Get all node errors and warnings for a specified Houdini graph context.
AI agents call get_node_errors to retrieve information from Houdini MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves diagnostic information (errors and warnings) from a Houdini graph context without executing code, modifying nodes, or triggering side effects. It is a read-only operation that returns existing state information. The low severity reflects that misuse would only expose debug information, not cause harm to the scene or external systems.
From the tool's definition Tool name 'get_node_errors' and description 'Get all node errors and warnings' indicate a query/retrieval operation with no modification of scene state.
Attacks that exploit this kind of access
Get all node errors and warnings for a specified Houdini graph context. It is categorised as a Read tool in the Houdini MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Houdini MCP Server MCP server in PolicyLayer and add a rule for get_node_errors: 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 Houdini MCP Server. Nothing to install.
get_node_errors 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 get_node_errors 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 get_node_errors. 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.
get_node_errors is provided by the Houdini MCP Server MCP server (kif11/houdini-mcp-server). 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 →