Skip to main content
Glama
Pulse Workflow MCP Server

Pulse Workflow MCP Server

Official

Pulse Workflow MCP Server

An MCP (Model Context Protocol) server that enables Claude Code to interact with and modify Pulse workflows directly.

Overview

This MCP server exposes Pulse workflow operations as tools, allowing you to:

  • Browse and select from available Pulse apps

  • Discover available node types, models, tools, and datasets at runtime

  • Create new workflow apps from scratch

  • View and navigate workflow structure

  • Add, edit, and delete nodes

  • Create and remove connections between nodes

  • Publish workflows

  • Run individual nodes for testing

  • Manage workflow features and variables

Related MCP server: n8n MCP Server

Installation

No installation required - use uvx to run directly:

# Install Claude Code skills (one-time setup)
uvx pulse-workflow-mcp install-skills

From PyPI

pip install pulse-workflow-mcp

# Or with uv
uv pip install pulse-workflow-mcp

For Development

git clone https://github.com/Pulse-Intelligence/pulse-workflow-mcp.git
cd pulse-workflow-mcp
uv pip install -e ".[dev]"

Skills

This package includes Claude Code skills for guided workflow development:

Skill

Description

/pulse

Overview and available commands

/pulse-create

Create a new workflow from description

/pulse-edit

Edit an existing workflow

/pulse-publish

Validate and publish workflow

Install skills to ~/.claude/skills/:

# Using uvx (no installation required)
uvx pulse-workflow-mcp install-skills
uvx pulse-workflow-mcp install-skills --force  # Overwrite existing
uvx pulse-workflow-mcp uninstall-skills        # Remove skills

# Or if installed via pip
pulse-workflow-mcp install-skills

Configuration

Set the following environment variables:

export PULSE_API_URL="http://localhost:5001"  # Pulse instance URL
export PULSE_API_KEY="your-api-key"           # Console API key
export PULSE_APP_ID="your-app-id"             # Optional: default app ID

Getting Your API Key

The easiest way is through the Pulse workflow editor:

  1. Open any workflow in Pulse

  2. Click "Connect Claude Code" button

  3. The modal will generate a token for you

App ID (Optional)

PULSE_APP_ID is now optional. You can:

  • Set it to always work with a specific app

  • Leave it empty and use list_apps + select_app tools to choose at runtime

The app ID is in the URL when viewing a workflow:

https://your-pulse.com/app/abc123def456/workflow
                        ^^^^^^^^^^^^
                        This is your app ID

Usage with Claude Code

Add to ~/.claude.json - no installation required:

{
  "mcpServers": {
    "pulse-workflow": {
      "command": "uvx",
      "args": [
        "pulse-workflow-mcp"
      ],
      "env": {
        "PULSE_API_URL": "http://localhost:5001",
        "PULSE_API_KEY": "your-api-key"
      }
    }
  }
}

Alternative: Direct Command

If installed via pip:

{
  "mcpServers": {
    "pulse-workflow": {
      "command": "pulse-workflow-mcp",
      "env": {
        "PULSE_API_URL": "http://localhost:5001",
        "PULSE_API_KEY": "your-api-key"
      }
    }
  }
}

With Default App ID

If you always work with one app, add PULSE_APP_ID:

{
  "mcpServers": {
    "pulse-workflow": {
      "command": "uvx",
      "args": [
        "pulse-workflow-mcp"
      ],
      "env": {
        "PULSE_API_URL": "http://localhost:5001",
        "PULSE_API_KEY": "your-api-key",
        "PULSE_APP_ID": "your-app-id"
      }
    }
  }
}

Usage

Once configured, in Claude Code:

> List my workflow apps

Claude will use: list_apps with mode="workflow"

> Select app abc123def456

Claude will use: select_app

Available Tools

App Operations

Tool

Description

list_apps

List available Pulse apps (filter by mode, name)

select_app

Select an app to work with for subsequent operations

create_app

Create a new workflow or chat app

Discovery Operations

Tool

Description

list_node_types

List all available node types with default configs

get_node_schema

Get detailed schema for a specific node type

list_tool_providers

List available tool/plugin providers

list_tools

List tools from a provider with input/output schemas

list_models

List available AI models (LLM, embedding, etc.)

list_datasets

List available knowledge base datasets

Node Operations

Tool

Description

add_node

Add a new node to the workflow

edit_node

Modify an existing node

delete_node

Remove a node and its connections

get_node

Get details of a specific node

list_nodes

List all nodes (optionally filtered by type)

Edge Operations

Tool

Description

connect_nodes

Create a connection between two nodes

disconnect_nodes

Remove connection(s) between nodes

list_edges

List all edges in the workflow

Workflow Operations

Tool

Description

view_workflow

View the complete workflow structure

publish_workflow

Publish the draft as a new version

validate_workflow

Check workflow for errors/warnings

run_node

Execute a single node for testing

Feature Operations

Tool

Description

get_features

Get workflow feature configuration

update_features

Update workflow features

get_variables

Get environment and conversation variables

Examples

List and Select Apps

> Show me my workflow apps

Claude will use: list_apps with mode="workflow"
Returns: List of apps with IDs, names, and modes

> Select the "Customer Support" app

Claude will use: select_app with the app ID

View Current Workflow

> Show me the current workflow

Claude will use: view_workflow

Add an LLM Node

> Add an LLM node called "Summarizer" that summarizes user input.
  Connect it after the Start node.

Claude will:
1. Use list_nodes to find the Start node ID
2. Use add_node with after_node_id to create and connect the LLM node

Build a RAG Pipeline

> Create a RAG pipeline that:
  1. Retrieves from my knowledge base (dataset ID: abc123)
  2. Uses GPT-4 to answer based on the context
  3. Returns the response to the user

Claude will:
1. add_node (knowledge-retrieval)
2. add_node (llm with context)
3. connect_nodes appropriately

Publish a Version

> Publish this workflow as version 1.0

Claude will use: publish_workflow with name="v1.0"

Create a Workflow from Scratch (Discovery Flow)

> Create a new customer support workflow with an LLM that responds to questions

Claude will:
1. create_app to create a new workflow app
2. list_node_types to discover available nodes
3. get_node_schema("llm") to understand LLM node config
4. list_models to discover available AI models
5. add_node to add the LLM node with proper config
6. connect_nodes to wire up the flow
7. validate_workflow to check for errors

Configure a Knowledge Retrieval Node

> Add knowledge retrieval from my product docs

Claude will:
1. list_datasets to find available knowledge bases
2. get_node_schema("knowledge-retrieval") to get config schema
3. add_node with the discovered dataset ID

Supported Node Types

Category

Node Types

Control

start, end, answer, if-else, iteration, loop

AI

llm, knowledge-retrieval, question-classifier, parameter-extractor

Transform

code, template-transform, variable-assigner, variable-aggregator, document-extractor, list-filter, assigner

External

http-request, tool

Resources

The server provides these MCP resources:

  • pulse://workflow/current - Current workflow as JSON

  • pulse://workflow/node-types - Available node type schemas

  • pulse://workflow/summary - Human-readable workflow summary

Prompts

Available MCP prompts:

  • workflow_context - Full context about the current workflow

  • discovery_workflow - Mandatory discovery workflow for building from scratch

  • add_rag_pipeline - Template for adding a RAG pipeline

  • add_llm_chain - Template for adding an LLM processing chain

Development

# Clone and install
git clone https://github.com/Pulse-Intelligence/pulse-workflow-mcp.git
cd pulse-workflow-mcp
uv pip install -e ".[dev]"

# Run tests
pytest tests/

# Run linter
ruff check .

# Run server locally
export PULSE_API_URL="http://localhost:5001"
export PULSE_API_KEY="your-api-key"
pulse-workflow-mcp

Architecture

┌─────────────────────────────────────────────────────────────┐
│                     Claude Code CLI                          │
│  > "Add an LLM node that summarizes user input"             │
└─────────────────────────────────────────────────────────────┘
                              │
                              │ MCP Protocol (stdio)
                              ▼
┌─────────────────────────────────────────────────────────────┐
│                  Pulse MCP Server                           │
│  ┌─────────────┐ ┌─────────────┐ ┌─────────────────────┐   │
│  │   Tools     │ │  Resources  │ │    Prompts          │   │
│  │ - list_apps │ │ - workflow  │ │ - workflow_context  │   │
│  │ - add_node  │ │ - node_types│ │ - add_rag_pipeline  │   │
│  │ - edit_node │ │ - summary   │ │ - add_llm_chain     │   │
│  │ - connect   │ │             │ │                     │   │
│  └─────────────┘ └─────────────┘ └─────────────────────┘   │
└─────────────────────────────────────────────────────────────┘
                              │
                              │ REST API
                              ▼
┌─────────────────────────────────────────────────────────────┐
│                    Pulse Backend                             │
│   /apps (GET)                                               │
│   /apps/{id}/workflows/draft (GET/POST)                     │
│   /apps/{id}/workflows/publish (POST)                       │
└─────────────────────────────────────────────────────────────┘

Error Handling

The server handles common errors:

  • WorkflowNotSyncError: Concurrent edit detected - refresh and retry

  • PulseClientError: API errors with status code and message

  • No app selected: Use list_apps and select_app to choose an app

License

MIT

Available Tools

36 tools
add_nodeB

Add node. Returns: {node_id}. Use get_node_schema first for config format.

Inputs: node_type (required), title, config, position, +3 more.

add_noteB

Add documentation note to canvas (visual only, not executed). Text supports newlines for paragraphs.

Inputs: text (required), theme, position, author, +3 more.

batch_add_nodesA

Add multiple nodes at once. More efficient than multiple add_node calls.

Inputs: nodes (required), connections.

connect_nodesC

Create edge between nodes

Inputs: source_id (required), target_id (required), source_handle, target_handle.

create_appC

Create app and auto-initialize workflow. Returns: {id, name, mode, start_node_id}

Inputs: name (required), mode, description, icon.

delete_nodeC

Delete node and its edges

Inputs: node_id (required).

delete_noteC

Delete sticky note

Inputs: note_id (required).

disconnect_nodesC

Remove edge between nodes

Inputs: source_id (required), target_id (required), source_handle, target_handle.

edit_nodeB

Update node (PATCH-style, only include changed fields)

Inputs: node_id (required), title, config, position.

edit_noteC

Update sticky note

Inputs: note_id (required), text, theme, position, +4 more.

get_agent_strategyC

Get agent strategy details including required parameters (instruction, query, model, tools, etc.) for agent_parameters config.

Inputs: provider_name (required).

get_datasetC

Get dataset details

Inputs: dataset_id (required).

get_documentC

Get document details

Inputs: dataset_id (required), document_id (required).

get_featuresC

Get workflow features config

Inputs: no named parameters.

get_nodeC

Get node details

Inputs: node_id (required).

get_node_schemaA

REQUIRED before configuring a node. Get config schema for node type.

Inputs: block_type (required), app_id.

get_variablesA

Get environment and conversation variables

Inputs: no named parameters.

initialize_workflowD

Initialize workflow draft (auto-called by create_app)

Inputs: app_id.

list_agent_strategiesA

List agent strategy providers for agent nodes. Returns providers with strategy names. Use get_agent_strategy for parameters.

Inputs: no named parameters.

list_appsC

List apps. Returns: [{id, name, mode}]

Inputs: mode, name, limit.

list_datasetsC

List knowledge bases for RAG

Inputs: limit.

list_documentsC

List documents in dataset

Inputs: dataset_id (required), page, limit, keyword.

list_edgesB

List edges. Returns: [{id, source, target}]

Inputs: no named parameters.

list_modelsC

List AI models for LLM nodes. Returns: [{provider, model, model_type}]

Inputs: model_type.

list_nodesC

List nodes. Returns: [{id, type, title}]

Inputs: filter_type.

list_node_typesB

REQUIRED before add_node. Lists available node types.

Inputs: app_id.

list_notesC

List sticky notes

Inputs: no named parameters.

list_tool_providersC

List external tool providers

Inputs: no named parameters.

list_toolsA

List tools from a provider with full schemas for agent configuration. Returns tool names, parameters (with form type, required, defaults).

Inputs: provider_id, tool_type.

publish_workflowC

Publish draft as new version

Inputs: name, comment.

run_nodeC

Execute single node for testing

Inputs: node_id (required), inputs, query.

search_datasetC

Query knowledge base (hit testing). Returns: [{score, content, document_name}]

Inputs: dataset_id (required), query (required), top_k, search_method.

select_appD

Select app for subsequent operations

Inputs: app_id (required).

update_featuresC

Update features (partial)

Inputs: file_upload, opening_statement, suggested_questions.

validate_workflowB

Check for errors. Returns: {valid, errors[], warnings[]}

Inputs: no named parameters.

view_workflowC

View workflow structure. Returns: {nodes:[{id,type,title}], edges:[{source,target}]}

Inputs: app_id, include_details.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    C2.7/5.0

    Scored across 36 tools

    Disambiguation5/5

    Each tool targets a distinct action or resource (nodes, notes, apps, workflows, datasets, agent strategies, etc.). No overlaps or ambiguous boundaries; even batch_add_nodes is clearly a bulk variant of add_node.

    Naming Consistency5/5

    All tools use consistent verb_noun snake_case naming (e.g., add_node, list_nodes, get_node_schema, batch_add_nodes). No mixing of conventions like camelCase or different verb styles.

    Tool Count2/5

    With 36 tools, this far exceeds the typical well-scoped range of 3-15. While the server covers a broad domain, the number of tools feels heavy and could overwhelm agents.

    Completeness4/5

    The tool set covers CRUD for nodes and notes, plus workflow lifecycle (initialize, validate, publish), and supporting functions (schemas, testing, search). Minor gaps: missing delete for apps and workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Wraps Claude Code as tools for MCP clients, enabling autonomous coding tasks via a 4-tool lifecycle with session management, async polling, and permission controls.
      4
      93 npm
      21
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to programmatically create, manage, and orchestrate n8n workflows through a standardized MCP interface.
      MIT