spike_complete_branch · Hedgehog MCP: Risk & Policy

WHAT IT DOES

What spike_complete_branch does on Hedgehog

AI agents use spike_complete_branch 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_complete_branch needs a policy

The tool operates on a persistent state system managing technical spike investigations. 'Complete' suggests marking a branch as done or finalizing its status—a reversible state change rather than deletion. This is consistent with Write category (modifies data reversibly). Severity is medium because it could affect workflow tracking and decision records, but the change appears reversible via other tools.

From the tool's definition Tool name 'spike_complete_branch' combined with sibling tools like 'spike_add_branch', 'spike_checkpoint', and 'spike_archive' indicates state modification within a technical spike investigation workflow. The description is empty, limiting precision.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

spike_complete_branch Rate-limited

spike_complete_branch 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_complete_branch": {
      "limits": [
        {
          "counter": "spike_complete_branch_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_complete_branch

What does the spike_complete_branch tool do? +

spike_complete_branch. 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_complete_branch? +

Register the Hedgehog MCP server in PolicyLayer and add a rule for spike_complete_branch: 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_complete_branch? +

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

Can I rate-limit spike_complete_branch? +

Yes. Add a rate_limit block to the spike_complete_branch 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_complete_branch completely? +

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

spike_complete_branch 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.