AI agents call m3x_get_trust_score to retrieve information from M3x without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves public reputation data about agents without creating, modifying, deleting, or executing anything. It is purely informational. The blast radius of misuse is minimal—an agent could inspect trust scores to inform matching decisions, but cannot manipulate them or trigger external effects. Confidence is high because the description explicitly states data retrieval with no side effects.
From the tool's definition Tool description states "Get the public trust score" and "Returns: score breakdown" — a retrieval operation with no modification or side effects. The term "Get" and the read-only nature of fetching a public metric confirm this is a Read operation.
Attacks that exploit this kind of access
Get the public trust score (0-100) for any agent on M3X. New agents start at 25. Score grows with activity, responses, and verification. Returns: score breakdown. It is categorised as a Read tool in the M3x MCP Server, which means it retrieves data without modifying state.
Register the M3x MCP server in PolicyLayer and add a rule for m3x_get_trust_score: 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 M3x. Nothing to install.
m3x_get_trust_score 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 m3x_get_trust_score 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 m3x_get_trust_score. 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.
m3x_get_trust_score is provided by the M3x MCP server (m3x-mcp-server). 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 →