Agent Task Decomposition Engine Connector for AI agents.
3 live capabilities
Turn vague objectives into structured task hierarchies for reliable planning
Waiting for input…
Why people use Agent Task Decomposition Engine
Solving agent planning failures with Agent Task Decomposition Engine
With this MCP, you stop guessing. Instead of fighting with the agent's reasoning, you give it a way to mathematically structure its own work. You get a clean, hierarchical plan that actually makes sense, complete with checks to ensure the agent isn't just spinning its wheels in a logical loop.
What Vinkius changes
You get a mathematically verified plan instead of a vague list of ideas.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,400+ Connectors
- Real-world use case 01
Automating complex software migrations
An engineer asks an agent to migrate a database.
- Real-world use case 02
Managing multi-stage marketing campaigns
A marketer provides a campaign goal.
- Real-world use case 03
Orchestrating multi-agent research teams
A researcher gives a broad topic.
Complete set · 3capabilities
The complete Agent Task Decomposition Engine capability set.
These are the exact actions your AI can choose when you ask it to work with Agent Task Decomposition Engine.
01—03
3 capabilities in this set.
Part of 3 available through Agent Task Decomposition Engine.
- 01 Capability
Analyze complexity
Calculates structural metrics for a task tree to show how hard it is to finish. It helps you understand the workload and parallelism potential.
- 02 Capability
Decompose task
Breaks a large goal into a hierarchy of subtasks and leaf actions. It turns a single prompt into a structured plan.
- 03 Capability
Validate dependencies
Checks the task hierarchy for logical loops. It ensures your agent doesn't get stuck in a cycle of tasks that depend on each other.
Set up in minutes
One URL. Then ask Agent Task Decomposition Engine to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Agent Task Decomposition Engine from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_v4Dy8TTc6YhYZ0YXxilte3cm6yCi43WQr1tyECyJ/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Agent Task Decomposition Engine, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Agent Task Decomposition Engine for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_v4Dy8TTc6YhYZ0YXxilte3cm6yCi43WQr1tyECyJ/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Agent Task Decomposition Engine URL.
- Step 03
Save and start
Save the connection and enable Agent Task Decomposition Engine in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"agent-task-decomposition-engine": {
"url": "https://edge.vinkius.com/vk_preview_v4Dy8TTc6YhYZ0YXxilte3cm6yCi43WQr1tyECyJ/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Agent Task Decomposition Engine
Open Agent mode in chat and ask: "Using Agent Task Decomposition Engine, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"agent-task-decomposition-engine": {
"url": "https://edge.vinkius.com/vk_preview_v4Dy8TTc6YhYZ0YXxilte3cm6yCi43WQr1tyECyJ/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Agent Task Decomposition Engine
Ask Copilot: "Using Agent Task Decomposition Engine, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"agent-task-decomposition-engine": {
"url": "https://edge.vinkius.com/vk_preview_v4Dy8TTc6YhYZ0YXxilte3cm6yCi43WQr1tyECyJ/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Agent Task Decomposition Engine
Open Cascade and ask: "Using Agent Task Decomposition Engine, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"agent-task-decomposition-engine": {
"url": "https://edge.vinkius.com/vk_preview_v4Dy8TTc6YhYZ0YXxilte3cm6yCi43WQr1tyECyJ/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Agent Task Decomposition Engine
Ask Cline: "Using Agent Task Decomposition Engine, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add agent-task-decomposition-engine --transport http "https://edge.vinkius.com/vk_preview_v4Dy8TTc6YhYZ0YXxilte3cm6yCi43WQr1tyECyJ/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Agent Task Decomposition Engine
Ask Claude: "Using Agent Task Decomposition Engine, show me...". 3 tools are ready
Where the request belongs
Work Agent Task Decomposition Engine can move forward.
This is for anyone building autonomous workflows or complex agentic systems that need to move from 'thinking' to 'doing' without getting lost.
AI Engineer
Building multi-step agentic workflows that require reliable planning and execution.
Product Manager
Breaking down product requirements into technical implementation roadmaps.
Automation Architect
Designing complex business processes that need to be split across multiple workers.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectors
Critical Thinking Prover
AI agents accept premises without questioning, analyze from one perspective, cherry-pick evidence, ignore consequences, and present uncertainty as certainty. This capability forces rigor: surface assumptions, apply competing frameworks, weigh counterevidence, trace ripple effects, bound confidence.
GitScrum Tasks
Master task execution via GitScrum. create, filter, assign, and track tasks with subtasks, checklists, and comments directly from any AI agent.
Agent Parallel Execution Optimizer
Optimize task distribution and efficiency metrics for agent swarms.
Structured
Connect your AI to Structured. Programmatically manage your daily planner, tasks, and routines seamlessly directly from your terminal.
DAG Topological Scheduler
Deterministic task scheduling and critical path analysis for multi-agent DAGs.
Workflow State Machine Validator
Verify the structural integrity and execution safety of agentic workflows using FSM validation.
Bring your own AI
Change the model, client or framework. Keep Agent Task Decomposition Engine connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Agent Task Decomposition Engine.
The practical details behind the request, access and result.
How does the Agent Task Decomposition Engine help with agent planning?
It provides a structured way to turn a single, large goal into a organized tree of smaller, manageable subtasks that an agent can follow without getting lost.
Can I use the Agent Task Decomposition Engine to find errors in my AI workflows?
Yes. You can use it to check your task structures for logical loops or circular dependencies that would otherwise cause an agent to get stuck in an infinite loop.
Will the Agent Task Decomposition Engine make my AI agents faster?
It can. By calculating the parallelism potential of a task tree, it identifies which parts of a plan can be executed at the same time, rather than one by one.
Is the Agent Task Decomposition Engine compatible with Claude or Cursor?
Yes, it works with any MCP-compatible client, including Claude, Cursor, and Windsurf.
How do I know if a task is too hard for my agent?
You can use the complexity scoring features to get a mathematical sense of how difficult a goal is, helping you decide if it needs to be broken down further.
One connection away
Give your agent a direct line to Agent Task Decomposition Engine.
Connect Agent Task Decomposition Engine once. Keep it beside 6,400+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available