模型上下文协议 (MCP) 服务器，提供对 PowerPlatform/Dataverse 实体和记录的智能访问。此工具提供上下文感知辅助、实体探索和元数据访问。
主要特点：
- 通过格式化、上下文感知的提示进行丰富的实体元数据探索
- 具有智能过滤功能的高级 OData 查询支持
- 全面的关系映射和可视化
- 通过人工智能代理进行人工智能辅助查询构建和数据建模
- 对实体属性、关系和全局选项集的完全访问权限
安装
您可以通过两种方式安装并运行此工具：
选项 1：全局安装
npm install -g powerplatform-mcp
然后运行它：
选项 2：直接使用 npx 运行
无需安装即可运行：
配置
运行前，设置以下环境变量：
# 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
用法
这是一个 MCP 服务器，旨在与兼容 MCP 的客户端（例如 Cursor、Claude App 和 GitHub Copilot）配合使用。运行后，它将提供用于检索 PowerPlatform 实体元数据和记录的工具。
可用工具
get-entity-metadata ：获取有关 PowerPlatform 实体的元数据get-entity-attributes ：获取 PowerPlatform 实体的属性/字段get-entity-attribute ：获取 PowerPlatform 实体的特定属性/字段get-entity-relationships ：获取 PowerPlatform 实体的关系get-global-option-set ：获取全局选项集定义get-record ：通过实体名称和 ID 获取特定记录query-records ：使用 OData 过滤器表达式查询记录use-powerplatform-prompt ：使用 PowerPlatform 实体的预定义提示模板
MCP 提示
该服务器包含一个提示功能，提供有关 PowerPlatform 实体的格式化、上下文丰富的信息。
可用的提示类型
use-powerplatform-prompt工具支持以下提示类型：
- ENTITY_OVERVIEW ：实体的全面概述
- ATTRIBUTE_DETAILS ：有关特定实体属性的详细信息
- QUERY_TEMPLATE ：带有示例过滤器的实体的 OData 查询模板
- RELATIONSHIP_MAP ：实体关系的可视化地图
示例
实体概览提示
// Example client code
await mcpClient.invoke("use-powerplatform-prompt", {
promptType: "ENTITY_OVERVIEW",
entityName: "account"
});
输出：
## Power Platform Entity: account
This is an overview of the 'account' entity in Microsoft Power Platform/Dataverse:
### Entity Details
- Display Name: Account
- Schema Name: Account
- Description: Business that represents a customer or potential customer
- Primary Key: accountid
- Primary Name: name
### Key Attributes
- 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)
### Relationships
- One-to-Many Relationships: 42
- Many-to-Many Relationships: 8
You can query this entity using OData filters against the plural name.
属性详情提示
await mcpClient.invoke("use-powerplatform-prompt", {
promptType: "ATTRIBUTE_DETAILS",
entityName: "account",
attributeName: "revenue"
});
输出：
## 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
### Usage Notes
- Data Type: Money
- Required: No
- Max Length: N/A
查询模板提示
await mcpClient.invoke("use-powerplatform-prompt", {
promptType: "QUERY_TEMPLATE",
entityName: "account"
});
输出：
## 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
常见过滤器示例
- 等于：
name eq 'Contoso' - 包含：
contains(name, 'Contoso') - 大于日期：
createdon gt 2023-01-01T00:00:00Z - 多个条件：
name eq 'Contoso' and statecode eq 0
#### Relationship Map Prompt
```javascript
await mcpClient.invoke("use-powerplatform-prompt", {
promptType: "RELATIONSHIP_MAP",
entityName: "contact"
});
输出：
## Relationship Map for contact
This shows all relationships for the 'contact' entity:
### One-to-Many Relationships (contact as Primary)
- 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)
### One-to-Many Relationships (contact as Related)
- account_primary_contact: account (1) → contact (N)
- customer_contacts: customer (1) → contact (N)
- system_user_contacts: systemuser (1) → contact (N)
### Many-to-Many Relationships
- contactleads_association: contact (N) ↔ lead (N)
- contactopportunities_association: contact (N) ↔ opportunity (N)
- contactquotes_association: contact (N) ↔ quote (N)
提示示例
以下是如何使用 PowerPlatform MCP 提示与助手交互的一些示例：
1.实体理解
您可以用自然语言向助手询问实体：
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
2. 构建查询
您可以寻求构建查询的帮助：
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. 理解关系
您可以自然地探索实体关系：
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
4. 领域/属性调查
您可以询问特定字段：
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
5.复杂数据建模
您可以获得有关数据建模决策的帮助：
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
Here's a sample lookup field structure...
[continues with detailed implementation guidance]
6. 调试协助
您可以获取故障排除帮助：
User: "Why am I getting 'invalid property' when querying account.customertypecode?"
Response:
[uses ATTRIBUTE_DETAILS prompt internally]
I see the issue. The field 'customertypecode' is actually named 'customertype' in your environment. Here's the correct field information:
- Logical Name: customertype
- Type: OptionSetValue
- Valid Values:
* 1 = Competitor
* 2 = Consultant
* 3 = Customer
* 4 = Investor
* 5 = Partner
* 6 = Influencer
Try updating your query to use 'customertype' instead of 'customertypecode'.
这些示例展示了 AI 助手如何利用 MCP 提示，为 PowerPlatform 开发任务提供情境感知的精准辅助。AI 能够理解您环境的具体配置，并能协助您完成简单的查询和复杂的架构决策。
执照
麻省理工学院