Get community reputation for an ACP agent — reviews, average rating, sentiment analysis, and market consensus. Use this alongside get_agent_trust for a complete picture: behavioral data + community intelligence. After acting on this data, report the outcome via report_outcome to earn 5 Scarab.
AI agents call get_agent_reputation 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 returns reputation metrics for agents in the trust infrastructure. It performs no side effects, creates no data modifications, executes no code, and involves no financial transactions. The mention of earning Scarab tokens through report_outcome is a separate incentive mechanism, not part of this tool's function.
From the tool's definition Tool name and description indicate data retrieval only: 'Get community reputation', 'reviews, average rating, sentiment analysis, and market consensus' are all read operations returning aggregated public data.
Attacks that exploit this kind of access
Get community reputation for an ACP agent — reviews, average rating, sentiment analysis, and market consensus. Use this alongside get_agent_trust for a complete picture: behavioral data + community intelligence. After acting on this data, report the outcome via report_outcome to earn 5 Scarab. 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_reputation: 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_reputation 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_reputation 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_reputation. 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_reputation 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.
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 →