add_coaching_feedback
AI agents use add_coaching_feedback to create or update resources in MCPacer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCPacer environment.
The 'add_' prefix indicates data creation or modification. This is reversible (feedback can be updated or deleted), so it is classified as Write rather than Execute or Destructive. Severity is medium because misuse could spam or pollute coaching feedback records, affecting user experience and trust, but the impact is bounded to metadata/coaching notes rather than destructive data loss or financial operations.
From the tool's definition Tool name 'add_coaching_feedback' indicates creation/modification of feedback data. The naming pattern mirrors sibling tools like 'add_plan_comment', 'add_plan_run', and 'add_run_note', all of which are Write operations that create or modify data.
Documented attack patterns abuse exactly the kind of access add_coaching_feedback gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCPacer, and nothing reaches the server without passing your rules. This is the rule we recommend for add_coaching_feedback:
{
"version": "1",
"default": "deny",
"tools": {
"add_coaching_feedback": {
"limits": [
{
"counter": "add_coaching_feedback_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_coaching_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.
add_coaching_feedback. It is categorised as a Write tool in the MCPacer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCPacer MCP server in PolicyLayer and add a rule for add_coaching_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 MCPacer. Nothing to install.
add_coaching_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 add_coaching_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 add_coaching_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.
add_coaching_feedback is provided by the MCPacer MCP server (wernerpe/mcpacer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCPacer, 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.
32 MCPacer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.