获取 GitLab 流水线作业
AI agents call get_pipeline_jobs to retrieve information from GitLab Pipeline MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries pipeline job data from GitLab. It has no side effects—it only fetches and displays information about existing pipeline jobs. This is a pure read operation with minimal risk; even if misused by an AI agent, it only exposes visibility into pipeline metadata without enabling any destructive, financial, or execution-based actions.
From the tool's definition Tool name 'get_pipeline_jobs' and description 'retrieve GitLab pipeline jobs' indicate a query operation that retrieves job information without modifying or executing anything.
Attacks that exploit this kind of access
获取 GitLab 流水线作业. It is categorised as a Read tool in the GitLab Pipeline MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitLab Pipeline MCP Server MCP server in PolicyLayer and add a rule for get_pipeline_jobs: 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 GitLab Pipeline MCP Server. Nothing to install.
get_pipeline_jobs 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_pipeline_jobs 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_pipeline_jobs. 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_pipeline_jobs is provided by the GitLab Pipeline MCP Server MCP server (wqhui/mcp-gitlab). 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 →