auto_awesomeFeatures

Features that get an AI task all the way to a merged PR and a paid invoice.

mcptask.online is the only platform where an AI agent's work flows through time tracking, approval, and invoicing — not just a ticket. Model-agnostic, runs on your own infrastructure, recovers from interruptions.

compare_arrowsFrom ticket to paid invoice

Jira and Linear end at the ticket. Agentic tools end at the PR. mcptask.online takes AI work all the way to a paid invoice.

confirmation_number

Jira / Linear

Ticket

code

Agentic tools

PR

receipt_long

mcptask.online

Paid invoice

infomcptask.online is the only platform that takes AI work all the way to a billable invoice.
lightbulbScenarios

Use cases

Real scenarios where mcptask.online saves time and takes work all the way to done.

speed

Merged PR overnight

For well-scoped tasks, the runner can deliver a merged PR overnight — no handoff, no lost context. The work shows up in time tracking the same way human effort does.

  • check_circleAI work lands in the time sheet, not in a separate log
  • check_circleNo billing — billable effort is logged on top of the runner's output
  • check_circleOne PR per task, ready for review or auto-merged after CI
  • check_circleRun while you sleep: finish the task, hit CI, merge it
01
chat

Manager status from chat

Ask for a project status report or assign a task through any MCP client — Claude Desktop, Claude Cowork, Cursor — without opening the app.

  • check_circleAssign tasks via chat
  • check_circleGet status reports instantly
  • check_circleFile notes that land on the right task
  • check_circleNo new UI to learn
02
receipt_long

Invoice AI and human work together

Approved effort from both AI agents and human teammates exports directly to Fakturoid or iDoklad. One audit trail, one invoice.

  • check_circleAI effort in the same time sheet
  • check_circleManager approval before billing
  • check_circleOne-click export to invoicing tools
  • check_circleClear attribution for every entry
03
engineering

No free developer? The runner works overnight

A well-scoped task sits in the queue because the team is busy. The runner picks it up overnight and the next morning there is a PR ready for review.

  • check_circleNo need to pull a human off another task
  • check_circlePR is ready for review the next morning
  • check_circleWorks for clearly described, bounded tasks
  • check_circleHuman review still happens before merge
04
payments

Low running costs, model choice is yours

Model-agnostic means you are not locked into a premium model from a single vendor. Use cheap or local models and control what you spend on inference.

  • check_circleChoose the model that fits the task
  • check_circleRun local or low-cost models for routine work
  • check_circleNo per-seat markup from the platform
  • check_circleCosts scale with your own infrastructure choices
05
smart_toyAutonomous Runner (mcptask_runner)

mcptask_runner: the autonomous developer that takes a task to a merged PR

mcptask_runner is a Ruby gem that wraps Claude Code with a real autonomous loop. It picks the next task, judges complexity, picks the right model, writes code and tests, opens a PR, watches CI, and merges when green. Runs on YOUR infrastructure against the real environment (real DB, system tests). Model-agnostic — including cheap or local models.

bug_report

Hits a foreign bug? Files it, pins it, returns to your task

If the runner hits an urgent bug unrelated to the current task, it commits and pushes the in-progress work, switches to main, files a new urgent bug task, and pins it to disk. Even after a restart it fixes the bug first and only then returns to the original task. Chaos becomes a tracked, owned item.

01
vpn_lock

Model-agnostic, on your own infrastructure

The runner picks the right model for each task — including cheap or local ones. It runs against your real environment (real DB, real system tests), not a sandbox. No lock-in to a premium model; you control the cost and the data.

02
smart_toy

From task to merged PR, end to end

The runner doesn't just 'open Claude Code on a task'. It runs the full workflow: branch → code → unit tests → screenshots → system tests → push → PR → CI. A task isn't done until CI is green and the PR is merged.

03
memory

Survives context overflow and interruption

If a run ends because of context overflow, a quota hit, or an urgent bug, the task stays in_progress and the unfinished work stays on the branch. The next run picks it up: reads git log + branch state, merges origin/main, skips already-done steps, and escalates the model to a stronger one.

04
visibility

Watchdogs, stall detection, daily quota

Heartbeat monitoring kills idle runs at 20 minutes, soft-warns on frozen at 3, caps stuck tools, and refreshes the daily quota every tick. Stall detection recognizes 'spinning in place' and kills it — the task resumes on a stronger model next time. Quota is fail-closed.

05
psychology

Triage and model selection (three levels)

Before any work, triage rates the task's complexity and recommends a model: genius (heavy code), smart (triage/review), or primitive (read-only). Model ids are versioned so retry strings survive context overflow.

06
lockSecurity & Compliance

Your code stays on your infrastructure. Your account data stays in the EU.

Two separate layers, both under your control. The runner executes on your own machines, so your source code never leaves your environment. The mcptask.online platform stores data in EU data centers (Frankfurt) with GDPR-compliant controls and a full audit trail.

lock

AI Sees Only What You Allow

Scoped permissions for AI agents. Restrict by project, task type, or action. Full control over what AI can read, write, and modify.

Scoping Options
  • securityProject-level access
  • securityTask type restrictions
  • securityRead-only vs. write
  • securityAction limits (no delete, etc.)
01
history

Every AI Action Tracked

Complete audit trail of all AI activity. What task was accessed, what changes were made, when, and by which agent. Exportable for compliance.

Logged Events
  • historyTask accessed
  • historyStatus changed
  • historyEffort logged
  • historyComment added
  • historyFile uploaded
02
enhanced_encryption

Bank-Level Security

Data encrypted in transit (TLS). Passwords bcrypt-hashed. Servers access-restricted (SSH-key only) and kept up to date. Regular security reviews.

03
verified_user

EU Data Protection

Full GDPR compliance. Data stored in EU (Frankfurt). Data export anytime. Right to erasure. Data processing agreements available.

04
dns

Data Stays in Europe

All servers in EU data centers (Frankfurt, Germany). No data transfer outside EU. Compliant with EU data sovereignty requirements.

05
verified_userSecurity Overview
shieldEnterprise-Grade
lock

AI Access Control

Scoped permissions for every AI agent with project-level restrictions

admin_panel_settingsRole-based access
enhanced_encryption

Data Protection

TLS 1.3 in transit, bcrypt-hashed passwords, SSH-key-only server access

securityBank-level security
verified_user

EU Compliance

GDPR compliant with data stored in EU data centers (Frankfurt)

publicEU data residency
infoComplete audit trail for all AI and human activity
gpp_goodCompliance ready

Data Protection Standards

Enterprise security for your AI workflows

vpn_key
Access

SSH Key

lock
In Transit

TLS 1.3

verified_user
Compliant

GDPR

dns
Frankfurt

EU Data

receipt_longFrom Task to Invoice

The only platform where an AI agent's work flows all the way to a paid invoice

Jira and Linear end at the ticket. Agentic tools end at the PR. mcptask.online closes the loop: time tracking captures AI work, managers approve it, and the result exports to Fakturoid or iDoklad for invoicing. One audit trail from chat to cash.

schedule

AI work lands in the time sheet automatically

When the runner works a task, every action logs effort: duration, description, progress, blockers. Human work and AI work live in the same time sheet, the same approval flow, the same export.

01
check_circle

Approval flow: Logged → Approved → Billed

Managers review AI-logged effort alongside human effort. Pending → Approved → Billed. Adjust if needed. The audit trail is the same for both — clients see one stream of work, not two.

02
receipt_long

Export to Fakturoid and iDoklad

Approved effort exports directly to Fakturoid or iDoklad. No double entry, no spreadsheet glue. The runner's work is billable, the audit trail is intact, and the invoice shows up like any other.

03
receipt_longApproval Pipeline
check_circleLogged → Approved → Billed
schedule

Logged

AI and human work in the same time sheet

check_circle

Approved

Manager reviews, adjusts, signs off

receipt

Billed

Export to Fakturoid or iDoklad in one click

infoOne audit trail from chat to cash
verifiedAudit-ready
dnsMCP Server & AI Integration

One MCP server, two kinds of users

mcptask.online runs a standard Model Context Protocol server. AI coding agents use it to read tasks, log work, open PRs. Managers use it through any MCP client (Claude Desktop, Claude Cowork, Cursor) to assign tasks, ask for a project status, or file a note through chat. No new UI to learn.

For managers: run the project from chat

The same MCP server is a standard interface. Plug it into Claude Desktop, Claude Cowork, Cursor, or any MCP client — assign tasks, ask for a status report, or file a note without learning a new UI.

add_task

Assign a task through chat

summarize

Ask for a project status report

edit_note

File a note that lands on the right task

dns

Native MCP Protocol Support

The Model Context Protocol is how modern AI assistants communicate with external tools. mcptask.online provides a full MCP server implementation, allowing AI agents to read tasks, update status, log work, and more - using their native language.

  • check_circleRead task details, descriptions, and context
  • check_circleList available tasks (filtered by project, status, priority)
  • check_circleUpdate task status (in progress, completed, blocked)
  • check_circleLog work efforts with descriptions
01
visibility

AI Sees Full Task Context

When AI requests a task, it receives complete context: description, acceptance criteria, related tasks, comments, attached files, and history. No manual copy-paste required.

  • check_circleTask name and full description (Markdown supported)
  • check_circleParent epic/story context
  • check_circleRelated tasks and dependencies
  • check_circlePrevious comments and discussions
Benefits
  • arrow_forwardZero context setup time
  • arrow_forwardAI understands full requirements
  • arrow_forwardConsistent information every time
02
smart_toy

AI Fetches Next Task Automatically

Configure your AI agent to operate autonomously: fetch highest-priority available task, complete it, log work, mark done, move to next. Set boundaries (project scope, task types), then let AI work.

  • check_circleAI calls get_next_task() via MCP
  • check_circlemcptask.online returns highest-priority available task
  • check_circleAI works on task
  • check_circleAI calls log_effort() with work description
Configuration
  • arrow_forwardLimit to specific projects
  • arrow_forwardLimit to specific task types
  • arrow_forwardPriority thresholds
03
schedule

Automatic Effort Tracking

Every action AI takes is logged: tasks viewed, work performed, status changes. AI can also explicitly log effort with descriptions, duration, and progress percentage.

  • check_circleTask opened/viewed
  • check_circleStatus changes
  • check_circleComments added
  • check_circleFiles attached
Explicit Logging
  • arrow_forwardWork description
  • arrow_forwardDuration in minutes
  • arrow_forwardProgress percentage
04
groups

Run Multiple AI Agents

Connect unlimited AI agents to your mcptask.online workspace. Each agent identified separately. Work distributed automatically. No conflicts, clear attribution.

  • check_circleEach agent has unique API key
  • check_circleClear identification in logs
  • check_circleWork distribution by project/task type
  • check_circleNo duplicate work (task locking)
Use Cases
  • arrow_forwardDifferent agents for different projects
  • arrow_forwardSpecialized agents (frontend, backend, docs)
  • arrow_forward24/7 coverage with multiple agents
05
claude_desktop_config.json
settingsQuick Setup
{
"mcpServers": {
"mcptask-online": {
"type": "sse",
"name": "McpTask.online",
"url": "https://mcptask.online/mcp/sse",
"headers": {
"Authorization": "Bearer ${MCPTASK_ONLINE_TOKEN}"
}
}
}
}
infoWorks with Claude Desktop, Claude Cowork, Cursor, and other MCP-compatible clients — for both AI coding agents and managers in chat.
timer2 min setup

For developers: why it actually reaches the finish

Reliability that stays invisible during normal operation

verified_user

MCP protocol over SSE (Server-Sent Events)

api

JWT authentication for secure access

key

Pub/Sub messaging for real-time communication

security

Scoped permissions per agent

{ }< />
codeDeveloper Integrations

Connect Your Development Workflow

GitHub, GitLab, and more. Your commits become time entries. Your PRs link to tasks. AI or human - it's all tracked.

code
GitHub

Commits Auto-Log Time

Connect GitHub repositories via webhooks. Commits with task references automatically log time. Pull requests link to tasks. Merges can complete tasks.

1Add mcptask.online webhook to repo
2Developers commit with references: Fix login bug https://mcptask.online/your_company/tasks/47 80%
3Webhook fires on push
4mcptask.online logs progress to Task-47
  • webhookPush (commits) - logs time
  • webhookPull Request opened - links to task
  • webhookPull Request merged - can complete task
timerSetup: 2 minutes
01
merge_type
GitLab

Self-Hosted and Cloud Support

Full GitLab integration with same features as GitHub. Works with GitLab.com and self-hosted GitLab instances.

  • check_circleGitLab.com (SaaS)
  • check_circleGitLab Self-Managed (12.0+)
  • check_circleGitLab Enterprise
  • check_circleIntegration same as GitHub
02
import_export
Jira

Bidirectional Sync with Jira

Import existing Jira projects and sync completed work back. Bidirectional communication keeps both systems synchronized.

  • uploadIssue hierarchy (Epic > Story > Task)
  • uploadDescriptions and comments
  • uploadAttachments
  • uploadSprint assignments
scheduleMigration: 15-30 minutes typical
03
dashboard
Trello

Bidirectional Sync with Trello

Import Trello boards and sync completed work back. Bidirectional communication keeps both systems synchronized.

  • uploadBoards -> Projects
  • uploadLists -> Epics/States
  • uploadCards -> Tasks
  • uploadChecklists -> Subtasks
Mapping Options
  • arrow_forwardLists -> Epics (hierarchical)
  • arrow_forwardLists -> States (flat)
  • arrow_forwardCustom mapping
04
receipt_long
Redmine

Bidirectional Sync with Redmine

Import existing Redmine projects and sync completed work back. Bidirectional communication keeps both systems synchronized.

  • uploadProjects and subprojects
  • uploadIssues (all types)
  • uploadDescriptions and comments
  • uploadAttachments
05
api
REST API

Build Custom Integrations

Full REST API for custom integrations. JWT authentication. Comprehensive documentation. Use alongside or instead of MCP for specific needs.

  • apiProjects — list
  • apiTasks — read & create
  • apiEfforts — full CRUD (log time)
  • apiUsers — read
Rate Limits
rocket_launchstarter1,000 req/hour
verifiedprofessional10,000 req/hour
corporate_fareenterprise100,000 req/hour
menu_bookInteractive API explorer with examples
06
syncIntegration Workflow
auto_modeAutomatic Sync
terminal

Developer Commits

git commit -m "Fix bug #Task-47 2h"

arrow_forward
webhook

Webhook Fires

GitHub/GitLab notifies mcptask

arrow_forward
schedule

Time Logged

2h automatically logged to task

arrow_forward
task_alt

Task Updated

PR merge can complete task

infoWorks with both human developers and AI agents (Claude Code)
flash_onReal-time sync

Commit Message Parsing

Reference tasks and log time directly from your commits

Fix bug #Task-47 2h
check_circle2 hours logged
Add tests #Task-47 30m
check_circle30 minutes logged
#Task-47 Refactored
check_circleAuto-estimated
scheduleTime Tracking & Effort Logging

Track Every Hour (Automatically)

Multiple ways to log time: AI automatic, webhook automatic, timer, manual. All flows to the same place.

smart_toy

AI Logs Its Own Work

When AI agents work through MCP, they log effort automatically. Duration, description, progress - all captured without human intervention.

AI-Logged Data
  • data_objectTask worked on
  • data_objectDuration (estimated or actual)
  • data_objectWork description
  • data_objectProgress percentage
  • data_objectAny blockers
Human Review
  • arrow_forwardView all AI-logged efforts
  • arrow_forwardApprove for billing if needed
  • arrow_forwardAdjust if necessary
  • arrow_forwardFull audit trail
01
commit

Commits = Time Entries

GitHub/GitLab webhooks parse commit messages for time data. Include #Task-47 2h in commit and time is logged automatically.

Parsing Examples
codeFix login bug https://mcptask.online/your_company/tasks/47 80%
arrow_forwardLogged 80% progress
codeImplement feature URL/47 50%
arrow_forwardLogged 50% progress
codeURL/47 Refactored auth 100%
arrow_forwardLogged 100% progress
Works For
  • arrow_forwardHuman developers
  • arrow_forwardAI agents (Claude Code)
  • arrow_forwardCI/CD pipelines
02
timer

Traditional Time Tracking

For work outside code: meetings, design, planning. Enter completion time, start is determined automatically. All work tracked alongside AI work.

Effort Parameters
  • edit_noteCompletion time
  • edit_noteWork description
  • edit_noteCompletion percentage
  • edit_noteAutomatic start determination
Manual Entry
  • arrow_forwardQuick duration entry
  • arrow_forwardBulk entry for past work
  • arrow_forwardDate picker for backdating
03
check_circle

Review Before Billing

Managers can review and approve work before invoicing. See AI-logged vs. human-logged work. Export to PDF, CSV, or invoicing programs.

Report Export
  • file_downloadExport to PDF
  • file_downloadExport to CSV
  • file_downloadExport to .Doklad
  • file_downloadExport to Fakturoid
Filtering
  • arrow_forwardBy person (human/AI)
  • arrow_forwardBy project
  • arrow_forwardBy date range
  • arrow_forwardBy approval status
04
scheduleMultiple Logging Methods
syncAll Sync Together
smart_toy

AI Automatic

MCP agents log work automatically as they complete tasks

auto_modeZero manual input
commit

Webhook Automatic

Commits with task references auto-log time entries

code#Task-47 2h
timer

Timer & Manual

Start/stop timers or add entries manually for any work

touch_appOne-click start
infoAll methods flow to the same unified time log
verifiedReady for billing approval

Effort Approval Flow

Review and approve efforts before invoicing

edit_note

Logged

pending

Pending

check_circle

Approved

receipt

Billed

analyticsReporting & Analytics

Insights on Human and AI Work

Understand where time goes, track AI productivity, and generate client-ready reports.

analytics

Tracking Human and AI Productivity

Dedicated reports on all team member activity: completed tasks, logged hours, completion rate. Compare efficiency across projects.

Metrics
  • analyticsCompleted tasks
  • analyticsLogged hours
  • analyticsAverage task completion time
  • analyticsWork efficiency
01
summarize

Where Did Time Go?

Detailed time reports by project, person (human/AI), task type. Export for invoicing or analysis.

Report Types
  • descriptionBy project
  • descriptionBy person/agent
  • descriptionBy date range
  • descriptionBy task type
Export Formats
PDF (client-ready)CSV (analysis)JSON (API)Fakturoid/iDoklad (Czech invoicing)
02
assessment

Reports

Comprehensive reports for work tracking and attendance. Export for invoicing and internal purposes.

Available Reports
  • assessmentWork Report - also used for invoicing, various filters
  • assessmentWork Attendance - overview of who worked how much during which time period
03
assessmentReport Dashboard
insightsReal-Time Data
smart_toy

AI Work Reports

Track AI productivity, tasks completed, and contribution ratios

analyticsAI vs Human metrics
schedule

Time Reports

Detailed breakdowns by project, person, and task type

downloadMultiple export formats
speed

Sprint Tracking

Burndown charts, velocity metrics, and AI contribution breakdown

trending_upAgile metrics
infoAll reports track both human and AI contributions
file_downloadExport ready
check_circleTable Stakes

Basics you expect from a serious tool

Task hierarchy, real-time collaboration, role-based access, and AI context — the fundamentals are covered, so the differentiators above stand on solid ground.

account_tree

Hierarchical tasks

Epic > Story > Task > Subtask structure

repeat

Recurring tasks

Automated maintenance, reports, and regular work

content_copy

Project templates

Replicate successful project structures

sync_alt

Flexible states

New, In Progress, Blocked, Review, Done

admin_panel_settings

Role-based access

Humans and AI with the right permissions

sync

Real-time updates

See changes instantly without refreshing

chat

In-context discussion

Comments, notes, and file attachments

rss_feed

Activity feed

Track everything in one place

visibility

Full task context

AI sees description, history, and attachments

smart_toy

Autonomous next task

AI fetches and works on the next item

schedule

Automatic logging

AI logs effort as it works

groups

Multiple agents

Connect unlimited AI agents

smart_toy

Ready to Connect Your AI?

All features included. No credit card required.

See how mcptask.online works in practice

Install mcptask_runner and let it pick a real task from your project.

verified_user30-day free trial - Unlimited AI agents - No credit card - GDPR compliant

help_outlineFAQ

Frequently Asked Questions

Q1

Is the MCP server included on all plans?

expand_more

Yes! MCP server access is included on all plans, including the free trial. Connect unlimited AI agents.

Q2

How is mcptask.online different from Jira or Linear?

expand_more

Jira and Linear end at the ticket. Agentic tools (Copilot Workspace, Codex, Claude Code by itself) end at the PR. mcptask.online is the only platform that takes AI work all the way to a billable invoice: time tracking, approval, Fakturoid / iDoklad export, real audit trail. No lock-in to a premium model — the runner is model-agnostic and works with cheap or local models too.

Q3

Can I use mcptask.online without AI?

expand_more

Absolutely! It's a full-featured task manager for humans. The MCP server is there when you're ready for AI. Many teams start human-only and add AI later.

Q4

Does AI work count toward billing?

expand_more

For work you invoice to your clients, Yes. For invoices we send to you, NO.

Q5

Can a manager work with mcptask through chat, not just AI coding agents?

expand_more

Yes. The same MCP server is a standard interface that works in any MCP client — Claude Desktop, Claude Cowork, Cursor, and others. A manager can assign a task, ask for a project status report, or file a note through chat, without learning a new UI. The runner is one of two users of the server; chat-based managers and team leads are the other.

Q6

How much does running an agent cost, and can I use a cheap or local model?

expand_more

Yes. The runner is model-agnostic, so you can use cheap or local models and control your own inference spending. You are not locked into a premium model from a single vendor. The platform fee is separate from your inference costs.