spike_approve_adr · Hedgehog MCP: Risk & Policy

WHAT IT DOES

What spike_approve_adr does on Hedgehog

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

WHY IT NEEDS A POLICY

Why spike_approve_adr needs a policy

This tool creates or modifies data in a reversible way by approving and completing a spike record. It aligns with Write category (creates/modifies data reversibly) rather than Destructive since approval and completion statuses can typically be changed or reverted in workflow systems.

From the tool's definition Tool marks spike as 'completed' and 'approves' the ADR, which modifies the state of a spike investigation record. The description indicates a state-changing operation rather than deletion or financial impact.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

spike_approve_adr Rate-limited

spike_approve_adr 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": {
    "spike_approve_adr": {
      "limits": [
        {
          "counter": "spike_approve_adr_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 Hedgehog, so you can run agents against it safely.

FAQ

Questions about spike_approve_adr

What does the spike_approve_adr tool do? +

Approve the ADR and mark the spike as completed. It is categorised as a Write tool in the Hedgehog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on spike_approve_adr? +

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

What risk level is spike_approve_adr? +

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

Can I rate-limit spike_approve_adr? +

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

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

spike_approve_adr is provided by the Hedgehog MCP server (jpalmerr/hedgehog). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.