AI agents call spike_get_state to retrieve information from Hedgehog without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns the current state of a spike investigation without modifying, deleting, or executing any external operations. It is a straightforward read operation that retrieves information about an investigation's status and data. The low severity reflects minimal risk even if an AI agent calls it—it only accesses existing state information without the ability to alter it.
From the tool's definition Tool name 'spike_get_state' and description 'Get the current state of a spike investigation' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the current state of a spike investigation. It is categorised as a Read tool in the Hedgehog MCP Server, which means it retrieves data without modifying state.
Register the Hedgehog MCP server in PolicyLayer and add a rule for spike_get_state: 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_get_state is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the spike_get_state 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_get_state. 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_get_state 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 →