AI agents invoke circleci_trigger_pipeline to trigger actions in UnClick. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
tag | string | — | Tag to build |
branch | string | — | Branch to build (default: main/master) |
api_key | string | Yes | CircleCI personal API token |
parameters | object | — | Pipeline parameters as key-value pairs |
project_slug | string | Yes | Project slug e.g. gh/MyOrg/my-repo |
Parameters from the server's own tool schema.
This tool triggers an external CI/CD pipeline execution, which runs code builds, tests, and deployments whose effects depend on the branch, tag, and parameters specified by the caller. This is Execute rather than Write because it initiates automated operations with side effects beyond simple data creation—it can execute arbitrary builds and deployments.
From the tool's definition Tool description states 'Trigger a new CircleCI pipeline for a project' with optional specification of branch, tag, or parameters.
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
Trigger a new CircleCI pipeline for a project. Optionally specify branch, tag, or parameters. It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
circleci_trigger_pipeline accepts 5 parameters: tag, branch, api_key, parameters, project_slug. Required: api_key, project_slug. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for circleci_trigger_pipeline: 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 UnClick. Nothing to install.
circleci_trigger_pipeline 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 circleci_trigger_pipeline 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 circleci_trigger_pipeline. 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.
circleci_trigger_pipeline is provided by the UnClick MCP server (@unclick/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 →