AI agents call get_item_config 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 Jenkins item configuration data without modifying, deleting, or executing operations. However, severity is elevated to 'medium' because Jenkins configurations often contain sensitive information such as credentials, API tokens, environment variables, and deployment parameters that could be leveraged for further attacks if exposed to an AI agent without proper safeguards.
From the tool's definition Tool name 'get_item_config' and description 'Get specific item config from Jenkins' indicate a retrieval operation with no modification or deletion. The verb 'Get' and lack of any destructive or write-oriented language confirm read-only semantics.
Attacks that exploit this kind of access
Get specific item config from Jenkins. 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 get_item_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. Nothing to install.
get_item_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 get_item_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 get_item_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.
get_item_config is provided by the Jenkins MCP server (mcpland/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 →