export_conversation_summary · Ai Analyst MCP: Risk & Policy

WHAT IT DOES

What export_conversation_summary does on Ai Analyst

AI agents use export_conversation_summary to create or update resources in Ai Analyst — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ai Analyst environment.

WHY IT NEEDS A POLICY

Why export_conversation_summary needs a policy

This tool creates/generates a new data artifact (a summary document) from existing conversation context. It does not merely read and return unmodified data, nor does it execute arbitrary queries or delete data. The act of exporting and generating a summary represents data creation/composition.

From the tool's definition Tool name 'export_conversation_summary' combined with description 'Export a comprehensive summary' indicates the tool creates and outputs a new artifact (summary document/file) based on conversation state, which is a write operation that creates data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

export_conversation_summary Rate-limited

export_conversation_summary 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "export_conversation_summary": {
      "limits": [
        {
          "counter": "export_conversation_summary_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Ai Analyst, so you can run agents against it safely.

FAQ

Questions about export_conversation_summary

What does the export_conversation_summary tool do? +

Export a comprehensive summary of the current conversation and analysis. It is categorised as a Write tool in the Ai Analyst MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on export_conversation_summary? +

Register the Ai Analyst MCP server in PolicyLayer and add a rule for export_conversation_summary: 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 Ai Analyst. Nothing to install.

What risk level is export_conversation_summary? +

export_conversation_summary is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit export_conversation_summary? +

Yes. Add a rate_limit block to the export_conversation_summary 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 export_conversation_summary completely? +

Set action: deny in the PolicyLayer policy for export_conversation_summary. 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 export_conversation_summary? +

export_conversation_summary is provided by the Ai Analyst MCP server (sbdk-dev/local-ai-analyst). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.