Union MCP
The Union MCP server provides tools to interact with Union tasks, workflows, and executions through natural language processing. You can:
Execute Tasks and Workflows: Run Union tasks and workflows using natural language prompts that automatically format inputs to match function signatures
Retrieve Information: Get detailed metadata for specific tasks, workflows, and executions, including inputs, outputs, and descriptions
Discovery: List all available tasks and workflows within specified projects and domains
Deploy and Manage: Deploy applications to the Union platform with configurable project, domain, and application settings, plus manage authentication tokens with rotation capabilities
Development Integration: Integrate with IDEs like Cursor and Claude Desktop for both local development and remote server access
Flexible Deployment: Run locally for development or deploy to Union platform for remote access
Supports configuration for macOS systems, with specific paths for Claude Desktop configuration files
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Union MCP create a new task to review the quarterly report"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Union MCP
An MCP server to use Union tasks, workflows, and apps as tools.
Deployment Guides
Union MCP supports both Union v1 and v2. The following guides provide instructions for deploying the MCP server for each version:
Available Tools
6 toolsget_executionD
Get personalized union execution.
Inputs: domain (required), name (required), project (required).
get_taskD
Get a union task.
Inputs: domain (required), name (required), project (required). Returns: result
list_tasksC
List all tasks in a project and domain.
Inputs: domain (required), project (required). Returns: result
list_workflowsC
List all workflows in a project and domain.
Inputs: domain (required), project (required). Returns: result
run_taskC
Run a task with natural language.
- Based on the prompt and inputs dictionary, determine the task to run
- Format the inputs dictionary so that it matches the task function signature
- Invoke the task
Args:
project: Project to run the task in.
domain: Domain to run the task in.
name: Name of the task to run.
inputs: A dictionary of inputs to the task.
Returns:
A dictionary of outputs from the task.
Inputs: domain (required), inputs (required), name (required), project (required). Returns: result
run_workflowB
Run a workflow with natural language.
- Based on the prompt and inputs dictionary, determine the workflow to run
- Format the inputs dictionary so that it matches the workflow function signature
- Invoke the workflow
Args:
project: Project to run the workflow in.
domain: Domain to run the workflow in.
name: Name of the task to run.
inputs: A dictionary of inputs to the workflow.
Returns:
A dictionary of outputs from the workflow.
Inputs: domain (required), inputs (required), name (required), project (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Most tools have distinct purposes: get_execution and get_task retrieve specific items, list_tasks and list_workflows list collections, and run_task and run_workflow execute operations. However, get_task and list_tasks could potentially be confused if an agent isn't clear on whether it needs a single task or multiple tasks, as both relate to tasks in the same domain.
All tool names follow a consistent verb_noun pattern (e.g., get_execution, list_tasks, run_workflow). The naming is uniform across all six tools, with clear and predictable conventions that make it easy for agents to understand the action and target resource.
With 6 tools, the count is well-scoped for a server focused on union execution, tasks, and workflows. It covers key operations like retrieval, listing, and execution without being overly sparse or bloated, fitting typical MCP server ranges of 3-15 tools.
The tool set provides good coverage for core operations in a union management domain, including getting items, listing collections, and running tasks/workflows. A minor gap exists in the lack of update or delete operations for tasks or workflows, which might limit full lifecycle management, but agents can still perform essential workflows with the available tools.
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Unified MCP Server is a remote MCP connector for AI agents and vertical AI products that provides access to 22,000+ authorized SaaS tools across 400+ integrations and 24 categories directly inside LLMs (Claude, GPT, Gemini, Cohere). Tools operate only on explicitly authorized customer connections, enabling agents to safely read and write against live third-party systems.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server built with mcp-framework that allows users to create and manage custom tools for processing data, integrating with the Claude Desktop via CLI.22 npm5MIT

Fastn Serverofficial
AlicenseNot gradedqualityCmaintenanceAn MCP server that enables dynamic tool registration and execution based on API definitions, providing seamless integration with services like Claude.ai and Cursor.ai.23MIT- FlicenseCqualityDmaintenanceA server built with mcp-framework that allows users to extend Claude's capabilities by adding custom tools that can be used through the Claude Desktop client.395 npm-
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server that allows Claude AI to interact with custom tools, enabling extension of Claude's capabilities through the MCP framework.-