PowerPlatform MCP Server

A Model Context Protocol (MCP) server that provides intelligent access to PowerPlatform/Dataverse entities and records. This tool offers context-aware assistance, entity exploration and metadata access.

Key features:
- Rich entity metadata exploration with formatted, context-aware prompts
- Advanced OData query support with intelligent filtering
- Comprehensive relationship mapping and visualization
- AI-assisted query building and data modeling through AI agent
- Full access to entity attributes, relationships, and global option sets

Installation

You can install and run this tool in two ways:

$3

``bash
npm install -g powerplatform-mcp
`

Then run it:

`bash
powerplatform-mcp
`

$3

Run without installing:

`bash
npx powerplatform-mcp
`

Configuration

Before running, set the following environment variables:

`bash

PowerPlatform/Dataverse connection details

POWERPLATFORM_URL=https://yourenvironment.crm.dynamics.com
POWERPLATFORM_CLIENT_ID=your-azure-app-client-id
POWERPLATFORM_CLIENT_SECRET=your-azure-app-client-secret
POWERPLATFORM_TENANT_ID=your-azure-tenant-id
`

$3

1. Clone the repository and install dependencies:
`bash
git clone https://github.com/michsob/powerplatform-mcp.git
cd powerplatform-mcp
npm install
`

2. Copy .env.example to .env and fill in your credentials:
`bash
cp .env.example .env
`

3. Build and test:
`bash
npm run build
npm run inspector:debug
`

Usage

This is an MCP server designed to work with MCP-compatible clients like Cursor, Claude App and GitHub Copilot. Once running, it will expose tools for retrieving PowerPlatform entity metadata and records.

$3

- get-entity-metadata: Get metadata about a PowerPlatform entity
- get-entity-attributes: Get attributes/fields of a PowerPlatform entity
- get-entity-attribute: Get a specific attribute/field of a PowerPlatform entity
- get-entity-relationships: Get relationships for a PowerPlatform entity
- get-global-option-set: Get a global option set definition
- get-record: Get a specific record by entity name and ID
- query-records: Query records using an OData filter expression
- use-powerplatform-prompt: Use pre-defined prompt templates for PowerPlatform entities

MCP Prompts

The server includes a prompts feature that provides formatted, context-rich information about PowerPlatform entities.

$3

The use-powerplatform-prompt tool supports the following prompt types:

1. ENTITY_OVERVIEW: Comprehensive overview of an entity
2. ATTRIBUTE_DETAILS: Detailed information about a specific entity attribute
3. QUERY_TEMPLATE: OData query template for an entity with example filters
4. RELATIONSHIP_MAP: Visual map of entity relationships

$3

#### Entity Overview Prompt

`javascript
// Example client code
await mcpClient.invoke("use-powerplatform-prompt", {
promptType: "ENTITY_OVERVIEW",
entityName: "account"
});
`

Output:
`

Power Platform Entity: account

This is an overview of the 'account' entity in Microsoft Power Platform/Dataverse:

$3

- Display Name: Account
- Schema Name: Account
- Description: Business that represents a customer or potential customer
- Primary Key: accountid
- Primary Name: name

$3

- name: String (Account Name)
- emailaddress1: String (Email)
- telephone1: String (Main Phone)
- address1_city: String (City)
- statecode: Status (Status)
- accountnumber: String (Account Number)
- industrycode: OptionSetValue (Industry)
- revenue: Money (Annual Revenue)
- ownerid: Owner (Owner)
- createdon: DateTime (Created On)

$3

- One-to-Many Relationships: 42
- Many-to-Many Relationships: 8

You can query this entity using OData filters against the plural name.
`

#### Attribute Details Prompt

`javascript
await mcpClient.invoke("use-powerplatform-prompt", {
promptType: "ATTRIBUTE_DETAILS",
entityName: "account",
attributeName: "revenue"
});
`

Output:
`

Attribute: revenue

Details for the 'revenue' attribute of the 'account' entity:

- Display Name: Annual Revenue
- Description: Annual revenue for the account
- Type: Money
- Format: Currency
- Is Required: No
- Is Searchable: true

$3

- Data Type: Money
- Required: No
- Max Length: N/A
`

#### Query Template Prompt

`javascript
await mcpClient.invoke("use-powerplatform-prompt", {
promptType: "QUERY_TEMPLATE",
entityName: "account"
});
`

Output:
`

OData Query Template for accounts

Use this template to build queries against the accounts entity:
accounts?$select=name,emailaddress1,telephone1, address1_city,statecode&$filter=name eq 'Example'&$orderby=name asc&$top=50
`

$3

- Equals: name eq 'Contoso'
- Contains: contains(name, 'Contoso')
- Greater than date: createdon gt 2023-01-01T00:00:00Z
- Multiple conditions: name eq 'Contoso' and statecode eq 0
`

#### Relationship Map Prompt

`javascript
await mcpClient.invoke("use-powerplatform-prompt", {
promptType: "RELATIONSHIP_MAP",
entityName: "contact"
});
`

Output:
`

Relationship Map for contact

This shows all relationships for the 'contact' entity:

$3

- contact_activity_parties: contact (1) → activityparty (N)
- contact_connections1: contact (1) → connection (N)
- contact_connections2: contact (1) → connection (N)
- contact_customer_contacts: contact (1) → contact (N)
- contact_master_contact: contact (1) → contact (N)

$3

- account_primary_contact: account (1) → contact (N)
- customer_contacts: customer (1) → contact (N)
- system_user_contacts: systemuser (1) → contact (N)

$3

- contactleads_association: contact (N) ↔ lead (N)
- contactopportunities_association: contact (N) ↔ opportunity (N)
- contactquotes_association: contact (N) ↔ quote (N)
`

Prompt Examples

Here are some examples of how you can interact with assistant using the PowerPlatform MCP prompts:

$3

You can ask assistant about entities in natural language:

`
User: "Tell me about the Account entity in our PowerPlatform environment"

Response:
[uses ENTITY_OVERVIEW prompt internally]

Here's what I found about the Account entity:
- It's a core business entity representing customers and potential customers
- The primary identifier is 'accountid' and the primary name field is 'name'
- Key fields include:
* name (Account Name)
* emailaddress1 (Email)
* telephone1 (Main Phone)
* revenue (Annual Revenue)
- It has 42 one-to-many relationships and 8 many-to-many relationships
`

$3

You can ask for help constructing queries:

`
User: "Help me write a query to find active accounts with revenue over $1M in California"

Response:
[uses QUERY_TEMPLATE prompt internally]

Here's the OData query you need:
accounts?$select=name,revenue,statecode,address1_stateorprovince
&$filter=statecode eq 0
and revenue gt 1000000
and address1_stateorprovince eq 'California'
&$orderby=revenue desc

This query:
1. Selects relevant fields
2. Filters for active accounts (statecode eq 0)
3. Checks revenue > $1M
4. Filters for California location
5. Orders by revenue highest to lowest
`

$3

You can explore entity relationships naturally:

`
User: "How are Accounts and Contacts related in our system?"

Response:
[uses RELATIONSHIP_MAP prompt for both entities internally]

Here are the key relationships between Accounts and Contacts:

1. Primary Contact (One-to-Many):
- account_primary_contact: Account (1) → Contact (N)
- An account can have many contacts, but one designated as primary

2. Customer Relationship:
- contact_customer_accounts: Contact (N) ← Account (1)
- Contacts can be associated with customer accounts

3. Additional Relationships:
- accountleads_association: For lead tracking
- account_connections: For relationship management
`

$3

You can ask about specific fields:

`
User: "What kind of field is the revenue field on Account?"

Response:
[uses ATTRIBUTE_DETAILS prompt internally]

The revenue field on Account is:
- Data Type: Money
- Format: Currency
- Not required
- Searchable: Yes
- Used for: Tracking annual revenue for the account
- Can be used in advanced find and filtered views
`

$3

You can get help with data modeling decisions:

``
User: "I need to design a solution for tracking product reviews. Which entities should I relate to?"

Response:
[uses multiple ENTITY_OVERVIEW and RELATIONSHIP_MAP prompts internally]

Based on the existing data model, here's a suggested approach:

1. Product (existing entity):
- Already has relationships with:
* Price lists
* Product categories
* Inventory units

2. New Review entity should relate to:
- Product (N:1) - Each review is for one product
- Contact (N:1) - Reviews are written by contacts
- Account (N:1) - Optional link to company if B2B review




These examples show how AI assistant can leverage the MCP prompts to provide context-aware, accurate assistance for PowerPlatform development tasks. The AI understands your environment's specific configuration and can help with both simple queries and complex architectural decisions.

License

MIT