PipelineFlow
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_pipelineC | Create a new workflow pipeline DAG with custom identifier and name. |
| add_nodeC | Add processing step (input, filter, transform, aggregate, custom) to pipeline. |
| connect_nodesC | Establish directed dependency edge from source node to target node. |
| run_pipelineB | Execute pipeline DAG in topological dependency order and collect node outputs. |
| get_node_outputB | Fetch cached execution output for a specific node in the pipeline. |
| export_pipeline_mermaidB | Export pipeline DAG structure as standard Mermaid diagram string. |
| list_pipelinesA | List all active pipelines with their node and edge metrics. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool targets a distinct pipeline-building action: create_pipeline, add_node, connect_nodes, run_pipeline, get_node_output, export, and list are largely separable. The only mild overlap is between run_pipeline (executes and collects outputs) and get_node_output (fetches cached output), but the descriptions clarify execution vs. retrieval.
All seven tools use a consistent snake_case verb_noun pattern (create_pipeline, add_node, connect_nodes, run_pipeline, get_node_output, list_pipelines). export_pipeline_mermaid is slightly longer but still follows the same verb_noun convention.
Seven tools is well-scoped for a pipeline DAG builder/runner, covering construction, execution, inspection, and export without redundancy. Every tool earns its place.
The surface covers creation, node/edge building, execution, output retrieval, listing, and export, but has notable gaps: no delete_pipeline, no update/rename, and no remove_node or disconnect_nodes, so agents cannot clean up or modify an existing DAG. These missing lifecycle operations will force workarounds.