dag-planner-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Host to bind when using HTTP transport. Default: 127.0.0.1 | 127.0.0.1 |
| MCP_PORT | No | Port to bind when using HTTP transport. Default: 8000 | 8000 |
| DATABASE_URL | No | SQLAlchemy connection URL (SQLite or PostgreSQL). Default: sqlite:///dag_planner.db | sqlite:///dag_planner.db |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_workflow_runC | Create a new workflow run in draft status. |
| create_plan_graphC | Create a plan graph (DAG of tasks) for an existing run. |
| replace_plan_branchC | Cancel downstream tasks from anchor and replace with new tasks. |
| get_ready_tasksC | Return tasks that are ready and not currently claimed. |
| claim_task_for_executionC | Claim a ready task for exclusive execution. |
| mark_task_runningC | Transition a task to running status. |
| mark_task_completedB | Mark a task completed and activate dependent tasks. |
| mark_task_failedC | Mark a task failed, with optional retry logic. |
| mark_task_blocked_humanC | Block a task pending human approval. |
| resume_taskC | Resume a blocked task after human decision. |
| put_task_outputC | Store working or final output for a task. |
| put_task_checkpointC | Save a checkpoint for a running task. |
| get_task_payload_refsB | Retrieve all payload data (input, output, checkpoint, contract) for a task. |
| get_taskC | Return full state of a single task. |
| list_tasksC | List tasks for a run with optional filters. |
| get_workflow_runC | Return workflow run state. |
| get_blocked_tasksB | Return all blocked tasks for a run. |
| get_dag_edgesC | Return all DAG edges for a run. |
| validate_task_outputC | Validate a task's output against its JSON Schema contract. |
| validate_dag_acyclicC | Validate that a task list forms an acyclic DAG. |
| get_my_taskC | Get task details from the executing agent's perspective. |
| update_my_progressC | Update working output and optionally checkpoint progress. |
| submit_my_outputC | Submit final output and mark task completed. |
| request_human_inputB | Request human input, blocking the task until decided. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Shubhamnegi/dag-planner-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server