Task Graph MCP
T

Task Graph MCP

Task Graph MCP Server is an MCP server that provides structured workflows and coordination functions for AI agents, supporting task hierarchy, dependency management, phase division, quality gating, and multi-agent coordination without external infrastructure.
2 points
6.6K

What is Task Graph MCP Server?

Task Graph MCP Server is a task coordination and workflow management system specifically designed for AI agents. It helps multiple AI agents collaborate to complete complex tasks through structured workflows, avoiding common coordination issues such as context loss, step skipping, and work conflicts.

How to use Task Graph MCP Server?

Using Task Graph is very simple: 1) Install the MCP server, 2) Configure it to your AI client (such as Claude Code), 3) Agents connect and start collaborating. The system provides pre-built workflow templates (such as solo, swarm, relay, etc.), and agents can automatically obtain tasks, coordinate file access, and track progress.

Applicable Scenarios

Task Graph is particularly suitable for the following scenarios: - Multi-agent collaborative development projects - Decomposition and execution of complex tasks - Automated processes requiring quality assurance - Team workflow management and coordination - Experimental AI workflow orchestration

Main Features

Structured Workflows
Provide phased workflows (exploration, implementation, review, testing) to guide agents to work step by step. Each phase has automated transition prompts to ensure that agents do not deviate from the track.
Quality Gating
Enforce quality standards when task status or phase transitions occur. For example, require tests to pass, code to be submitted, or reviews to be completed before moving to the next phase to ensure work quality.
Multi-agent Coordination
Support multiple AI agents working simultaneously, avoiding conflicts and duplicate work through file advisory locks, DAG dependencies, and atomic task claiming mechanisms.
Pre-built Workflow Templates
Provide a variety of ready-made workflow topologies: solo (single agent), swarm (parallel group), relay (expert relay), hierarchical (hierarchical delegation), which can be used out of the box.
Token and Cost Tracking
Automatically track the token usage, dollar cost, and execution time of each task, providing detailed cost accounting and performance analysis.
File Coordination
Agents can mark files to indicate work intentions, and other agents can see these marks and avoid conflicts, supporting change polling and reason explanations.
Tag-based Routing
Route tasks to agents with corresponding capabilities through a tag system. Tasks can require specific tag combinations (AND/OR conditions) to ensure that the right agents handle the right tasks.
Zero Infrastructure Dependency
Use an SQLite database without running a database server. Single-file deployment, supporting WAL mode for multi-process concurrent access, and working completely offline.
Advantages
Out-of-the-box workflow management without building a coordination system from scratch
Support for complex multi-agent collaboration scenarios, avoiding work conflicts
Built-in quality control and progress tracking to improve work reliability
Lightweight deployment without additional infrastructure
Detailed cost and time tracking for easy analysis and optimization
Flexible configuration system to customize workflows according to needs
Limitations
Requires AI clients to support the MCP protocol
May seem too complex for simple tasks
Steep configuration learning curve, requiring an understanding of workflow concepts
Currently mainly targeted at technical users and developers
File coordination is advisory and does not provide mandatory locking

How to Use

Install the Server
Install via cargo or download the pre-compiled binary file
Configure the MCP Client
Add the Task Graph server to the configuration file of your AI client (such as Claude Code)
Create a Configuration File
Create a .task-graph/config.yaml file in the project directory to configure workflows, states, and dependencies
Agent Connection
AI agents connect to the server, select a workflow, and declare capability tags
Create and Manage Tasks
Create a task tree, set dependencies, and agents claim and execute tasks

Usage Examples

Multi-agent Code Development
Three AI agents collaborate to develop a web application: one is responsible for the front end, one for the back-end API, and one for testing.
Quality Assurance Process
Implement automated quality gating for code review and testing to ensure code quality.
File Coordination to Avoid Conflicts
Multiple agents need to edit the same configuration file and coordinate access through file marking.
Hierarchical Task Decomposition
Decompose a large project into a hierarchical task tree for easy management and distribution.

Frequently Asked Questions

Is Task Graph suitable for single AI agents?
Do I need to run a database server?
How to prevent work conflicts between agents?
Can I customize workflows?
Which AI clients are supported?
How to track costs and performance?
Is file coordination mandatory?
How complex can task relationships be?

Related Resources

GitHub Repository
Source code, issue tracking, and release versions
Complete Configuration Documentation
Detailed configuration file reference, including workflow, prompt, gating, and tag configuration
Database Schema Documentation
Database table structure, state machine design, and data relationships
Workflow Topology Guide
Detailed explanation of multi-agent workflow patterns: solo, swarm, relay, hierarchical, etc.
Model Context Protocol
Official documentation and specifications of the MCP protocol
Release Version Download
Pre-compiled binary files, supporting Linux, macOS, and Windows

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "task-graph": {
      "command": "task-graph-mcp"
    }
  }
}

{
  "mcpServers": {
    "task-graph": {
      "command": "task-graph-mcp",
      "args": []
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
9.6K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
10.2K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
15.0K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
7.9K
4 points
P
Paperbanana
Python
9.1K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
9.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
9.1K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
9.1K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
28.6K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
23.1K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
82.2K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
39.3K
5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
38.6K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
71.1K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
55.6K
4.8 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
108.0K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase