AI agents use spike_archive 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.
Archiving moves data to a different location (archive directory) but does not destroy it or make it irretrievable. This is a write-class operation (modifies state by relocating records) that is reversible—archived data can be restored. While it changes the visibility or accessibility of spike investigation records, the operation is not destructive.
From the tool's definition Tool description states 'Archive a spike investigation (move to archive directory)' - this is a reversible file/data move operation, not a deletion.
Attacks that exploit this kind of access
Archive a spike investigation (move to archive directory). 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.
Register the Hedgehog MCP server in PolicyLayer and add a rule for spike_archive: 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.
spike_archive is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the spike_archive 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.
Set action: deny in the PolicyLayer policy for spike_archive. 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.
spike_archive 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →