AI agents call inspect_script to retrieve information from Molmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is part of a discovery/documentation engine designed to help agents find and understand code symbols and signatures. The name 'inspect_script' indicates passive examination of script structure or metadata, consistent with other Read-category siblings like 'inspect_structure' and 'get_command_doc'. No destructive, execution, write, or financial operations are implied.
From the tool's definition Tool named 'inspect_script' with empty description. Based on naming convention and sibling tools (explain_command, explain_error, get_command_doc, inspect_structure, list_compute_ops), this appears to be a read-only inspection/discovery tool.
Attacks that exploit this kind of access
inspect_script. It is categorised as a Read tool in the Molmcp MCP Server, which means it retrieves data without modifying state.
Register the Mol MCP server in PolicyLayer and add a rule for inspect_script: 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 Molmcp. Nothing to install.
inspect_script 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 inspect_script 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 inspect_script. 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.
inspect_script is provided by the Mol MCP server (molcrafts/molmcp). 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 →