Call any PyMOL XML-RPC method and return the result.
AI agents call pymol_get to retrieve information from Pymol Cursor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the tool can call 'any' PyMOL XML-RPC method, the explicit framing as returning results suggests it is intended for introspection and data retrieval (e.g., querying molecular structure properties, atom coordinates, or display settings). The presence of sibling tools (run_command, run_python) that likely handle execution suggests pymol_get is scoped to read operations.
From the tool's definition pymol_get is described as 'Call any PyMOL XML-RPC method and return the result,' which indicates data retrieval from PyMOL's state rather than modification or execution of arbitrary operations.
Attacks that exploit this kind of access
Call any PyMOL XML-RPC method and return the result. It is categorised as a Read tool in the Pymol Cursor MCP Server, which means it retrieves data without modifying state.
Register the Pymol Cursor MCP server in PolicyLayer and add a rule for pymol_get: 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 Pymol Cursor. Nothing to install.
pymol_get 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 pymol_get 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 pymol_get. 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.
pymol_get is provided by the Pymol Cursor MCP server (truong128/pymol-cursor-mcp). 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 →