Create (trigger) a new CI/CD pipeline.
AI agents invoke create_pipeline_tool to trigger actions in MCP Gitlab. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Triggering a CI/CD pipeline executes automated workflows that can run arbitrary code, deploy software, modify infrastructure, or perform other operations with significant blast radius. This is an Execute-category action — it initiates external operations whose effects depend on the pipeline's contents.
From the tool's definition Create (trigger) a new CI/CD pipeline
Attacks that exploit this kind of access
Create (trigger) a new CI/CD pipeline. It is categorised as a Execute tool in the MCP Gitlab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Gitlab MCP server in PolicyLayer and add a rule for create_pipeline_tool: 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 Gitlab. Nothing to install.
create_pipeline_tool is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_pipeline_tool 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 create_pipeline_tool. 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.
create_pipeline_tool is provided by the MCP Gitlab MCP server (mcp-gitlab-crunchtools). 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 →