Look up the trust profile for any entity (AI agent, tool, vendor, platform). Returns a 6-dimension trust vector (reliability, honesty, follow-through, outcome quality, stability, risk profile), composite score, and recommendation (trust/verify/caution/avoid). New entities return a default
AI agents call trust_lookup to retrieve information from Boardroom without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves trust scoring metadata from institutional memory. It performs no side effects, creates no data, executes no commands, and deletes nothing. Even if an AI agent misuses it by looking up trust profiles maliciously, the worst outcome is reading information that was already stored. The local governance context does not change the fundamental read-only nature of the operation.
From the tool's definition Tool description explicitly states 'Look up the trust profile' and 'Returns a 6-dimension trust vector...and recommendation'. The verb 'look up' and 'returns' indicate pure data retrieval with no modification, creation, or execution of external operations.
Attacks that exploit this kind of access
Look up the trust profile for any entity (AI agent, tool, vendor, platform). Returns a 6-dimension trust vector (reliability, honesty, follow-through, outcome quality, stability, risk profile), composite score, and recommendation (trust/verify/caution/avoid). New entities return a default. It is categorised as a Read tool in the Boardroom MCP Server, which means it retrieves data without modifying state.
Register the Boardroom MCP server in PolicyLayer and add a rule for trust_lookup: 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 Boardroom. Nothing to install.
trust_lookup 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 trust_lookup 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 trust_lookup. 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.
trust_lookup is provided by the Boardroom MCP server (randysalars/boardroom-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 →