Task Orchestrator
by Evozimcommunityv1.0.0
188
22
An MCP server for orchestrating task workflows with persistent work-item graphs, dependency tracking, notes, and server-enforced transition gates. It can block actions until required notes or dependency conditions are satisfied and supports actor attribution and auditing.
From the registry: Multi-agent swarm planner and project sprint allocator.
Install & configure
Prerequisites
- requiredInstall DockerDocker must be installed and running to use the recommended containerized MCP server.https://www.docker.com/products/docker-desktop/
- requiredPull the Task Orchestrator imageDownload the latest container image before configuring your MCP client.
$ docker pull ghcr.io/jpicklyk/task-orchestrator:latest
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `task-orchestrator` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Docker** — Docker must be installed and running to use the recommended containerized MCP server. (https://www.docker.com/products/docker-desktop/)
- **Pull the Task Orchestrator image** — Download the latest container image before configuring your MCP client. Run: `docker pull ghcr.io/jpicklyk/task-orchestrator:latest`
Canonical MCP server config (stdio transport):
- command: `docker`
- args: ["run","--rm","-i","-v","mcp-task-data:/app/data","ghcr.io/jpicklyk/task-orchestrator:latest"]
Note: Recommended install path is the Docker-based STDIO server. The server auto-initializes on first run. Optional workflow schema enforcement can be enabled by mounting your project's .taskorchestrator directory and setting AGENT_CONFIG_DIR=/project. Canonical optional additions: args += ["-v","<your-workspace>/.taskorchestrator:/project/.taskorchestrator:ro","-e","AGENT_CONFIG_DIR=/project"] and env includes AGENT_CONFIG_DIR with example "/project". README mentions the stack supports STDIO and HTTP transport, but only STDIO client configuration is documented, so HTTP config is not extracted.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: Recommended install path is the Docker-based STDIO server. The server auto-initializes on first run. Optional workflow schema enforcement can be enabled by mounting your project's .taskorchestrator directory and setting AGENT_CONFIG_DIR=/project. Canonical optional additions: args += ["-v","<your-workspace>/.taskorchestrator:/project/.taskorchestrator:ro","-e","AGENT_CONFIG_DIR=/project"] and env includes AGENT_CONFIG_DIR with example "/project". README mentions the stack supports STDIO and HTTP transport, but only STDIO client configuration is documented, so HTTP config is not extracted.
Tools (13)
manage_items
Create, update, and manage work items in the hierarchy
query_items
Query work items
create_work_tree
Create a hierarchical work breakdown tree atomically
complete_tree
Mark a work tree complete
manage_notes
Create or update persistent notes attached to items
query_notes
Query notes attached to items
manage_dependencies
Create or modify typed dependency edges
query_dependencies
Query dependency relationships
advance_item
Trigger workflow transitions with gate and dependency checks
get_next_status
Get the next status for an item
get_context
Return current workflow context and state
get_next_item
Get the next actionable item
get_blocked_items
List items blocked by unmet requirements or dependencies
Environment variables
AGENT_CONFIG_DIRPoints the server to the project config directory containing .taskorchestrator configurationRemote Endpoints
https://task-orchestrator-mcp-three.vercel.app/api/mcp
type: sse
Details
- Language
- Kotlin
- License
- MIT
- Released
- May 28, 2026
- Last commit
- May 23, 2026
- Registry name
- io.github.Evozim/task-orchestrator