Prepare and optionally submit a PMCP feedback issue to GitHub.
AI agents use gateway.submit_feedback to create or update resources in PMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PMCP environment.
This tool creates a GitHub issue (or prepares one for submission), which is a reversible write operation — issues can be closed or deleted. The blast radius is medium since a misused agent could spam GitHub issues or expose sensitive information in public issue content, but no irreversible destruction or financial action is involved.
From the tool's definition Prepare and optionally submit a PMCP feedback issue to GitHub
Documented attack patterns abuse exactly the kind of access gateway.submit_feedback gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for gateway.submit_feedback:
{
"version": "1",
"default": "deny",
"tools": {
"gateway.submit_feedback": {
"limits": [
{
"counter": "gateway.submit_feedback_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}gateway.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.
Prepare and optionally submit a PMCP feedback issue to GitHub. It is categorised as a Write tool in the PMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the P MCP server in PolicyLayer and add a rule for gateway.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 PMCP. Nothing to install.
gateway.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 gateway.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 gateway.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.
gateway.submit_feedback is provided by the P MCP server (viperjuice/pmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PMCP, 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.
26 PMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.