Platform
Platform Overview Maps Memory Shadow Mode Widget Governance Actions Integrations
Developers
Overview Catalog Guardrails Dry Run Idempotency Credentials Audit Trail API Reference
Company
About Blog Contact Book a Demo
MCP Integrations Circleci
MCP & AI Agent Integration

Circleci
automation.

18 AI agent actions for Circleci — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Circleci to update contacts, move deals through pipelines, and trigger follow-up sequences automatically. Full governance, audit trail, and dry-run safety on every execution.

Connect Circleci free Browse all integrations →
No credit card required
Live in production environments
<200ms median execution
Dry-run before production
Execution trace
live
18
actions
100%
governed
<200ms
latency
18
AI agent actions
12
Read operations
6
Write operations
3
High-risk actions (approval gated)
CRM Circleci is a CRM integration — use it to automate contact management, deals, and pipeline operations from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Circleci.

Every action below is available as an MCP tool and a verb in Cerebral OS — callable from any AI agent, Claude, Cursor, Windsurf, or your own runtime via the BYOA API. All executions are governed, audited, and dry-run safe.

Get Context
circleci:get_context
Fetch a single context's details and metadata.
Read Low risk
Get Job
circleci:get_job
Fetch a single job's details including status, timing, and executor info.
Read Low risk
Get Job Artifacts
circleci:get_job_artifacts
List all artifacts produced by a job with download URLs.
Read Low risk
Get Job Tests
circleci:get_job_tests
Get test results and metadata for a job.
Read Low risk
Get Pipeline
circleci:get_pipeline
Fetch a single pipeline's details including status and metadata.
Read Low risk
Get Project
circleci:get_project
Fetch a single project's details and configuration.
Read Low risk
Get Workflow
circleci:get_workflow
Fetch a single workflow's details including status and timing.
Read Low risk
List Contexts
circleci:list_contexts
List all contexts the user has access to.
Read Low risk
List Jobs
circleci:list_jobs
List all jobs for a specific workflow with status and timing info.
Read Low risk
List Pipelines
circleci:list_pipelines
List pipelines for a project with filtering and pagination.
Read Low risk
List Projects
circleci:list_projects
List all projects the user has access to with basic information.
Read Low risk
List Workflows
circleci:list_workflows
List all workflows for a specific pipeline.
Read Low risk
Cancel Job
circleci:cancel_job
Cancel a running job.
Write High risk
Cancel Workflow
circleci:cancel_workflow
Cancel a running workflow and all its jobs.
Write High risk
Create Context
circleci:create_context
Create a new context for storing environment variables.
Write Medium risk
Delete Context
circleci:delete_context
Delete a context and all its environment variables permanently.
Write High risk
Rerun Workflow
circleci:rerun_workflow
Rerun a workflow from the beginning or from failed jobs.
Write Medium risk
Trigger Pipeline
circleci:trigger_pipeline
Trigger a new pipeline for a project on a specific branch or tag.
Write Medium risk
MCP & Runtime API

Call Circleci
from any AI agent.

Any AI agent — Claude, Cursor, LangChain, AutoGen, or your own — can call Circleci actions through the Cerebral OS Runtime API. Governance, credentials, and audit trail fire automatically.

circleci:get_context READ
# Call via Runtime API
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "circleci:get_context",
    "args": {},
    "execution_id": "agent-001"
  }'
circleci:cancel_job WRITE
# Dry-run first — no production risk
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "circleci:cancel_job",
    "args": {},
    "execution_id": "agent-001",
    "metadata": {"dryRun": true}
  }'
Get your Runtime API key at app.cerebralos.com/signup — 1,000 free executions, no credit card required.
AI agent examples

What your AI agent
can do with Circleci.

Real patterns your AI agent can execute via MCP or the Runtime API. Every action governed, dry-run safe, and fully audited.

Trigger
AI agent needs Circleci data
Call circleci:get_context via MCP or Runtime API
AI processes result and takes next action
Full execution logged to audit trail automatically
Trigger
Workflow needs to write to Circleci
Dry-run validates circleci:cancel_job before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Lead or deal event
Score with AI
Route to right rep
Trigger outreach sequence
How it works

Every Circleci action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of Circleci — adding governance, dry-run safety, and a full audit trail to every operation.

Governance first
Every verb carries a risk classification. High-risk writes require explicit approval gates before they execute in production.
Dry-run safe
Simulate any Circleci action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every Circleci action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Connect with

Circleci works best
alongside these.

Build multi-step workflows that connect Circleci to the rest of your stack. All governed. All audited.

Hubspot Salesforce Pipedrive Gmail Slack
Circleci integration

Start free.
No credit card required.

Start free with 1,000 runs — no credit card required. Connect Circleci in minutes, dry-run every action before it touches production, full audit trail on everything.

Start free — 1,000 runs Browse all integrations →