AI agents call molexp_list_projects 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.
This tool queries and returns a list of projects, which is a non-destructive read operation. It has no side effects, does not execute code, create/modify data, or delete anything. The blast radius of misuse is minimal - an agent could only discover what projects exist in the workspace, which is informational. This aligns with the Read category for retrieval operations.
From the tool's definition Tool name contains 'list' and description states 'Enumerate projects in the workspace' - a read operation that retrieves and displays existing project metadata without modification, deletion, or execution.
Attacks that exploit this kind of access
Enumerate projects in the workspace. 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 molexp_list_projects: 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.
molexp_list_projects 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 molexp_list_projects 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 molexp_list_projects. 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.
molexp_list_projects 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 →