memories and causal chains most relevant to query and. It is categorised as a Read tool in the State Trace MCP Server, which means it retrieves data without modifying state.
Register the State Trace MCP server in PolicyLayer and add a rule for retrieve: 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 State Trace. Nothing to install.
retrieve 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 retrieve 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 retrieve. 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.
retrieve is provided by the State Trace MCP server (agent-pattern-labs/state-trace). 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 →