spike_mark_dead_end · Hedgehog MCP: Risk & Policy

WHAT IT DOES

What spike_mark_dead_end does on Hedgehog

AI agents use spike_mark_dead_end 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_mark_dead_end needs a policy

The tool modifies investigation metadata (marking a branch as dead-end) rather than deleting it (which would be spike_delete), making it a Write operation. Severity is medium because misuse could leave misleading investigation records or block legitimate exploration paths, but effects are reversible and localized to investigation tracking state without external system impact.

From the tool's definition Tool name 'spike_mark_dead_end' suggests marking or updating the status of a spike investigation branch as a dead end, which modifies state within the spike management system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

spike_mark_dead_end Rate-limited

spike_mark_dead_end 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_mark_dead_end": {
      "limits": [
        {
          "counter": "spike_mark_dead_end_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_mark_dead_end

What does the spike_mark_dead_end tool do? +

spike_mark_dead_end. 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_mark_dead_end? +

Register the Hedgehog MCP server in PolicyLayer and add a rule for spike_mark_dead_end: 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_mark_dead_end? +

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

Can I rate-limit spike_mark_dead_end? +

Yes. Add a rate_limit block to the spike_mark_dead_end 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_mark_dead_end completely? +

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

spike_mark_dead_end 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.