bulk_scan · Pulspeed MCP: Risk & Policy

WHAT IT DOES

What bulk_scan does on Pulspeed

AI agents invoke bulk_scan to trigger actions in Pulspeed. 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 bulk_scan needs a policy

This tool triggers external scanning operations against multiple URLs, which constitutes executing external operations. It initiates active network requests and performance audits against target sites. The blast radius is medium as it could be misused to scan unintended URLs or generate excessive load, but it does not modify or delete data.

From the tool's definition 'Scan multiple URLs at once... runs scans asynchronously and returns job IDs for polling... run sequentially and return all results'

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

bulk_scan Rate-limited

bulk_scan 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": {
    "bulk_scan": {
      "limits": [
        {
          "counter": "bulk_scan_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 Pulspeed, so you can run agents against it safely.

FAQ

Questions about bulk_scan

What does the bulk_scan tool do? +

Scan multiple URLs at once. By default runs scans asynchronously and returns job IDs for polling. Set wait=true to run sequentially and return all results (slower, may take several minutes). It is categorised as a Execute tool in the Pulspeed MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on bulk_scan? +

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

What risk level is bulk_scan? +

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

Can I rate-limit bulk_scan? +

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

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

bulk_scan is provided by the Pulspeed MCP server (pulspeed/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.