Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_HOSTNoHost to bind when using HTTP transport. Default: 127.0.0.1127.0.0.1
MCP_PORTNoPort to bind when using HTTP transport. Default: 80008000
DATABASE_URLNoSQLAlchemy connection URL (SQLite or PostgreSQL). Default: sqlite:///dag_planner.dbsqlite:///dag_planner.db

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
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

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

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