deep_dive · surveyHelper MCP: Risk & Policy

WHAT IT DOES

What deep_dive does on surveyHelper

AI agents invoke deep_dive to trigger actions in surveyHelper. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why deep_dive needs a policy

This tool executes a compound operation: it expands a citation graph traversal and triggers deep analysis on multiple papers. It's not a simple read/query but an active processing pipeline that runs analysis jobs, likely consuming significant compute and potentially writing results. 'Execute' is most appropriate as it triggers external operations whose effects depend on arguments (depth, K value).

From the tool's definition 'Expand a paper's graph to depth 2 AND deep-analyze its top-K most-influential' — triggers multi-step graph expansion and deep analysis operations

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

deep_dive Rate-limited

deep_dive stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "deep_dive": {
      "limits": [
        {
          "counter": "deep_dive_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about deep_dive

What does the deep_dive tool do? +

Expand a paper's graph to depth 2 AND deep-analyze its top-K most-influential. It is categorised as a Execute tool in the surveyHelper MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on deep_dive? +

Register the surveyHelper MCP server in PolicyLayer and add a rule for deep_dive: 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 surveyHelper. Nothing to install.

What risk level is deep_dive? +

deep_dive is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit deep_dive? +

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

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

deep_dive is provided by the surveyHelper MCP server (rich7420/surveyhelper). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.