Read job config.xml. Jenkins may redact secrets without Configure permission.
AI agents call jenkins_get_job_config to retrieve information from Jenkins Http without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries job configuration data from Jenkins without modifying any state or triggering operations. The description clarifies it is a read-only operation. The note about secret redaction indicates the server respects permission boundaries.
From the tool's definition Tool name contains 'get' and description explicitly states 'Read job config.xml', indicating data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Read job config.xml. Jenkins may redact secrets without Configure permission. It is categorised as a Read tool in the Jenkins Http MCP Server, which means it retrieves data without modifying state.
Register the Jenkins Http MCP server in PolicyLayer and add a rule for jenkins_get_job_config: 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 Http. Nothing to install.
jenkins_get_job_config 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 jenkins_get_job_config 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_get_job_config. 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_get_job_config is provided by the Jenkins Http MCP server (mdtahmidhossain/jenkins-http-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 →