AI agents invoke update_project to trigger actions in Ansys Workbench. 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.
The tool triggers execution of an Update() operation inside a running Ansys Workbench process. This is an Execute-category action: it initiates computation/simulation workflows whose effects depend on the current project state. While not inherently destructive, misuse could trigger expensive or unintended simulation runs, overwrite result files, or destabilize a live session.
From the tool's definition 'Run Workbench Update() in the running bridge' — explicitly runs/executes a command in the live Workbench session
Documented attack patterns abuse exactly the kind of access update_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ansys Workbench, and nothing reaches the server without passing your rules. This is the rule we recommend for update_project:
{
"version": "1",
"default": "deny",
"tools": {
"update_project": {
"limits": [
{
"counter": "update_project_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}update_project 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.
Run Workbench Update() in the running bridge. It is categorised as a Execute tool in the Ansys Workbench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ansys Workbench MCP server in PolicyLayer and add a rule for update_project: 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 Ansys Workbench. Nothing to install.
update_project 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 update_project 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 update_project. 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.
update_project is provided by the Ansys Workbench MCP server (hongwenwang36-eng/ansys-workbench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ansys Workbench, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
29 Ansys Workbench tools catalogued and risk-classified — across an index of 43,000+ MCP servers.