Capture feedback directly from PM
AI agents call capture_raw_feedback to retrieve information from ProduckAI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool's primary function is to ingest feedback input, which is a read/retrieval operation. It gathers information from a PM without modifying, executing external code, deleting data, or triggering financial transactions. The scope is limited to data collection for the ProduckAI system's feedback pipeline.
From the tool's definition The tool 'capture_raw_feedback' with description 'Capture feedback directly from PM' retrieves or collects feedback data from a product manager.
Attacks that exploit this kind of access
Capture feedback directly from PM. It is categorised as a Read tool in the ProduckAI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ProduckAI MCP Server MCP server in PolicyLayer and add a rule for capture_raw_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 ProduckAI MCP Server. Nothing to install.
capture_raw_feedback 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 capture_raw_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 capture_raw_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.
capture_raw_feedback is provided by the ProduckAI MCP Server MCP server (rohitsaraff33-bit/produckai-mcp-server). 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 →