Dynamics 365 Finance & Operations

Production-ready MCP server exposing D365 F&O data and actions to MCP-compatible clients and AI assistants.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mafzaal-d365fo-client": {
      "command": "uvx",
      "args": [
        "--from",
        "d365fo-client@latest",
        "d365fo-fastmcp-server"
      ],
      "env": {
        "D365FO_BASE_URL": "https://your-environment.dynamics.com",
        "D365FO_CLIENT_ID": "your-client-id",
        "D365FO_LOG_LEVEL": "INFO",
        "D365FO_TENANT_ID": "your-tenant-id",
        "D365FO_CLIENT_SECRET": "your-client-secret"
      }
    }
  }
}

The Dynamics 365 Finance & Operations MCP Server exposes the full capabilities of D365 F&O to MCP-compatible tools and AI assistants. It enables integrated workflows, secure access, and scalable interactions through a production-ready MCP implementation with multiple transport options and robust security features.

How to use

Connect a compatible MCP client to harness the D365 F&O data and operations. Use the standard stdio transport for local development with a command that starts the MCP server through the FastMCP framework. You can also run the server as an HTTP endpoint for web integrations or SSE for real-time updates. In your client, point to the MCP server and begin discovering available tools, then execute queries, CRUD operations, metadata lookups, and actions against D365 F&O.

How to install

Prerequisites you need before starting:

Python 3.7+ and pip for Python-based setup
Optional: Docker if you prefer containerized deployment

What you will do to install and run the MCP server:

Install the MCP client package that includes the MCP server tooling

pip install d365fo-client

Start the FastMCP server via the standard command shown for development and integration use

uvx --from d365fo-client@latest d365fo-fastmcp-server

If you plan to connect with explicit credentials, set the required environment variables before starting the server

export D365FO_BASE_URL="https://your-environment.dynamics.com"
export D365FO_LOG_LEVEL="INFO"
export D365FO_CLIENT_ID="your-client-id"      # optional with default credentials
export D365FO_CLIENT_SECRET="your-client-secret"  # optional with default credentials
export D365FO_TENANT_ID="your-tenant-id"          # optional with default credentials

Azure deployment options (production-ready HTTP endpoint)

You can deploy the MCP server as a secure HTTP endpoint for web integrations with OAuth or API Key authentication. This enables remote AI assistants to access D365 F&O through a stable, authenticated API surface.

Option 1: Bash script deployment (recommended) allows you to install and deploy quickly.

# Download and run the deployment script
curl -O https://raw.githubusercontent.com/mafzaal/d365fo-client/main/deploy-aca.sh
chmod +x deploy-aca.sh

# Set authentication (choose OAuth or API Key)
export D365FO_MCP_AUTH_CLIENT_ID="your-client-id"
export D365FO_MCP_AUTH_CLIENT_SECRET="your-client-secret"
export D365FO_MCP_AUTH_TENANT_ID="your-tenant-id"
# OR
export D365FO_MCP_API_KEY_VALUE="your-secret-key"

# Deploy
./deploy-aca.sh

Additional deployment options

Option 2: ARM template deployment lets you provision the HTTP endpoint in Azure Container Apps or similar cloud environments. Download the template, provide your parameters in the portal, and deploy.

Also available is a comprehensive Python client library that provides OData endpoints, metadata operations, label management, and CLI tools for interacting with D365 F&O through MCP.

Built by

VeilStrat

AI signals for GTM teams