update_job
AI agents use update_job to create or update resources in CATS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CATS MCP Server environment.
The tool name and server context strongly suggest this updates job records reversibly (e.g., job details, descriptions, requirements). Without an explicit description, confidence is moderated, but job updates in ATS systems are typically Write operations—creating or modifying data without deletion.
From the tool's definition Tool name 'update_job' indicates modification of job data. Description is empty/uninformative. Context from sibling tools (attach_*_tags, change_*_thumbnail, change_job_status) shows this server handles reversible data modifications across recruiting…
Attacks that exploit this kind of access
update_job. It is categorised as a Write tool in the CATS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CATS MCP Server MCP server in PolicyLayer and add a rule for update_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 CATS MCP Server. Nothing to install.
update_job is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_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 update_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.
update_job is provided by the CATS MCP Server MCP server (vanman2024/cats-mcp-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 →