AI agents call getJob to retrieve information from Jenkins without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves job information by querying Jenkins for metadata about an existing job. It performs no modifications, deletions, or executions—it is purely a data retrieval operation. The low severity reflects minimal blast radius: exposure of this tool allows an agent to query job definitions but not alter them or trigger builds. The high confidence reflects unambiguous read-only semantics.
From the tool's definition Tool name 'getJob' and description 'Get a Jenkins job by its full path' indicate retrieval of job metadata with no side effects. Sibling tools like 'getAllJobs', 'getBuild', and 'getBuildLog' confirm this server's read/query operations.
Attacks that exploit this kind of access
Get a Jenkins job by its full path. It is categorised as a Read tool in the Jenkins MCP Server, which means it retrieves data without modifying state.
Register the Jenkins MCP server in PolicyLayer and add a rule for getJob: 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 Jenkins. Nothing to install.
getJob 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 getJob 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 getJob. 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.
getJob is provided by the Jenkins MCP server (redhat-community-ai-tools/jenkins-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 →