Look up a brief by target slug. D-13 decision tree: staleness dominates; age is
AI agents call get_brief to retrieve information from Vault Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval operation that queries and returns a brief based on a target slug identifier. It has no side effects, does not create or modify data, and does not execute commands. The 'look up' language confirms a passive read operation. The incomplete description suggests caching/freshness considerations but does not change the fundamental read-only nature of the tool.
From the tool's definition Tool name 'get_brief' with verb 'Look up' and action 'retrieve' a brief by slug. No modification, deletion, or execution indicated.
Attacks that exploit this kind of access
Look up a brief by target slug. D-13 decision tree: staleness dominates; age is. It is categorised as a Read tool in the Vault Memory MCP Server, which means it retrieves data without modifying state.
Register the Vault Memory MCP server in PolicyLayer and add a rule for get_brief: 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 Vault Memory. Nothing to install.
get_brief 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 get_brief 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 get_brief. 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.
get_brief is provided by the Vault Memory MCP server (owrede/vault-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 →