TaskFabric
Provides version control for tasks, with automatic commits on every mutation and support for remote repositories.
Allows syncing tasks to a GitHub repository for backup, collaboration, and history tracking using a fine-grained personal access token.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TaskFabriclist tasks tagged urgent"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TaskFabric
A file-based task manager operated entirely through an MCP server over Streamable HTTP. Every task is a markdown file with YAML frontmatter, indexed via QMD for hybrid semantic + keyword search, and git-synced for versioning. No UI — agents are the only interface.
How it works
Tasks live as plain markdown files organized by status:
/tasks/
├── inbox/ # New, untriaged tasks
├── active/ # Currently being worked on
├── waiting/ # Blocked or waiting
├── done/2026-03/ # Completed (monthly subdirs)
└── archived/2026-03/ # Old tasks (monthly subdirs)Each task has YAML frontmatter (id, title, status, priority, tags, due, assignee, completed_at, waiting_on, dependencies) and a markdown body with free-form content and a ## Log section for timestamped entries. Filenames include the task ID to prevent collisions on duplicate titles.
Every mutation auto-commits to git and pushes to a remote, so all changes are versioned and recoverable.
Related MCP server: TasksMultiServer
MCP Tools
Category | Tools |
CRUD |
|
Search |
|
Workflow |
|
Views |
|
Maintenance |
|
Sync |
|
Settings |
|
Setup
Environment Variables
Variable | Required | Description |
| Yes | Path to the tasks directory |
| Yes | Bearer token for MCP authentication |
| Yes | Git commit author name |
| Yes | Git commit author email |
| No | Git remote URL (clones on first start) |
| No | GitHub PAT for private repos (fine-grained PAT with Contents read/write) |
| No | Server port (default: 8181) |
Run locally
bun install
TASKS_DIR=./tasks API_KEY=your-secret GIT_USER_NAME="Your Name" GIT_USER_EMAIL="you@example.com" bun run src/server.tsRun with Docker
Create a .env file:
API_KEY=your-secret
GIT_USER_NAME=Your Name
GIT_USER_EMAIL=you@example.com
TASKS_REPO_URL=https://github.com/you/your-tasks-repo.git
GIT_TOKEN=ghp_your_github_patdocker compose up --buildThe server starts at http://localhost:8181 with:
/mcp— MCP endpoint (requiresAuthorization: Bearer <API_KEY>)/health— Health check (returns{ "status": "ready" })
Connect MCP Clients
Claude Code (CLI)
claude mcp add --transport http task-fabric http://localhost:8181/mcp \
--header "Authorization: Bearer your-secret"Or add to .mcp.json in your project root:
{
"mcpServers": {
"task-fabric": {
"type": "http",
"url": "http://localhost:8181/mcp",
"headers": {
"Authorization": "Bearer your-secret"
}
}
}
}Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"task-fabric": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8181/mcp",
"--header",
"Authorization: Bearer your-secret"
]
}
}
}Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"task-fabric": {
"type": "streamable-http",
"url": "http://localhost:8181/mcp",
"headers": {
"Authorization": "Bearer your-secret"
}
}
}
}OpenAI Codex CLI
Add to ~/.codex/config.toml:
[mcp_servers.task-fabric]
command = "http://localhost:8181/mcp"
http_headers = { "Authorization" = "Bearer your-secret" }Or use an environment variable for the token:
[mcp_servers.task-fabric]
command = "http://localhost:8181/mcp"
bearer_token_env_var = "TASK_FABRIC_API_KEY"Tests
bun test # All tests (159)
bun test src/__tests__/e2e/ # E2E tests (MCP protocol + HTTP)
bun test src/__tests__/tools/ # Integration testsStack
Runtime: Bun
MCP:
@modelcontextprotocol/sdk(Streamable HTTP)Search:
@tobilu/qmd(BM25 + vector + LLM re-ranking)Git:
simple-gitFrontmatter:
gray-matterValidation: Zod
This server cannot be deployed
Maintenance
Related MCP Connectors
- DazbenchOAuthapp.dazbench
Task management your AI agents can actually run. One line becomes a context-ready task over MCP.
Shared task layer for AI coding agents. One MCP surface: task_search, task_get, task_mutate.
Work management where AI agents are first-class members: tasks, projects, memory over hosted MCP
MCP Server for an Agent Task Marketplace
Related MCP Servers
- AlicenseAqualityBmaintenanceA comprehensive and efficient Model Context Protocol server for task management that works with Claude, Cursor, and other MCP clients, providing powerful search, filtering, and organization capabilities across multiple file formats.5145 npm47MIT
- AlicenseAqualityCmaintenanceMulti-interface task management system that enables AI agents and users to manage hierarchical tasks (projects, task lists, tasks) with dependency tracking, tags, and search through MCP Server, REST API, or React UI.23MIT
- AlicenseNot gradedqualityDmaintenanceA file-backed MCP server for hierarchical project management that enables AI assistants to create, claim, and complete tasks within a project→epic→feature→task structure, with dependency management and Markdown-based storage.MIT
- FlicenseNot gradedqualityCmaintenanceMCP server for managing a project backlog as Markdown files in Git, enabling AI agents to read, create, and update tasks programmatically.2-