Check job progress
AI agents call query_job_status to retrieve information from MOF Tools 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 status information without creating, modifying, deleting, or executing any processes. It is a simple query/read operation on existing job state, making it a low-severity Read category tool suitable for monitoring scientific workflows.
From the tool's definition Tool name 'query_job_status' and description 'Check job progress' indicate a status-checking operation with no modification of data or execution of new operations.
Attacks that exploit this kind of access
Check job progress. It is categorised as a Read tool in the MOF Tools MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MOF Tools MCP Server MCP server in PolicyLayer and add a rule for query_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 MOF Tools MCP Server. Nothing to install.
query_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 query_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 query_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.
query_job_status is provided by the MOF Tools MCP Server MCP server (liuyuxiang92/mofmaster-scientific-server). 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 →