Create a new Jenkins job from an XML configuration
AI agents use jenkins_create_job to create or update resources in Mcp Jenkins — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Jenkins environment.
This tool creates a new Jenkins job, which is a reversible write operation (the job can be deleted via jenkins_delete_job also present on this server). However, given that jobs in Jenkins can trigger arbitrary builds and execute code, creating a malicious job could enable significant harm downstream.
From the tool's definition Tool name: 'jenkins_create_job'; description: 'Create a new Jenkins job from an XML configuration' — the verb 'Create' and explicit mention of job creation indicate persistent data modification.
Attacks that exploit this kind of access
Create a new Jenkins job from an XML configuration. It is categorised as a Write tool in the Mcp Jenkins MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Jenkins MCP server in PolicyLayer and add a rule for jenkins_create_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 Mcp Jenkins. Nothing to install.
jenkins_create_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 jenkins_create_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 jenkins_create_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.
jenkins_create_job is provided by the Mcp Jenkins MCP server (@kud/mcp-jenkins). 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 →