AI agents call molexp_list_runs 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.
Based on the tool name pattern and sibling tools which are all Read operations (explain, get, inspect - all information retrieval), this tool appears to be querying run history or status data. List operations are fundamentally non-destructive reads with no side effects. Empty description prevents absolute certainty, but naming conventions and server context strongly suggest this is a simple retrieval operation.
From the tool's definition Tool name 'molexp_list_runs' indicates a listing operation that queries/retrieves existing runs without modifying or deleting them. The 'list' verb is consistent with Read category operations. Description is empty, which slightly lowers confidence.
Attacks that exploit this kind of access
molexp_list_runs. 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_runs: 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_runs 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_runs 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_runs. 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_runs 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 →