search_feedback · Slack Feedback MCP Server MCP

WHAT IT DOES

What search_feedback does on Slack Feedback MCP Server

AI agents call search_feedback to retrieve information from Slack Feedback MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

WHY IT NEEDS A POLICY

Why search_feedback needs a policy

This tool retrieves and searches existing feedback data without modifying, deleting, or executing external operations. Search operations are read-only with no side effects. The incomplete description ('Search Bryan') slightly reduces confidence, but the server's stated capability of 'searching feedback by keywords' and the pattern of sibling read tools support the Read classification.

From the tool's definition Tool description indicates 'searching feedback by keywords' from the product feedback collection system. The incomplete description 'Search Bryan' appears to be a truncation, but context from sibling tools (get_stakeholder_feedback, get_thread_context) and…

Attacks that exploit this kind of access

Questions about search_feedback

What does the search_feedback tool do? +

Search Bryan\. It is categorised as a Read tool in the Slack Feedback MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_feedback? +

Register the Slack Feedback MCP Server MCP server in PolicyLayer and add a rule for search_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 Slack Feedback MCP Server. Nothing to install.

What risk level is search_feedback? +

search_feedback is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_feedback? +

Yes. Add a rate_limit block to the search_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.

How do I block search_feedback completely? +

Set action: deny in the PolicyLayer policy for search_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.

What MCP server provides search_feedback? +

search_feedback is provided by the Slack Feedback MCP Server MCP server (nmontoro44/slack-feedback-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.