Stop Copy-Pasting Task Context to AI
mcptask.online is an MCP-native project tracker. Claude Code, Claude Desktop, and any MCP-compatible assistant can read your tasks and log work directly — no copy-paste, no lost context.
Acceptance Criteria: User can login...
✓ Acceptance criteria
✓ Related tasks
✓ Attachments
What You Need
Three things. No Ruby, no servers, no CLI magic. A free mcptask.online account is enough to try it today.
An MCP-capable AI client
Any client that speaks the Model Context Protocol — the open standard Claude Code uses to connect to external tools.
Examples: Claude Code, Claude Desktop, Cursor, Cline, Continue.
A free mcptask.online account
Sign up, create a project, add a few tasks. Two minutes.
No credit card. 30-day Professional trial on every new account.
An MCPTASK_TOKEN from Settings → API Access
A long secret string that proves the agent is acting as you. Treat it like a password — anyone with it can act as you on mcptask.online.
Free on every plan. Generate one in a click, revoke it the same way.
Optional for autonomous overnight loops: the `mcptask_runner` gem (Rails projects only) — see the install guide.
AI Reads Tasks Directly via MCP
How It Works
Set Up the MCP Connection
Add this entry to your client's MCP config (for Claude Code: `.mcp.json` in your project root; for Claude Desktop: Settings → Developer → Edit Config). The endpoint, transport, and auth header are exactly what every MCP-native client expects.
{
"mcpServers": {
"mcptask-online": {
"type": "sse",
"url": "https://mcptask.online/mcp/sse",
"headers": { "Authorization": "Bearer ${MCPTASK_TOKEN}" }
}
}
}
- 1Sign up at mcptask.online (free, 30-day Professional trial)
- 2Open Settings → API Access → click "Generate token"
- 3Copy the token, then `export MCPTASK_TOKEN=mcptask_...` in your shell (or add it to ~/.zshrc / ~/.bashrc)
- 4Paste the config above into `.mcp.json` (or your client's MCP settings)
- 5Restart your AI client
- 6Ask the agent: "List the next open task from my mcptask.online project."
Where this goes: `.mcp.json` (Claude Code) or the developer's MCP config dialog (Claude Desktop, Cursor, Cline). The `${MCPTASK_TOKEN}` reference is resolved from the environment variable — export it once in your shell profile so every client picks it up.
Ask the AI to Read a Task
In plain English, ask the agent to work on something. The agent resolves `mcptask://pieces/{account_code}/{piece_id}` against mcptask.online over MCP — no copy-paste.
"Read task #47 and implement the login feature"The URI pattern is the canonical read entry point. Everything in mcptask.online is a **piece** — tasks, stories, epics, recurents, projects — and they all share the same `mcptask://pieces/{account_code}/{id}` shape.
mcptask://pieces/jchsoft/10575AI Gets Full Context Automatically
AI receives:
- Piece name and full description
- Parent epic/story context
- Acceptance criteria
- Related pieces and dependencies
- All comments and discussion
- Attached files (specs, designs)
- Work history
AI Logs Work Automatically
When done, the agent calls MCP to log progress — duration, what changed, status, blockers. You can ask it to log, or you can run the optional `mcptask_runner` gem that handles the autonomous loop end-to-end.
- Log time spent
- Describe what was done
- Update task status
- Add notes and blockers
Note: Plain MCP access does not log work on its own — the agent has to call the log tool, or the runner has to drive it. Zero-effort logging is a property of a well-instructed agent or the runner, not of MCP itself.
Zero manual context setup. Zero manual logging — when the agent (or runner) does the logging.
The AI Context Problem
Manual Context Setup Every Time
Every Claude Code session starts the same:
- Copy task description
- Paste into chat
- Copy acceptance criteria
- Paste into chat
- Explain the context
- Finally start working
No Automatic Work Logging
AI helped you fix 5 bugs today. But your task system shows nothing. You spend 30 minutes at day's end reconstructing what AI did and logging it manually.
Lost Data:
- What AI actually implemented
- Time spent per task
- Context for future reference
Inconsistent Context
Sometimes you copy the full task. Sometimes you summarize. Sometimes you forget related tasks. AI works with incomplete information. Results vary.
Consequences:
- AI misses requirements
- Rework needed
- Frustration
No Audit Trail
Manager asks: "What exactly did the AI help with this sprint?"
You have: scattered chat logs, fuzzy memories, no structured data.
Impact:
- Can't justify AI tool costs
- No visibility into AI productivity
- No metrics for improvement
Feature Highlights
Complete Piece Context
What AI Receives:
- Piece name and full description
- Parent epic/story context
- Acceptance criteria
- Related pieces and dependencies
- All comments and discussion
- Attached files (specs, designs)
- Work history
Benefit:
AI understands the full picture, not just a snippet.
Automatic Work Logging
AI Logs (when instructed, or via mcptask_runner):
- Piece worked on
- Duration (estimated from session)
- What was implemented
- Progress percentage
- Any blockers encountered
Human Effort:
Zero — once you tell the agent (or runner) to log, it logs. Plain MCP reads do not log on their own.
Consistent Workflow
Every Session:
- 1AI reads piece from MCP
- 2AI works on piece
- 3AI logs completion via MCP
- 4Human reviews when convenient
No more:
Copy-paste ceremonies, forgotten logging, inconsistent context.
Clear Attribution
Every Action Tagged:
"Effort logged by Claude-Code-1"
"Status changed by AI Agent"
"Comment added by AI Assistant"
Benefit:
Always know what AI did vs. what human did.
Workflow Examples
Bug Fix Session
Before mcptask.online:
- 1Open Jira, find bug ticket (2 min)
- 2Copy description, paste to Claude (1 min)
- 3Copy steps to reproduce (1 min)
- 4Claude investigates and fixes (15 min)
- 5Manually log time in Jira (2 min)
- 6Update ticket status (1 min)
With mcptask.online:
- 1Tell Claude "work on bug #47" (10 sec)
- 2Claude reads piece via MCP automatically
- 3Claude investigates and fixes (15 min)
- 4Claude logs work via MCP automatically
Feature Implementation
Before mcptask.online:
- 1Read epic and stories in Jira (5 min)
- 2Copy relevant context to Claude (3 min)
- 3Discuss approach with Claude (5 min)
- 4Claude implements feature (30 min)
- 5Manually document what was done (5 min)
- 6Log time across multiple tasks (3 min)
With mcptask.online:
- 1Tell Claude "implement story #23" (10 sec)
- 2Claude reads story and all subtasks via MCP
- 3Discuss approach with Claude (5 min)
- 4Claude implements feature (30 min)
- 5Claude logs work automatically via MCP
Illustrative Example
Note: The quote and numbers below are illustrative. We use them to show what an MCP-native workflow looks like in practice — we have not collected this testimonial from a named user.
Claude Code is much more useful when it can read the full task context, understand the requirements, and log its own work. I haven't copy-pasted a task description in months.
Illustrative — full-stack developer
Full-Stack Developer
Using Claude Code with mcptask.online
What the workflow looks like
Context setup time:
5 min → 10 seconds (example)
Work logging time:
30 min/day → 0 (when the agent logs)
AI productivity:
Better context → better output (qualitative)
Audit trail:
Every MCP action is logged with full attribution
Technical Details
Supported AI Tools
Fully Compatible (MCP-native):
- Claude Code (Anthropic)
- Claude Desktop
- Cursor, Cline, Continue, and any MCP-compatible assistant
Via REST API:
- Custom AI agents
- Tools that do not speak MCP yet
MCP Capabilities
Read:
- Pieces (tasks, stories, epics, recurents, projects)
- Comments and attachments
- Project structure
- Work history
Write (when the agent decides to):
- Log efforts
- Update status
- Add comments
- Create or complete pieces
Security
Access Control:
- One MCPTASK_TOKEN per agent or per user
- Scoped permissions (read-only tokens available)
- Project-level access reflects your account membership
- Token rate limits per token
Audit:
- Every MCP action is logged
- Full attribution (which token, when, what)
- Exportable history
Pricing for AI Teams
Live prices are loaded from the Tariff model (Settings → Tariffs), so this page never drifts from what checkout charges.
Starter
- 5 projects
- Unlimited pieces
- MCP server access
- GitHub/GitLab webhooks
- 1 user + 1 AI agent
Best For:
Solo developers using AI daily
Professional
- Unlimited projects
- Unlimited team members
- Advanced MCP features
- Sprint management
- AI work approval workflow
- Advanced reporting
Best For:
Teams where everyone uses AI assistants
MCP access for AI agents is free on every plan. You only pay for account users.
FAQ
Where do I find my MCPTASK_TOKEN?
Log in to mcptask.online, open Settings → API Access, and click "Generate token". Copy the long string. Treat it like a password — anyone with it can act as you on mcptask.online. You can revoke it the same way.
What is MCP?
MCP — Model Context Protocol — is the open standard Claude Code (and other MCP-native clients) use to connect to external tools. mcptask.online runs an MCP server at https://mcptask.online/mcp/sse, so any MCP-compatible client can read and write your project data with one config entry.
Do I need to install anything?
For the basic read/write flow: no. A free mcptask.online account, an MCP-compatible client, and a token are enough. For the fully-autonomous daily loop (an agent picking up today's tasks on its own), the optional `mcptask_runner` gem is a one-line addition in a Rails project — see the install guide.
Which AI tools support MCP?
Claude Code, Claude Desktop, Cursor, Cline, Continue, and a growing list of MCP-native clients. If your tool speaks MCP, mcptask.online works with it. If not, use the REST API.
Is the mcptask_runner required?
No. The runner is a convenience wrapper for the fully-autonomous loop in a Rails project. Plain MCP read and write works without it, on any stack.
What is a "piece"?
A piece is the generic name for everything in mcptask.online: tasks, stories, epics, recurents, and projects. The MCP URI is always `mcptask://pieces/{account_code}/{piece_id}` — there are no separate `/tasks/` or `/stories/` paths.
Can AI create pieces?
Yes, if you grant that permission. The MCP write tools let the agent create pieces, subtasks, and comments. You can scope tokens to read-only if you do not want that.
Is AI access logged?
Every MCP action is logged with full attribution — which token, when, what changed. You always know what AI did.
Do I need to change my workflow?
Minimally. You ask the AI to read pieces instead of copy-pasting, and (optionally) to log work when done. Everything else improves automatically.
Give Your AI Assistant the Context It Needs
30-day free Professional trial. MCP server included. Connect Claude Code in five minutes.
No credit card. Unlimited MCP actions. Cancel anytime.