MCP Integration

Beta Feature

MCP Integration is currently in beta. The available tools and configuration format may change in future releases.

Overview

MaestroHub exposes a Model Context Protocol (MCP) server that lets AI coding assistants interact directly with your industrial automation platform. Once connected, an AI assistant can query connections, build pipelines, publish data to the Unified Namespace, create dashboards, and more — all through natural language.

This enables use cases such as:

• Rapid prototyping — describe a pipeline in plain English and have the AI build it
• Data exploration — ask questions about your UNS topics, connections, and pipeline executions
• Dashboard creation — generate monitoring dashboards from conversational descriptions
• Troubleshooting — inspect connection statuses, execution logs, and dependency graphs with AI assistance

Prerequisites

• OAuth2 module enabled — The MCP server authenticates via Personal Access Tokens (PATs), which require the OAuth2 module
• A Personal Access Token — Generated from your profile page (see below)

Step 1: Generate a Personal Access Token

Create a PAT from your profile's Security tab. Give it a descriptive name (e.g., "MCP - Claude Code"), select an expiration period (1 year recommended for development use), and grant the permissions needed for your workflow.

For detailed instructions, see Personal Access Tokens.

Step 2: Obtain the Organization ID

Most MCP configurations require an Organization ID to scope API requests to the correct organization.

For how to find and copy your Organization ID, see Organization Context.

Step 3: Configure Your Editor

Choose your editor from the guides below to set up MCP integration:

• Claude Code
• Claude Desktop App
• Cursor
• VS Code
• Antigravity
• Codex

Each guide provides the exact configuration file format and location for the editor.

For real-world prompt examples with actual outputs, see the Example Prompts page. For a full end-to-end walkthrough, see Walkthrough: Antigravity + Gemini.

Available Tools

The MCP server exposes the following tools, grouped by module.

Authentication & Authorization

Tool	Description
auth_get_user	Get a user by ID or email
auth_get_user_stats	Get aggregate user statistics
auth_list_users	List users with optional filtering
auth_list_identity_providers	List configured SSO identity providers
authz_check_access	Check if a user has permission for an action
authz_get_user_roles	Get role assignments for a user
authz_get_users_with_role	Get users with a specific role
authz_list_roles	List all roles with permissions

Connectors

Tool	Description
connectors_list_connections	List all connections with optional search
connectors_get_connection	Get connection details by ID
connectors_connection_status	Get runtime status and metrics
connectors_test_connection	Test connectivity for a connection
connectors_start_connection	Start a connection runtime
connectors_stop_connection	Stop a connection runtime
connectors_list_functions	List functions for a connection
connectors_get_function	Get function details by ID
connectors_execute_function	Execute a connector function
connectors_list_protocols	List all supported protocols

Pipeline Engine

Tool	Description
engine_list_pipelines	List pipelines with search and filtering
engine_get_pipeline	Get pipeline details including node graph
engine_create_pipeline	Create a new pipeline with nodes and edges
engine_update_pipeline	Update an existing pipeline
engine_validate_pipeline	Validate pipeline configuration
engine_enable_pipeline	Enable a pipeline
engine_disable_pipeline	Disable a pipeline
engine_list_executions	List recent executions for a pipeline
engine_get_execution	Get execution details
engine_list_node_types	List available node types
engine_list_models	List data models
engine_get_model	Get a data model by ID

Unified Namespace (UNS)

Tool	Description
uns_list_topics	List all UNS topics
uns_search_topics	Search topics by name
uns_get_topic	Get topic details and schema
uns_create_topic	Create a new topic
uns_publish_data	Publish data to a topic
uns_fetch_recent	Fetch most recent data from a topic
uns_fetch_range	Fetch data within a time range
uns_broker_status	Get MQTT broker status

Dashboards

Tool	Description
uns_list_dashboards	List dashboards with optional search
uns_get_dashboard	Get dashboard details and panels
uns_create_dashboard	Create a dashboard with panels
uns_update_dashboard	Update dashboard properties
uns_delete_dashboard	Delete a dashboard
uns_add_panel	Add a panel to a dashboard
uns_update_panel	Update a panel
uns_remove_panel	Remove a panel
uns_list_panel_types	List available panel types

Dependencies

Tool	Description
deps_get_insights	Get dependency graph insights
deps_query_graph	Query the full dependency graph
deps_query_dependencies	Find what an entity depends on
deps_query_dependents	Find what depends on an entity
deps_query_impact	Impact analysis for changes
deps_query_orphans	Find unused entities

Scheduler

Tool	Description
scheduler_get_stats	Get scheduler statistics
scheduler_list_webhooks	List registered webhook paths
scheduler_trigger_manually	Manually trigger a pipeline

Search

Tool	Description
search_query	Search across all entity types
search_find_by_id	Find an entity by ID
search_get_stats	Get search index statistics

Organization & License

Tool	Description
org_get_organization	Get organization details
org_list_organizations	List organizations
org_get_settings	Get organization settings
org_get_maintenance_status	Check maintenance mode
license_get_status	Get license status
license_get_features	List enabled features
license_check_feature	Check a specific feature flag

WebSocket

Tool	Description
ws_get_status	Get WebSocket server status
ws_get_presence	Get users present on a pipeline editor

Tips & Best Practices

• HTTP vs HTTPS — The examples in these guides use https://. If your MaestroHub instance is deployed locally without TLS (e.g., http://localhost:8080), replace https:// with http:// in the MCP server URL.
• Token management — Rotate tokens periodically and use a 1-year expiration for development.
• Organization context — The X-Organization-ID header determines which organization's data the AI can access. Make sure it matches your target environment.
• Tool discovery — Ask the AI "What MCP tools are available?" to get a full list of capabilities. The AI can also call engine_list_node_types and connectors_list_protocols to discover what pipeline nodes and connector types are supported.
• Iterative building — Start with simple pipelines and add complexity incrementally. The AI can update existing pipelines with engine_update_pipeline.
• Impact analysis — Before modifying or deleting a connection or function, ask the AI to run deps_query_impact to understand what will be affected.