List the node9 snapshot history. Each entry shows the git hash, tool that triggered it,
AI agents call node9_undo_list to retrieve information from Node9-Proxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays audit/snapshot history information. It has no side effects—it only queries and lists existing data. While it provides visibility into system operations which could inform an attacker, the tool itself performs no destructive, modifying, or execution action.
From the tool's definition Tool name 'node9_undo_list' and description 'List the node9 snapshot history' indicate a retrieval/query operation that returns historical snapshot data (git hash, triggering tool) without modifying or deleting anything.
Documented attack patterns abuse exactly the kind of access node9_undo_list gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Node9-Proxy, and nothing reaches the server without passing your rules. This is the rule we recommend for node9_undo_list:
{
"version": "1",
"default": "deny",
"tools": {
"node9_undo_list": {}
}
}node9_undo_list is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List the node9 snapshot history. Each entry shows the git hash, tool that triggered it,. It is categorised as a Read tool in the Node9-Proxy MCP Server, which means it retrieves data without modifying state.
Register the Node9-Proxy MCP server in PolicyLayer and add a rule for node9_undo_list: 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 Node9-Proxy. Nothing to install.
node9_undo_list 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 node9_undo_list 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 node9_undo_list. 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.
node9_undo_list is provided by the Node9-Proxy MCP server (node9-ai/node9-proxy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 16 Node9-Proxy tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
16 Node9-Proxy tools catalogued and risk-classified — across an index of 42,500+ MCP servers.