AI agents call decision_brief to retrieve information from QuReDec without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve decision briefs based on naming convention and sibling tool patterns. No description is available, which reduces confidence, but the server's documented purpose (providing briefs with citations and sources) and sibling Read operations (get_brief_status, list_recent_briefs) indicate this is likely a data retrieval operation with no side effects.
From the tool's definition Tool name is 'decision_brief' with no description provided. Context from sibling tools ('get_brief_status', 'list_recent_briefs') and server description ('Evidence-backed decision briefs with citations') suggests this retrieves or queries decision brief data.
Attacks that exploit this kind of access
decision_brief. It is categorised as a Read tool in the QuReDec MCP Server, which means it retrieves data without modifying state.
Register the QuReDec MCP server in PolicyLayer and add a rule for decision_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 QuReDec. Nothing to install.
decision_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 decision_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 decision_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.
decision_brief is provided by the QuReDec MCP server (Advanced-Binary-Operations/QuReDec_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 →