Get the status of a processing job
AI agents call get_job_status to retrieve information from Document Parser MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the state of an existing job in the queue system. It performs a read-only retrieval of status data with no ability to modify, delete, or trigger execution. The blast radius of misuse is minimal—an attacker could only learn the status of jobs, not interfere with processing or access sensitive document content through this tool alone.
From the tool's definition Tool name 'get_job_status' and description 'Get the status of a processing job' indicate a query operation that retrieves status information without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Get the status of a processing job. It is categorised as a Read tool in the Document Parser MCP MCP Server, which means it retrieves data without modifying state.
Register the Document Parser 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 Document Parser MCP. 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 Document Parser MCP server (kgand/document-parser-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 →