MCP Server for SS&C Next Generation

🧾 MCP Server for SS&C Next Generation

This project provides an MCP-compatible server that connects AI agents to SS&C Next Generation, enabling automated execution of business processes via the REST API.

Designed with flexibility in mind, this server allows you to:

Easily define and manage tools using a simple CSV configuration, without modifying source code.

Automatically submit items to Work Queues, a key component of Next Gen RPA orchestration.

Trigger automation flows in response to new queue items, creating a seamless bridge between AI-driven decisions and RPA actions.

Whether you're integrating conversational agents, scheduling systems, or custom applications, this server gives you a low-code interface to dynamically register actions and automate task submission with minimal overhead.

🚀 Installation & Setup

This section helps you set up and run an MCP-compatible server that interacts with SS&C Next Gen REST API.

🔧 Prerequisites

Python 3.10 or later
uv (recommended) package manager
MCP-compatible client (e.g., Claude Desktop)
SS&C Next Generation Environment(Japanese/English)

📥 Installation Steps

Prepare Next Generation Service Account

Refer to the link below to create a service account.

Service Account

Prepare Next Generation Work Queue

Work queue preparation is required when using dynamic tools. Please refer to the following link to create a work queue.

Work Queues

When combining with automated processing, it is necessary to check the following Automation Flow information and link it to the work queue

Automation Flow

Prepare the project directory

git clone https://github.com/abe1bp/mcp-server-nextgen.git
cd mcp-server-nextgen

⚙️ Add MCP Server to `claude_desktop_config.json`

To connect Claude Desktop to your server, add:

{
  "mcpServers": {
    "mcp-server-nextgen": {
      "command": "uv",
      "args": [
        "--directory",
        "{folder path}",
        "run",
        "mcp-server-nextgen"
      ],
      "env": {
        "OAUTH_CLIENT_ID": "{your-client-id}",
        "OAUTH_CLIENT_SECRET": "{your-client-secret}",
        "OAUTH_TOKEN_URL": "https://{tenant-domain}/realms/{tenant-id}/protocol/openid-connect/token",
        "BASE_URL": "https://{tenant-domain}/regions/{region}/api/rpa/rest/v1"
      }
    }
  }
}

{folder path} is the folder prepared in Prepare the project directory.

Cconfigure the {your-client-id} and {your-client-secret} of the Service Account created in Step 1 of the Installation Steps.

For each URL parameters, please refer to the links provided below. Next Generation REST API Then restart Claude Desktop and select mcp-server-nextgen.

📌 Purpose

This Python-based MCP server leverages the Model Context Protocol (MCP) to:

Connect to Next Generation REST API
Authenticate via OAuth2 and expose secure MCP endpoints
Dynamically define tools to submit items to Next Generation Work Queues

📁 Key Components

🛠 Tool Types

🧩 Retrive Tools (predefined)

retrieve-automation-flow-list
retrieve-activity-log-list
retrieve-digital-worker-list
retrieve-session-list

🧩 Start automation flow Tool (predefined)

start-automation-flow

📄 Dynamic Tools (CSV-defined)

CSV Configuration for Dynamic Tool Loading

The workqueues.csv file defines tools that are dynamically loaded at server startup. Each row in the CSV represents a tool that can submit an item to a specific work queue.

Column Descriptions

Here is a clearer breakdown of the required columns:

Column	Required	Description
`workqueueid`	Yes	The unique identifier (UUID format) of the work queue where the item will be submitted.
`name`	Yes	A short, unique identifier for the tool. Used as its registered name.
`description`	Yes	A brief explanation of what the tool does. Displayed to clients and used to assist tool discovery.
`inputSchema`	Yes	A JSON Schema (as a string) defining the input structure required by the tool. Each input parameter must include a `description` to be usable by the client.
`keyValue`	No	A key or identifier that will be passed to the queue item (e.g., an Order ID). Can be a fixed value or a reference.
`priority`	No	An integer indicating the priority of the submitted item (e.g., 0 = lowest, 100 = highest).
`status`	No	Initial status assigned to the item when submitted (e.g., `New`, `Pending`).
`tags`	No	Comma-separated tags to help categorize or filter items in the queue.

Example

workqueueid,name,description,inputSchema,keyValue,priority,status,tags
aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee,submit-order,"Submit an order",{"type":"object","properties":{"OrderId":{"type":"string","description":"Order ID"}}},"Order001",50,"New","order,urgent"

Notes

Make sure inputSchema is a valid JSON object serialized as a string.
The description fields within inputSchema are essential for UI rendering and interaction.
You can omit optional columns if not needed, but headers must still be present.

This format allows you to configure and register dynamic tools for queue submissions without code changes.

📌 Dynamic tools are flexible:

You can define multiple tools per work queue.
Set proper name, description, inputSchema, and parameters to trigger item submission only when needed.

📤 Prompts

This is used when Client id and Client Secret are not set as environment variables.

Prompt Name	Purpose
Set-NextGen-Login	Set Client ID / Secret manually

🧪 Example: Tool Execution

✅ Call `retrieve-digital-worker-list`

Returns the list of digital workers and updates MCP clients via resources_changed.

✅ Call `submit-order` (CSV-defined tool)

Posts an item to a work queue:

{
  "keyValue": "Order001",
  "priority": 50,
  "status": "New",
  "tags": ["order", "urgent"],
  "data": "<base64-encoded XML>"
}

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

An MCP-compatible server that connects AI agents to SS&C Next Generation, enabling automated execution of business processes via REST API.

Related MCP Servers

Postman Tool Generation MCP Server
giovannicocco
A
security
A
license
A
quality
An MCP server that generates AI agent tools from Postman collections and requests. This server integrates with the Postman API to convert API endpoints into type-safe code that can be used with various AI frameworks.
Last updated -
1
7
JavaScript
MIT License
Superset MCP Integration
aptro
-
security
A
license
-
quality
MCP server enabling AI agents to programmatically connect to and control Apache Superset instances, allowing users to manage dashboards, charts, databases, datasets, and run SQL queries through natural language interactions.
Last updated -
20
Python
MIT License
Sequential Thinking Multi-Agent System
FradSer
-
security
F
license
-
quality
An advanced MCP server that implements sophisticated sequential thinking using a coordinated team of specialized AI agents (Planner, Researcher, Analyzer, Critic, Synthesizer) to deeply analyze problems and provide high-quality, structured reasoning.
Last updated -
124
Python
Agentforce MCP Server
xlengelle-sf
-
security
-
license
-
quality
This MCP server provides tools to interact with the Salesforce Agentforce API, allowing authentication, session creation, and message exchange with Salesforce agents.
Last updated -
1
Python

View all related MCP servers

MCP Server for SS&C Next Generation