MCP & AI Agent Integration

Devin
automation.

14 AI agent actions for Devin — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Devin to create tasks, update project status, and coordinate work across teams automatically. Full governance, audit trail, and dry-run safety on every execution.

No credit card required
Live in production environments
<200ms median execution
Dry-run before production
Execution trace
live
14
actions
100%
governed
<200ms
latency
14
AI agent actions
6
Read operations
8
Write operations
2
High-risk actions (approval gated)
Productivity Devin is a Productivity integration — use it to automate tasks, projects, and team workflows from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Devin.

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 Project
devin:get_project
Fetch a single project by ID with current status and configuration.
Read Low risk
Get Session
devin:get_session
Fetch a single work session by ID with activity details and logs.
Read Low risk
Get Task
devin:get_task
Fetch a single task by ID with current status and progress details.
Read Low risk
List Projects
devin:list_projects
List projects with optional filtering by status and language.
Read Low risk
List Sessions
devin:list_sessions
List work sessions with optional filtering by project and status.
Read Low risk
List Tasks
devin:list_tasks
List tasks with optional filtering by project, status, and priority.
Read Low risk
Cancel Task
devin:cancel_task
Cancel a pending or in-progress task.
Write High risk
Create Project
devin:create_project
Create a new project for Devin to work on.
Write Medium risk
Create Task
devin:create_task
Create a new task for Devin to work on within a project.
Write Medium risk
Delete Project
devin:delete_project
Permanently delete a project and all associated data.
Write High risk
Start Session
devin:start_session
Start a new work session for Devin to begin working on a task.
Write Medium risk
Stop Session
devin:stop_session
Stop an active work session and save progress.
Write Low risk
Update Project
devin:update_project
Update an existing project's configuration and metadata.
Write Medium risk
Update Task
devin:update_task
Update an existing task's details and status.
Write Medium risk
MCP & Runtime API

Call Devin
from any AI agent.

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

devin:get_project READ
# Call via Runtime API
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "devin:get_project",
    "args": {},
    "execution_id": "agent-001"
  }'
devin:cancel_task 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": "devin:cancel_task",
    "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 Devin.

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 Devin data
Call devin:get_project 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 Devin
Dry-run validates devin:cancel_task before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Task or project event
Update status automatically
Notify assignees
Sync across tools
How it works

Every Devin action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of Devin — 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 Devin action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every Devin action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Connect with

Devin works best
alongside these.

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

Devin integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →