physics_add
AI agents use physics_add to create or update resources in COMSOL MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your COMSOL MCP Server environment.
The 'add' verb indicates reversible creation/modification of simulation physics parameters rather than deletion or code execution. However, in a physics simulation environment, modifying physics configurations could alter computational models with potentially significant downstream effects, warranting 'high' severity.
From the tool's definition Tool name 'physics_add' suggests adding/creating physics configurations in COMSOL simulations. Sibling tools (geometry_add_block, geometry_add_circle, geometry_add_cylinder) follow 'add' pattern indicating data creation.
Attacks that exploit this kind of access
physics_add. It is categorised as a Write tool in the COMSOL MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the COMSOL MCP Server MCP server in PolicyLayer and add a rule for physics_add: 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 COMSOL MCP Server. Nothing to install.
physics_add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the physics_add 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 physics_add. 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.
physics_add is provided by the COMSOL MCP Server MCP server (zhangyoupeng1996/codex_mcp_comsol). 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 →