Get the behavioral trust score for an AI agent wallet address. Returns a 0-100 score, verdict (proceed/caution/avoid), and breakdown based on Virtuals ACP job history. Use this before transacting with or delegating to any ACP agent.
AI agents call get_agent_trust to retrieve information from Maiat Protocol 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 reputation data for an agent wallet address. It performs a read-only lookup operation that returns a trust score and assessment. There is no data creation, modification, deletion, code execution, or financial transaction. The verb 'Get' and the stated return of information confirms this is a pure Read operation.
From the tool's definition Tool name 'get_agent_trust' and description 'Get the behavioral trust score' and 'Returns a 0-100 score, verdict, and breakdown' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get the behavioral trust score for an AI agent wallet address. Returns a 0-100 score, verdict (proceed/caution/avoid), and breakdown based on Virtuals ACP job history. Use this before transacting with or delegating to any ACP agent. It is categorised as a Read tool in the Maiat Protocol MCP Server, which means it retrieves data without modifying state.
Register the Maiat Protocol MCP server in PolicyLayer and add a rule for get_agent_trust: 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 Maiat Protocol. Nothing to install.
get_agent_trust 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_agent_trust 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_agent_trust. 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_agent_trust is provided by the Maiat Protocol MCP server (jhinresh/maiat-protocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_agent_trust is one line of Maiat Protocol's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →