Look up an active entry by its canonical topic_key (feature slug, or
AI agents call resolve_topic_key to retrieve information from Domain memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only lookup of knowledge entries by a canonical key identifier. It retrieves existing domain knowledge without creating, modifying, or deleting data. Severity is low because misuse at most exposes internal project documentation.
From the tool's definition "Look up an active entry by its canonical topic_key" — this is a lookup/retrieval operation with no indication of side effects
Attacks that exploit this kind of access
Look up an active entry by its canonical topic_key (feature slug, or. It is categorised as a Read tool in the Domain memory MCP Server, which means it retrieves data without modifying state.
Register the Domain memory MCP server in PolicyLayer and add a rule for resolve_topic_key: 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 Domain memory. Nothing to install.
resolve_topic_key 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 resolve_topic_key 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 resolve_topic_key. 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.
resolve_topic_key is provided by the Domain memory MCP server (mashware/domain-memory). 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 →