AI agents use submit_feedback to create or update resources in Metatron — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Metatron environment.
Without a description, classification relies on the name and context. 'submit' indicates a write operation that creates or records feedback as new data within the system. This is reversible (feedback can be updated/removed) rather than destructive.
From the tool's definition Tool name 'submit_feedback' combined with 'submit_candidate_decision' sibling tool suggests this writes structured data (feedback/decisions) into Metatron's decision store, creating or modifying the codebase priors database.
Documented attack patterns abuse exactly the kind of access submit_feedback gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Metatron, and nothing reaches the server without passing your rules. This is the rule we recommend for submit_feedback:
{
"version": "1",
"default": "deny",
"tools": {
"submit_feedback": {
"limits": [
{
"counter": "submit_feedback_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}submit_feedback stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
submit_feedback. It is categorised as a Write tool in the Metatron MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Metatron MCP server in PolicyLayer and add a rule for submit_feedback: 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 Metatron. Nothing to install.
submit_feedback 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_feedback 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_feedback. 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_feedback is provided by the Metatron MCP server (kerbelp/metatron). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Metatron, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Metatron tools catalogued and risk-classified — across an index of 43,000+ MCP servers.