Get Jenkins info
AI agents call get_jenkins_info to retrieve information from MCP Jenkins Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries Jenkins server metadata without side effects. It retrieves information about the Jenkins instance itself (version, configuration, plugins, etc.). Unauthorized information disclosure about CI/CD infrastructure has low immediate blast radius compared to build triggering or job deletion, though it could inform further attacks.
From the tool's definition Tool name 'get_jenkins_info' and description 'Get Jenkins info' indicate a retrieval operation. The server description lists this among tools for 'view server info' and 'inspect builds', and sibling tools like 'get_build_console_output', 'get_build_info',…
Attacks that exploit this kind of access
Get Jenkins info. It is categorised as a Read tool in the MCP Jenkins Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Jenkins Server MCP server in PolicyLayer and add a rule for get_jenkins_info: 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 Server. Nothing to install.
get_jenkins_info 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_jenkins_info 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_jenkins_info. 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_jenkins_info is provided by the MCP Jenkins Server MCP server (winjayx/014.jenkinsmcp). 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 →