Task Graph MCP Server

Agent task workflows that actually work.

When you have AI agents working on complex tasks, things go wrong fast. Agents lose context, skip steps, forget to coordinate. Task Graph solves this with structured workflows: phases to guide work, prompts for automatic guidance, gates to enforce quality, and coordination primitives for multi-agent scenarios—all through the Model Context Protocol.

Why Task Graph?

The problem: You've got complex tasks that need structured execution. Maybe a single agent working through phases, or multiple agents coordinating in parallel. Without proper workflows, agents lose track, skip steps, and produce inconsistent results.

What you get:

Structured workflows — Phases (explore, implement, review, test) guide agents through work. Transition prompts provide automatic guidance at each step.
Quality gates — Require tests to pass, code to be committed, or reviews to complete before transitions. Enforce your standards automatically.
Ready-to-use topologies — Pre-built workflows for solo work, parallel swarms, specialist relays, or hierarchical delegation. Start immediately, customize later.
Configurable workflows — Define your own states, phases, prompts, and gates. Match your process, not ours.
Multi-agent coordination — Advisory file locks, DAG dependencies, atomic claiming. No more conflicts or duplicate work.
Token-efficient — Designed for LLM context limits. Compact queries, minimal round-trips, structured outputs.
Built-in accounting — Track tokens, cost, and time per task. Know exactly what your agents are spending.
Zero infrastructure — SQLite with WAL mode. No database server to run. Just point at a file.

Features

Feature	Description
Task Hierarchy	Unlimited nesting with parent/child relationships
DAG Dependencies	Typed edges (blocks, follows, contains) with cycle detection
Phases	Categorize work type (explore, implement, review, test, deploy)
Workflows	Named workflow topologies (solo, swarm, relay, hierarchical)
Transition Prompts	Automatic agent guidance on status/phase changes
Gates	Exit requirements for status/phase transitions
Atomic Claiming	Strict locking with limits and tag-based routing
File Coordination	Advisory locks with reasons and change polling
Cost Tracking	Token usage and USD cost per task
Time Tracking	Automatic accumulation from state transitions
Live Status	Real-time "current thought" visible to other agents
Full-text Search	FTS5-powered search across tasks and attachments
Attachments	Inline content, file references, or media storage

Quick Start

# Install

cargo install task-graph-mcp


# Add to your MCP client (Claude Code, etc.)

{
  "mcpServers": {
    "task-graph": {
      "command": "task-graph-mcp"
    }
  }
}

# Agent workflow (worker_id auto-generated if omitted)
connect(workflow="swarm", tags=["code"])                 → "bright-lunar-swift-fox"
list_tasks(ready=true, agent="bright-lunar-swift-fox")   → claimable work
claim(worker_id="bright-lunar-swift-fox", task="add-auth")  → you own it
update(..., phase="implement")                           → enter implementation phase
thinking(agent="bright-lunar-swift-fox", thought="Adding JWT...")  → visible to others
update(worker_id="bright-lunar-swift-fox", task="add-auth",
       status="completed",
       attachments=[{type:"commit", content:"abc123"}])  → done

Installation

From crates.io (Recommended)

cargo install task-graph-mcp

Pre-built Binaries

Download the latest release for your platform from GitHub Releases:

Platform	Download
Linux (x64)	`task-graph-mcp-x86_64-unknown-linux-gnu.tar.gz`
macOS (Intel)	`task-graph-mcp-x86_64-apple-darwin.tar.gz`
macOS (Apple Silicon)	`task-graph-mcp-aarch64-apple-darwin.tar.gz`
Windows (x64)	`task-graph-mcp-x86_64-pc-windows-msvc.zip`

Extract and place the binary in your PATH.

From Source

git clone https://github.com/Oortonaut/task-graph-mcp.git

cd task-graph-mcp

cargo build --release

The binary will be at target/release/task-graph-mcp.

Usage

As an MCP Server

Add to your MCP client configuration:

{
  "mcpServers": {
    "task-graph": {
      "command": "task-graph-mcp",
      "args": []
    }
  }
}

CLI Options

task-graph-mcp [OPTIONS]

Options:
  -c, --config <FILE>     Path to configuration file
  -d, --database <FILE>   Path to database file (overrides config)
  -v, --verbose           Enable verbose logging
  -h, --help              Print help
  -V, --version           Print version

Configuration

Full reference: See docs/CONFIGURATION.md for complete configuration documentation including workflows, prompts, gates, roles, and tags.

Create .task-graph/config.yaml:

server:
  db_path: .task-graph/tasks.db
  media_dir: .task-graph/media  # Directory for file attachments
  skills_dir: .task-graph/skills  # Custom skill overrides
  stale_timeout_seconds: 900
  default_format: json  # or markdown

paths:
  style: relative  # or project_prefixed

auto_advance:
  enabled: false        # Auto-transition unblocked tasks
  target_state: ready   # Target state (requires custom state in states config)

States Configuration

Task states are configurable. Default states: pending, working, completed, failed, cancelled.

To add a ready state for auto-advance:

states:
  initial: pending
  disconnect_state: pending  # State for tasks when owner disconnects (must be untimed)
  blocking_states: [pending, working]
  definitions:
    pending:
      exits: [ready, working, cancelled]
    ready:
      exits: [working, cancelled]
    working:
      exits: [completed, failed, pending]
      timed: true    # Time in this state counts toward time_actual_ms
    completed:
      exits: []
    failed:
      exits: [pending]
    cancelled:
      exits: []

auto_advance:
  enabled: true
  target_state: ready

See SCHEMA.md for full documentation on state definitions.

Dependencies Configuration

Dependency types define how tasks relate to each other. Default types: blocks, follows, contains, duplicate, see-also.

dependencies:
  definitions:
    blocks:
      display: horizontal  # Same-level relationship
      blocks: start        # Blocks claiming the dependent task
    follows:
      display: horizontal
      blocks: start
    contains:
      display: vertical    # Parent-child relationship
      blocks: completion   # Blocks completing the parent
    duplicate:
      display: horizontal
      blocks: none         # Informational only
    see-also:
      display: horizontal
      blocks: none

Property	Values	Description
`display`	`horizontal`, `vertical`	Visual relationship (same-level vs parent-child)
`blocks`	`none`, `start`, `completion`	What the dependency blocks

Attachments Configuration

Preconfigured attachment keys provide default MIME types and modes, reducing boilerplate when attaching common content types.

attachments:
  unknown_key: warn  # allow | warn (default) | reject
  definitions:
    commit:
      mime: text/git.hash
      mode: append
    checkin:
      mime: text/p4.changelist
      mode: append
    meta:
      mime: application/json
      mode: replace
    note:
      mime: text/plain
      mode: append

Property	Values	Description
`unknown_key`	`allow`, `warn`, `reject`	Behavior for undefined attachment keys
`definitions.<key>.mime`	MIME type string	Default MIME type for this key
`definitions.<key>.mode`	`append`, `replace`	Default mode (append keeps existing, replace overwrites)

Built-in defaults:

Key	MIME Type	Mode	Use Case
`commit`	text/git.hash	append	Git commit hashes
`checkin`	text/p4.changelist	append	Perforce changelists
`changelist`	text/plain	append	Files changed
`meta`	application/json	replace	Structured metadata
`note`	text/plain	append	General notes
`log`	text/plain	append	Log output
`error`	text/plain	append	Error messages
`output`	text/plain	append	Command/tool output
`diff`	text/x-diff	append	Patches and diffs
`plan`	text/markdown	replace	Plans and specs
`result`	application/json	replace	Structured results
`context`	text/plain	replace	Current context/state

Usage:

# MIME and mode auto-filled from config:
attach(task="123", name="commit", content="abc1234")
# → mime=text/git.hash, mode=append

attach(task="123", name="meta", content='{"v":1}')
# → mime=application/json, mode=replace (overwrites existing meta)

# Explicit values override defaults:
attach(task="123", name="commit", mime="text/plain", content="override")

Environment variables:

TASK_GRAPH_CONFIG_PATH: Path to configuration file (takes precedence over .task-graph/config.yaml)
TASK_GRAPH_DB_PATH: Database file path (fallback if no config file)
TASK_GRAPH_MEDIA_DIR: Media directory for file attachments (fallback if no config file)
TASK_GRAPH_LOG_DIR: Log directory path (fallback if no config file)

MCP Tools

Worker Management

Tool	Description
`connect(worker_id?, tags?, workflow?, force?, db_path?, media_dir?, log_dir?, config_path?)`	Register a worker. Optional `workflow` selects named workflow (solo, swarm, relay, hierarchical). Returns `worker_id` and active `paths`.
`disconnect(worker_id: worker_str, final_status?: status_str = "pending")`	Unregister worker and release all claims/locks.
`list_workers(tags?: str[], file?: filename, task?: task_str, depth?: int)`	List connected workers with filters.

Task CRUD

Tool	Description
`create(description: str, id?: task_str, parent?: task_str, priority?: int = 5, points?: int, time_estimate_ms?: int, tags?: str[])`	Create a task. Priority 0-10 (higher = more important).
`create_tree(tree, parent?, child_type?, sibling_type?)`	Create nested task tree. `child_type` (default: "contains") for parent→child deps, `sibling_type` for sibling deps.
`get(task: task_str)`	Get task by ID with attachment metadata and counts.
`list_tasks(status?: status_str[], ready?: bool, blocked?: bool, claimed?: bool, owner?: worker_str, parent?: task_str, worker_id?: worker_str, tags_any?: str[], tags_all?: str[], sort_by?: str, sort_order?: str, limit?: int)`	Query tasks with filters. Use `ready=true` for claimable tasks.
`update(worker_id: worker_str, task: task_str, status?: status_str, phase?: str, assignee?: worker_str, title?: str, description?: str, priority?: int, points?: int, tags?: str[], needed_tags?: str[], wanted_tags?: str[], time_estimate_ms?: int, reason?: str, force?: bool, attachments?: object[])`	Update task. Status/phase changes auto-manage ownership and trigger prompts. Include `attachments` to record commits/changelists.
`delete(worker_id: worker_str, task: task_str, cascade?: bool, reason?: str, obliterate?: bool, force?: bool)`	Delete task. Soft delete by default; `obliterate=true` for permanent.
`scan(task: task_str, before?: int, after?: int, above?: int, below?: int)`	Scan task graph in multiple directions. Depth: 0=none, N=levels, -1=all.
`search(query: str, limit?: int = 20, include_attachments?: bool, status_filter?: status_str)`	FTS5 search. Supports phrases, prefix*, AND/OR/NOT, title:word.

Task Claiming

Tool	Description
`claim(worker_id: worker_str, task: task_str, force?: bool)`	Claim a task. Fails if deps unsatisfied, at limit, or lacks tags. Use `force` to steal.

Note: Release via update(status="pending"). Complete via update(status="completed"). Status changes auto-manage ownership.

Dependencies

Tool	Description
`link(from: task_str\|task_str[], to: task_str\|task_str[], type?: dep_str = "blocks")`	Create dependencies. Types: blocks, follows, contains, duplicate, see-also.
`unlink(from: task_str\|"", to: task_str\|"", type?: dep_str)`	Remove dependencies. Use `*` as wildcard.
`relink(prev_from: task_str[], prev_to: task_str[], from: task_str[], to: task_str[], type?: dep_str = "contains")`	Atomically move dependencies (unlink then link).

Tracking

Tool	Description
`thinking(worker_id: worker_str, thought: str, tasks?: task_str[])`	Broadcast live status. Visible to other workers. Refreshes heartbeat.
`task_history(task: task_str, states?: status_str[])`	Get status transition history with time tracking.
`project_history(from?: datetime_str, to?: datetime_str, states?: status_str[], limit?: int = 100)`	Project-wide history with date range filters.
`log_metrics(worker_id: worker_str, task: task_str, cost_usd?: float, values?: int[8])`	Log metrics (aggregated).
`get_metrics(task: task_str\|task_str[])`	Get metrics for task(s).

File Coordination

Tool	Description
`mark_file(worker_id: worker_str, file: filename\|filename[], task?: task_str, reason?: str)`	Mark file(s) to signal intent. Advisory, non-blocking.
`unmark_file(worker_id: worker_str, file?: filename\|filename[]\|"*", task?: task_str, reason?: str)`	Remove marks. Use `*` for all.
`list_marks(files?: filename[], worker_id?: worker_str, task?: task_str)`	Get current file marks.
`mark_updates(worker_id: worker_str)`	Poll for mark changes since last call.

Attachments

Tool	Description
`attach(task: task_str\|task_str[], name: str, content?: str, mime?: mime_str, file?: filename, store_as_file?: bool, mode?: str)`	Add attachment. Use `file` for reference, `store_as_file` for media storage.
`attachments(task: task_str, name?: str, mime?: mime_str)`	Get attachment metadata. Glob patterns supported for name.
`detach(worker_id: worker_str, task: task_str, name: str, delete_file?: bool)`	Delete attachment by name.

Advanced

Tool	Description
`check_gates(task: task_str)`	Check gate requirements before status/phase transition. Returns unsatisfied gates with pass/warn/fail status.
`query(sql: str, params?: str[], limit?: int = 100, format?: str)`	Execute read-only SQL. SELECT only. Requires permission.

MCP Resources

URI	Description
`tasks://all`	Full task graph with dependencies
`tasks://ready`	Tasks ready to claim
`tasks://blocked`	Tasks blocked by dependencies
`tasks://claimed`	All claimed tasks
`tasks://worker/{id}`	Tasks owned by a worker
`tasks://tree/{id}`	Task with all descendants
`files://marks`	All file marks
`workers://all`	Registered workers
`workflow://current`	Current workflow configuration
`workflow://{name}`	Named workflow (solo, swarm, relay, hierarchical)
`config://current`	Current server configuration
`plan://acp`	ACP-compatible plan export
`stats://summary`	Aggregate statistics

Task Tree Structure

Create hierarchical tasks with create_tree:

{
  "tree": {
    "title": "Implement auth",
    "children": [
      { "title": "Design schema" },
      { "title": "Write migrations" },
      { "title": "Implement endpoints", "children": [
        { "title": "Login endpoint" },
        { "title": "Logout endpoint" },
        { "title": "Refresh endpoint" }
      ]},
      { "title": "Write tests" }
    ]
  },
  "sibling_type": "follows"
}

Tree Node Fields

Field	Description
`title`	Task title (required for new tasks)
`description`	Task description
`id`	Custom task ID (UUID7 generated if omitted)
`ref`	Reference existing task by ID (other fields ignored when set)
`priority`	Priority 0-10 (default 5)
`points`	Story points / complexity estimate
`time_estimate_ms`	Estimated duration in milliseconds
`tags`	Categorization tags for the task
`needed_tags`	Agent must have ALL of these tags to claim (AND)
`wanted_tags`	Agent must have AT LEAST ONE of these tags to claim (OR)
`children`	Nested child nodes

Top-Level Parameters

Parameter	Default	Description
`tree`	required	Root node of the task tree
`parent`	null	Attach tree root to existing parent task
`child_type`	"contains"	Dependency type from parent to children
`sibling_type`	null	Dependency type between siblings ("follows" for sequential, null for parallel)

Referencing Existing Tasks

Use ref to integrate existing tasks into a tree structure:

{
  "tree": {
    "title": "Sprint 5",
    "children": [
      { "title": "New feature" },
      { "ref": "existing-task-id" },
      { "title": "Another task" }
    ]
  },
  "sibling_type": "follows"
}

Tag-Based Affinity

Workers declare capabilities via tags when connecting. Tasks can require specific tags to control which workers can claim them.

Example tag categories:

Model capabilities: image-in, audio-out, video-in, code, bulk
Access levels: prod-access, admin, external
Specializations: rust, python, frontend, database

Note: Roles like coordinator/reviewer/deployer are better represented using phases.

Task requirements:

needed_tags (AND): Agent must have ALL of these
wanted_tags (OR): Agent must have AT LEAST ONE

{
  "title": "Analyze screenshot and generate code",
  "needed_tags": ["image-in", "code"],
  "wanted_tags": ["bulk"]
}

{
  "title": "Deploy to production",
  "phase": "deploy",
  "needed_tags": ["prod-access"],
  "wanted_tags": ["aws", "gcp"]
}

Workflows and Phases

Phases

Tasks can have a phase to categorize the type of work being performed:

{
  "title": "Add authentication",
  "phase": "implement"
}

Built-in phases: explore, implement, review, test, security, deploy, triage, diagnose, design, plan, doc, integrate, monitor, optimize

Phases enable:

Transition prompts — Automatic guidance when entering/exiting phases
Gates — Requirements that must be satisfied before phase transitions
Role-based routing — In relay workflows, specialists own specific phases

Named Workflows

Pre-built workflow topologies optimize for different coordination patterns:

Workflow	Description	Best For
`solo`	Single agent, full autonomy	Simple tasks, prototyping
`swarm`	Parallel generalists, pull-based	High throughput, independent tasks
`relay`	Sequential specialists, handoffs	Complex tasks, domain expertise
`hierarchical`	Lead/worker delegation	Large projects, team coordination

Select a workflow on connect:

connect(worker_id="agent-1", workflow="swarm")

Each workflow provides tailored prompts and coordination guidance. See WORKFLOW_TOPOLOGIES.md for detailed patterns.

Transition Prompts

Agents receive automatic guidance when status or phase changes:

# workflows.yaml
states:
  working:
    prompts:
      enter: |

        You are now working on this task.
        From {{current_status}} you can transition to: {{valid_exits}}
      exit: |

        Before leaving:
        - [ ] Attach results
        - [ ] Log costs

Prompts support template variables: {{current_status}}, {{valid_exits}}, {{current_phase}}, {{valid_phases}}

Gates

Gates are requirements that must be satisfied before status or phase transitions:

gates:
  status:working:
    - type: gate/tests
      enforcement: warn
      description: "Tests must pass"

Satisfy a gate by attaching evidence:

attach(task="123", type="gate/tests", content="All tests passing")

Enforcement levels: allow (advisory), warn (blocks unless force=true), reject (hard block)

File Coordination

Agents can coordinate file edits using advisory marks with change tracking:

Worker A: connect() -> "worker-a"
Worker A: mark_file("worker-a", "src/main.rs", "refactoring")
Worker B: connect() -> "worker-b"
Worker B: mark_updates("worker-b") -> sees worker-a's mark
Worker A: unmark_file("worker-a", "src/main.rs", "ready for review")
Worker B: mark_updates("worker-b") -> sees removal with reason
Worker B: mark_file("worker-b", "src/main.rs", "adding tests")

Architecture

┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│  Agent A    │     │  Agent B    │     │  Agent C    │
│  (Claude)   │     │  (GPT-4)    │     │  (Worker)   │
└──────┬──────┘     └──────┬──────┘     └──────┬──────┘
       │ stdio             │ stdio             │ stdio
       ▼                   ▼                   ▼
┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│ task-graph  │     │ task-graph  │     │ task-graph  │
│    MCP      │     │    MCP      │     │    MCP      │
└──────┬──────┘     └──────┬──────┘     └──────┬──────┘
       │                   │                   │
       └───────────────────┼───────────────────┘
                           ▼
                  ┌─────────────────┐
                  │   SQLite + WAL  │
                  │  .task-graph/   │
                  │    tasks.db     │
                  └─────────────────┘

Transport: Stdio — each worker spawns its own server process
Database: SQLite with WAL mode for concurrent access across processes
Deployment: Single binary, no external dependencies, works offline

Compared to Alternatives

	Task Graph	Linear task lists	Custom databases
Workflow phases	✓ Built-in with prompts	✗ Manual tracking	DIY
Quality gates	✓ Configurable enforcement	✗	DIY
Multi-agent safe	✓ Atomic claims, file locks	✗ Race conditions	Maybe, DIY
Dependency tracking	✓ DAG with cycle detection	✗ Manual ordering	DIY
MCP native	✓ First-class	✗ Wrapper needed	✗ Wrapper needed
Token accounting	✓ Built-in	✗	DIY
Setup required	None	None	Database server

Documentation

Document	Description
CONFIGURATION.md	Complete configuration reference (config.yaml, workflows, prompts, gates, tags)
SCHEMA.md	Database schema and state machine documentation
DESIGN.md	Architecture and design decisions
WORKFLOW_TOPOLOGIES.md	Multi-agent workflow patterns (solo, swarm, relay, hierarchical)
EXPORT_IMPORT.md	Data export and import functionality

License

Apache 2.0

Built for AI agents that need structured workflows and reliable coordination.

task-graph-mcp 0.2.1

Task Graph MCP Server

Why Task Graph?

Features

Quick Start

Installation

From crates.io (Recommended)

Pre-built Binaries

From Source

Usage

As an MCP Server

CLI Options

Configuration

States Configuration

Dependencies Configuration

Attachments Configuration

MCP Tools

Worker Management

Task CRUD

Task Claiming

Dependencies

Tracking

File Coordination

Attachments

Advanced

MCP Resources

Task Tree Structure

Tree Node Fields

Top-Level Parameters

Referencing Existing Tasks

Tag-Based Affinity

Workflows and Phases

Phases

Named Workflows

Transition Prompts

Gates

File Coordination

Architecture

Compared to Alternatives

Documentation

License