get_job_status
AI agents call get_job_status to retrieve information from FoldRun MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve the status of a protein prediction job without modifying state or triggering external operations. The empty description prevents higher confidence, but the naming pattern and context of read-only status checking aligns with the Read category (retrieves data; no side effects). Severity is low because job status queries have minimal blast radius.
From the tool's definition Tool name 'get_job_status' and sibling tools ('submit_protein_prediction', 'get_prediction_results') indicate a job management workflow. The 'get_' prefix and absence of write/execute operations suggest status querying.
Attacks that exploit this kind of access
get_job_status. It is categorised as a Read tool in the FoldRun MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FoldRun MCP Server MCP server in PolicyLayer and add a rule for get_job_status: 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 FoldRun MCP Server. Nothing to install.
get_job_status 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_status 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_status. 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_status is provided by the FoldRun MCP Server MCP server (jz3736/foldrun-mcp-ge-demo). 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 →