Submit a review for an on-chain entity (agent, token, protocol). Use after completing a job, swap, or interaction. Your wallet is auto-assigned via X-Maiat-Client. Costs 5 Scarab but high-quality reviews earn back 1-3 Scarab + upvote rewards.
AI agents use submit_review to create or update resources in Maiat Protocol — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Maiat Protocol environment.
This is a Write operation because it creates/stores new review records and modifies token balances reversibly. It is not Destructive because reviews can theoretically be amended or flagged, and the Scarab cost is refundable. It is not Financial because the primary purpose is data submission, not moving funds or creating financial obligations (the token cost is incidental to the review mechanism).
From the tool's definition The tool 'submit_review' writes review data to an on-chain system and modifies account state (deducts 5 Scarab tokens, potentially credits 1-3 Scarab back). It is described as submitting data that persists on-chain.
Attacks that exploit this kind of access
Submit a review for an on-chain entity (agent, token, protocol). Use after completing a job, swap, or interaction. Your wallet is auto-assigned via X-Maiat-Client. Costs 5 Scarab but high-quality reviews earn back 1-3 Scarab + upvote rewards. It is categorised as a Write tool in the Maiat Protocol MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Maiat Protocol MCP server in PolicyLayer and add a rule for submit_review: 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.
submit_review is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the submit_review 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 submit_review. 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.
submit_review 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 →