deep-research · Vectorize MCP: Risk & Policy

WHAT IT DOES

What deep-research does on Vectorize

AI agents invoke deep-research to trigger actions in Vectorize. 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-research needs a policy

The tool 'deep-research' generates deep research by running a configured pipeline. This implies executing a multi-step process on external infrastructure (Vectorize.io pipelines), which may involve querying external sources, processing data, and producing results. This goes beyond a simple read/query operation — it triggers an external pipeline execution.

From the tool's definition "Generate a deep research on the configured pipeline" — triggers a pipeline execution process

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

deep-research Rate-limited

deep-research 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-research": {
      "limits": [
        {
          "counter": "deep-research_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 Vectorize, so you can run agents against it safely.

FAQ

Questions about deep-research

What does the deep-research tool do? +

Generate a deep research on the configured pipeline. It is categorised as a Execute tool in the Vectorize 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-research? +

Register the Vectorize MCP server in PolicyLayer and add a rule for deep-research: 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 Vectorize. Nothing to install.

What risk level is deep-research? +

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

Can I rate-limit deep-research? +

Yes. Add a rate_limit block to the deep-research 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-research completely? +

Set action: deny in the PolicyLayer policy for deep-research. 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-research? +

deep-research is provided by the Vectorize MCP server (@vectorize-io/vectorize-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.