AI agents invoke execute_grasshopper_code to trigger actions in GH_mcp_server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool directly executes Python code, making it an Execute category tool. The severity is high because arbitrary Python code execution in a 3D modeling context could: (1) corrupt design files, (2) consume excessive computational resources, (3) access the file system, (4) modify geometry or parameters without user intent, or (5) interface with external systems.
From the tool's definition The tool description states it will 'Execute given Python code.' The tool name and description explicitly indicate code execution capabilities.
Documented attack patterns abuse exactly the kind of access execute_grasshopper_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GH_mcp_server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_grasshopper_code:
{
"version": "1",
"default": "deny",
"tools": {
"execute_grasshopper_code": {
"limits": [
{
"counter": "execute_grasshopper_code_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_grasshopper_code stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute given Python code. It is categorised as a Execute tool in the GH_mcp_server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GH_mcp_server MCP server in PolicyLayer and add a rule for execute_grasshopper_code: 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 GH_mcp_server. Nothing to install.
execute_grasshopper_code is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_grasshopper_code 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 execute_grasshopper_code. 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.
execute_grasshopper_code is provided by the GH_mcp_server MCP server (veoery/gh_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 12 GH_mcp_server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
12 GH_mcp_server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.