// SCAN REPORT

HoudiniMCP

16 tools. 14 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 11 Jun 2026

14 can modify or destroy data

2 read-only

16 tools total

Community server · catalogue entry verified 11/06/2026

How to control HoudiniMCP ↓

TOOL MAP

What HoudiniMCP exposes to your agents

Read (2) Write / Execute (13) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous HoudiniMCP tools

Destructive · High delete_node Deleting a node from a Houdini scene is irreversible without manual undo/recovery. Execute · High execute_houdini_code Executing arbitrary Python code in Houdini constitutes running code whose effects are entirely argument-dependent and unpredictable. Execute · High run_simulation run_simulation executes a computation-intensive external operation (Houdini physics/particle simulation) whose effects depend on the simulation parameters and scene state. Execute · High create_simulation Based on the tool name 'create_simulation' and the server context (Houdini 3D software), this tool likely triggers a simulation computation (e.g., fluid, cloth, rigid body dynamics) within Houdini.

14 of HoudiniMCP's 16 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control HoudiniMCP

PolicyLayer is an MCP gateway — it sits between your AI agents and HoudiniMCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_node": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "connect_nodes": {
    "limits": [
      {
        "counter": "connect_nodes_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_node_info": {
    "limits": [
      {
        "counter": "get_node_info_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register HoudiniMCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON HOUDINIMCP →

Free to start. No card required.

FULL CATALOGUE

All 16 HoudiniMCP tools

DESTRUCTIVE 1 tools

Destructive delete_node Delete a node from the Houdini network.

EXECUTE 4 tools

Execute execute_houdini_code Execute arbitrary Python code in Houdini. Execute run_simulation run_simulation Execute create_simulation create_simulation Execute render_scene render_scene

WRITE 9 tools

Write connect_nodes connect_nodes Write create_camera create_camera Write create_geometry create_geometry Write create_light create_light Write create_node create_node Write export_fbx Export a node to FBX format. Write modify_node modify_node Write set_material set_material Write set_parameter set_parameter

READ 2 tools

Read get_node_info Get detailed information about a specific node in the Houdini scene. Read get_scene_info Get detailed information about the current Houdini scene

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about HoudiniMCP

Can an AI agent delete data through the Houdini MCP server? +

Yes. The HoudiniMCP server exposes 1 destructive tools including delete_node. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through HoudiniMCP? +

The HoudiniMCP server has 9 write tools including connect_nodes, create_camera, create_geometry. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach HoudiniMCP.

How many tools does the Houdini MCP server expose? +

16 tools across 4 categories: Destructive, Execute, Read, Write. 2 are read-only. 14 can modify, create, or delete data.

How do I enforce a policy on HoudiniMCP? +

Register the Houdini MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every HoudiniMCP tool call.

Deterministic rules across all 16 HoudiniMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON HOUDINIMCP →

Free to start. No card required.

16 HoudiniMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.