Pulse Workflow MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PULSE_APP_ID | No | Optional default app ID | |
| PULSE_API_KEY | Yes | Console API key | |
| PULSE_API_URL | Yes | Pulse instance URL |
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_appsC | List apps. Returns: [{id, name, mode}] |
| select_appD | Select app for subsequent operations |
| create_appC | Create app and auto-initialize workflow. Returns: {id, name, mode, start_node_id} |
| initialize_workflowD | Initialize workflow draft (auto-called by create_app) |
| view_workflowC | View workflow structure. Returns: {nodes:[{id,type,title}], edges:[{source,target}]} |
| validate_workflowB | Check for errors. Returns: {valid, errors[], warnings[]} |
| publish_workflowC | Publish draft as new version |
| add_nodeB | Add node. Returns: {node_id}. Use get_node_schema first for config format. |
| edit_nodeB | Update node (PATCH-style, only include changed fields) |
| delete_nodeC | Delete node and its edges |
| get_nodeC | Get node details |
| list_nodesC | List nodes. Returns: [{id, type, title}] |
| batch_add_nodesA | Add multiple nodes at once. More efficient than multiple add_node calls. |
| add_noteB | Add documentation note to canvas (visual only, not executed). Text supports newlines for paragraphs. |
| edit_noteC | Update sticky note |
| list_notesC | List sticky notes |
| delete_noteC | Delete sticky note |
| connect_nodesC | Create edge between nodes |
| disconnect_nodesC | Remove edge between nodes |
| list_edgesB | List edges. Returns: [{id, source, target}] |
| list_node_typesB | REQUIRED before add_node. Lists available node types. |
| get_node_schemaA | REQUIRED before configuring a node. Get config schema for node type. |
| list_modelsC | List AI models for LLM nodes. Returns: [{provider, model, model_type}] |
| list_tool_providersC | List external tool providers |
| list_toolsA | List tools from a provider with full schemas for agent configuration. Returns tool names, parameters (with form type, required, defaults). |
| list_agent_strategiesA | List agent strategy providers for agent nodes. Returns providers with strategy names. Use get_agent_strategy for parameters. |
| get_agent_strategyC | Get agent strategy details including required parameters (instruction, query, model, tools, etc.) for agent_parameters config. |
| list_datasetsC | List knowledge bases for RAG |
| get_datasetC | Get dataset details |
| list_documentsC | List documents in dataset |
| get_documentC | Get document details |
| search_datasetC | Query knowledge base (hit testing). Returns: [{score, content, document_name}] |
| get_featuresC | Get workflow features config |
| update_featuresC | Update features (partial) |
| get_variablesA | Get environment and conversation variables |
| run_nodeC | Execute single node for testing |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| workflow_context | Get full context about the current workflow for understanding and modifications |
| discovery_workflow | Get the mandatory discovery workflow for building Pulse workflows from scratch |
| add_rag_pipeline | Template for adding a RAG (Retrieval Augmented Generation) pipeline |
| add_llm_chain | Template for adding an LLM processing chain |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Current Workflow | The current draft workflow structure including nodes, edges, and configuration |
| Available Node Types | List of available node types with their configuration schemas |
| Workflow Summary | Human-readable summary of the current workflow |
TDQS
Scored across 36 tools
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.
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.
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.
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.