Report a data quality issue or agent intent gap with a DataNexus tool response. Read-only call. Records feedback for human and AI review. tool_id: Tool identifier e.g. T04 or security_fetch_cve_detail. Required. query_hash: Hash from the response being reported. Required. Found in the query_hash ...
Part of the DataNexus MCP server.
Free to start. No card required.
AI agents call report_feedback to retrieve information from DataNexus MCP without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though report_feedback only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"report_feedback": {}
}
}See the full DataNexus MCP policy for all 55 tools.
These attack patterns abuse exactly the kind of access report_feedback gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Report a data quality issue or agent intent gap with a DataNexus tool response. Read-only call. Records feedback for human and AI review. tool_id: Tool identifier e.g. T04 or security_fetch_cve_detail. Required. query_hash: Hash from the response being reported. Required. Found in the query_hash field of any response. signal: One of incorrect_data, missing_field, stale_data, not_useful, wrong_entity, or data_quality. Required for user_feedback. feedback_type: user_feedback (default) or agent_gap. Use agent_gap when the tool returned a valid 200 response but the result did not serve the user's actual need. intended_query: What the agent was trying to accomplish — used when feedback_type=agent_gap. Optional. Max 256 chars. gap_description: What was missing or wrong in the result — used when feedback_type=agent_gap. Optional. Max 256 chars. comment: Description of the issue. Optional. Max 500 characters. missing_fields: List of field names that are absent or wrong. Optional. Call this after receiving a result that appears wrong, outdated, or incomplete. Do not call this to report network errors — those resolve on retry. If this tool response did not serve the user's need, call report_feedback with feedback_type="agent_gap", tool_id="{this_tool_id}", intended_query="{what the user needed}", gap_description="{what was missing or wrong in the result}".. It is categorised as a Read tool in the DataNexus MCP MCP Server, which means it retrieves data without modifying state.
Register the DataNexus MCP server in PolicyLayer and add a rule for report_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 DataNexus MCP. Nothing to install.
report_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 report_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 report_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.
report_feedback is provided by the DataNexus MCP server (dev-7bd0/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 55 DataNexus MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.