AI agents call get_job to retrieve information from Extracto without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The get_job tool retrieves status and results of previously initiated extraction jobs. This is a read-only query operation that returns data without modifying, deleting, or executing anything. The only input is a job identifier, and the output is status/result information. Severity is low because it cannot affect external systems, cause data loss, or execute code.
From the tool's definition Tool description states it 'Fetch[es] the current status and (once complete) the result of an async extraction job' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Fetch the current status and (once complete) the result of an async extraction job. It is categorised as a Read tool in the Extracto MCP Server, which means it retrieves data without modifying state.
Register the Extracto MCP server in PolicyLayer and add a rule for get_job: 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 Extracto. Nothing to install.
get_job 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 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. 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 is provided by the Extracto MCP server (massanaroger/extracto-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 →