MCP & AI Agent Integration

Desktime
automation.

18 AI agent actions for Desktime — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Desktime 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
18
actions
100%
governed
<200ms
latency
18
AI agent actions
7
Read operations
11
Write operations
3
High-risk actions (approval gated)
Productivity Desktime 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 Desktime.

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 Employee
desktime:get_employee
Fetch a single employee by ID with their basic information and settings.
Read Low risk
Get Project
desktime:get_project
Fetch a single project by ID with details and assigned employees.
Read Low risk
Get Time Entry
desktime:get_time_entry
Fetch a single time entry by ID with project and employee details.
Read Low risk
Get Timer Status
desktime:get_timer_status
Check if an employee has a running timer and get its details.
Read Low risk
List Employees
desktime:list_employees
List employees with optional filtering by department and status.
Read Low risk
List Projects
desktime:list_projects
List projects with optional filtering by status and client.
Read Low risk
List Time Entries
desktime:list_time_entries
List time entries with optional filtering by employee, project, and date range.
Read Low risk
Create Employee
desktime:create_employee
Create a new employee in DeskTime with basic information.
Write Medium risk
Create Project
desktime:create_project
Create a new project in DeskTime with optional employee assignments.
Write Medium risk
Create Time Entry
desktime:create_time_entry
Create a new manual time entry for an employee and project.
Write Medium risk
Delete Employee
desktime:delete_employee
Delete an employee from DeskTime. WARNING: This permanently removes all their data.
Write High risk
Delete Project
desktime:delete_project
Delete a project from DeskTime. WARNING: This permanently removes all associated data.
Write High risk
Delete Time Entry
desktime:delete_time_entry
Delete a time entry from DeskTime. WARNING: This permanently removes the entry.
Write High risk
Start Timer
desktime:start_timer
Start a time tracking timer for an employee on a specific project.
Write Medium risk
Stop Timer
desktime:stop_timer
Stop the currently running timer for an employee and create a time entry.
Write Medium risk
Update Employee
desktime:update_employee
Update an existing employee's information in DeskTime.
Write Medium risk
Update Project
desktime:update_project
Update an existing project's information and assignments in DeskTime.
Write Medium risk
Update Time Entry
desktime:update_time_entry
Update an existing time entry's details. Note: Employee cannot be changed.
Write Medium risk
MCP & Runtime API

Call Desktime
from any AI agent.

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

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

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 Desktime data
Call desktime:get_employee 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 Desktime
Dry-run validates desktime:create_employee 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 Desktime action
governed end-to-end.

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

Desktime works best
alongside these.

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

Desktime integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →