Get log output from a running or completed job.
AI agents call get_job_log to retrieve information from ESMfold MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves job log information for monitoring and debugging purposes. It queries state without altering it, making it a Read operation. The severity is low because log data is typically non-sensitive metadata about job execution, and retrieval poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_job_log' and description 'Get log output from a running or completed job' indicate retrieval of existing log data without modification or side effects.
Attacks that exploit this kind of access
Get log output from a running or completed job. It is categorised as a Read tool in the ESMfold MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ESMfold MCP Server MCP server in PolicyLayer and add a rule for get_job_log: 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 ESMfold MCP Server. Nothing to install.
get_job_log 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 get_job_log 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 get_job_log. 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.
get_job_log is provided by the ESMfold MCP Server MCP server (macromnex/esmfold_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 →