Skip to main content
Glama
Sign In
PipelineFlow

PipelineFlow

by johannschiffer
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

PipelineFlow MCP (Lite Edition)

License: MIT Protocol: MCP Python: >=3.10

PipelineFlow MCP is a lightweight, declarative workflow DAG and data pipeline orchestrator designed for AI agents (Claude Desktop, Cursor, OpenAI Codex, LangGraph).

It enables agents to define multi-step data pipelines, validate dependency acyclicity via topological sorting (Kahn's algorithm), execute transformations predictably, and export visual Mermaid diagrams—without heavy cloud orchestrators like Airflow or Prefect.

🎯 The Problem

When autonomous AI agents execute multi-step workflows:

  1. Unstructured Command Chains: Agents run disconnected shell commands or Python scripts with no dependency graph or cycle detection.

  2. Lack of Visual Representation: Neither humans nor agents can visualize the pipeline topology or inspect intermediate step outputs.

  3. Heavy Orchestrator Bloat: Enterprise orchestrators (Airflow, Dagster) require databases, workers, and gigabytes of dependencies, making them unsuitable for local agent runtimes.

PipelineFlow provides a pure-Python, zero-dependency DAG engine that runs directly inside the MCP protocol.

Related MCP server: AllBrain MCP

✨ Features (Lite Edition)

  • 🔄 Declarative Pipeline DAG: Add nodes (inputs, filters, transforms, aggregates, outputs) and connect directed edges.

  • 🛡️ Cycle Detection & Topological Sort: Guarantees deterministic execution order and prevents circular deadlocks using Kahn's algorithm.

  • 📊 Instant Mermaid Diagrams: Generates clean Mermaid graph diagrams of any pipeline with one tool call.

  • ⚡ Zero-Dependency Engine: Pure standard library execution with zero cloud setup.

🚀 Quickstart

1. Installation

git clone https://github.com/johannschiffer/pipelineflow-mcp.git
cd pipelineflow-mcp
pip install -e .

2. Configure in Claude Desktop or Cursor

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "pipelineflow": {
      "command": "pipelineflow",
      "args": ["run"]
    }
  }
}

3. Run Demo via CLI

pipelineflow demo

🛠️ MCP Tools Reference

Tool

Parameters

Description

create_pipeline

pipeline_id, name

Creates a new pipeline DAG

add_node

pipeline_id, node_id, node_type, params

Adds a node (input, filter, transform, aggregate, custom, output)

connect_nodes

pipeline_id, from_node, to_node

Connects source node to target node (validates acyclicity)

run_pipeline

pipeline_id, initial_data

Executes pipeline in topological dependency order

get_node_output

pipeline_id, node_id

Retrieves execution output for any node

export_pipeline_mermaid

pipeline_id

Returns Mermaid diagram string of the pipeline graph

list_pipelines

(none)

Lists all registered pipelines and node counts

🚀 Upgrade to PipelineFlow Pro

Need enterprise pipeline caching, parallel branch execution, and interactive HTML dashboards?

The PipelineFlow Pro Edition adds:

  • ⚡ Content-Addressable Cache (SQLite WAL): Caches node execution outputs by SHA-256 hash of inputs, skipping redundant executions.

  • 🔀 Concurrent Branch Runner: Runs independent DAG branches in parallel using a managed thread pool.

  • 🛡️ Per-Node Retry & Circuit-Breaker Policies: Configurable exponential backoff and error recovery.

  • 🎨 Interactive HTML Visualizer: Generates standalone interactive SVG/HTML pipeline dashboards.

  • 🐳 Production Docker & Docker Compose manifests.

  • 🧪 100% Passing Pytest Suite.

👉 Get PipelineFlow Pro on Gumroad ($14.99 USD)

📄 License

MIT © 2026 Johann Schiffer

Available Tools

7 tools
add_nodeC

Add processing step (input, filter, transform, aggregate, custom) to pipeline.

Inputs: node_id (required), pipeline_id (required), params, node_type.

connect_nodesC

Establish directed dependency edge from source node to target node.

Inputs: to_node (required), from_node (required), pipeline_id (required).

create_pipelineC

Create a new workflow pipeline DAG with custom identifier and name.

Inputs: pipeline_id (required), name.

export_pipeline_mermaidB

Export pipeline DAG structure as standard Mermaid diagram string.

Inputs: pipeline_id (required).

get_node_outputB

Fetch cached execution output for a specific node in the pipeline.

Inputs: node_id (required), pipeline_id (required).

list_pipelinesA

List all active pipelines with their node and edge metrics.

Inputs: no named parameters.

run_pipelineB

Execute pipeline DAG in topological dependency order and collect node outputs.

Inputs: pipeline_id (required), initial_data.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    TDQS

    A3.5/5.0

    Scored across 7 tools

    Disambiguation4/5

    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.

    Naming Consistency5/5

    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.

    Tool Count5/5

    Seven tools is well-scoped for a pipeline DAG builder/runner, covering construction, execution, inspection, and export without redundancy. Every tool earns its place.

    Completeness3/5

    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.

    Resources

    Related MCP Connectors

    Related MCP Servers