kingdee-mcp
Click on "Install 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., "@kingdee-mcpShow me all sales orders created this month"
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.
kingdee-mcp
一个用于查询 Kingdee-ierp(金蝶云苍穹) 的 MCP 服务,基于 uvx 打包。
功能
查询销售订单
查询生产工单
查询 SO-MO 关联关系
查询交付风险
查询物料短缺
导出 SO-MO Excel 报表
Related MCP server: sap-mcp
环境变量
在启动服务之前,请先设置以下环境变量:
$env:KINGDEE_BASE_URL = "https://your-host/ierp/kapi"
$env:KINGDEE_CLIENT_ID = "your-client-id"
$env:KINGDEE_CLIENT_SECRET = "your-client-secret"
$env:KINGDEE_USERNAME = "your-username"
$env:KINGDEE_ACCOUNT_ID = "your-account-id"
$env:KINGDEE_LANGUAGE = "zh_CN"必填变量:
KINGDEE_BASE_URLKINGDEE_CLIENT_IDKINGDEE_CLIENT_SECRETKINGDEE_USERNAMEKINGDEE_ACCOUNT_ID
第一步
1.第三方应用——新增 2.获取CLIENT_ID,CLIENT_SECRET,ACCOUNT_ID
第二步
pip install kingdee-mcp-ierp第三步
设置配置
Trae MCP 配置
你也可以直接复制 .mcp.json.example,然后填入你自己的配置值。
{
"mcpServers": {
"kingdee": {
"command": "uvx",
"args": ["kingdee-mcp-ierp"],
"env": {
"KINGDEE_BASE_URL": "https://your-host/ierp/kapi",
"KINGDEE_CLIENT_ID": "your-client-id",
"KINGDEE_CLIENT_SECRET": "your-client-secret",
"KINGDEE_USERNAME": "your-username",
"KINGDEE_ACCOUNT_ID": "your-account-id",
"KINGDEE_LANGUAGE": "zh_CN"
}
}
}
}Available Tools
6 toolsexport_so_mo_reportC
导出完整的 SO-MO 关联报告为 Excel 文件。
| Name | Required | Description | Default |
|---|---|---|---|
| end_date | Yes | ||
| start_date | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It only states export to Excel but omits details like file size limits, time range constraints, authentication needs, or whether the file is generated synchronously.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, but it lacks structure such as breaking down purpose, parameters, or output. It is functional but minimal.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool exports to Excel and has an output schema, the description should clarify what the report contains (e.g., order details). It remains vague, limiting the agent's understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%; the description does not mention the parameters (start_date, end_date) or their format. It adds no meaning beyond the property names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool exports a complete SO-MO associated report to an Excel file. The verb 'export' and resource 'SO-MO associated report' are specific and distinguish it from sibling query tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like query_so_mo_relation. Contexts such as data volume, prerequisites, or when not to use are absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query_delivery_riskC
查询存在交货风险的工单。
| Name | Required | Description | Default |
|---|---|---|---|
| end_date | Yes | ||
| start_date | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description provides no behavioral traits beyond basic purpose. No annotations exist, so the description carries full burden but fails to disclose whether the operation is read-only, destructive, or any other behaviors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one short sentence, efficiently conveying purpose but omitting critical details. While concise, it sacrifices necessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has two required parameters with no descriptions and no annotations, the description is too minimal. It does not compensate for the lack of parameter semantics or behavioral transparency.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain the two parameters (start_date, end_date). The input schema also lacks parameter descriptions, leaving the agent with no semantic information about the date range meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries work orders with delivery risk. It uses a specific verb 'query' and resource 'work orders with delivery risk', which distinguishes it from sibling tools like query_material_shortage or export_so_mo_report.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. The description does not specify context, prerequisites, or scenarios where this tool is appropriate over siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query_material_shortageC
查询欠料/瓶颈物料汇总。
| Name | Required | Description | Default |
|---|---|---|---|
| top_n | No | ||
| end_date | Yes | ||
| start_date | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies a read-only query but does not explicitly disclose behavioral traits. No annotations are present to aid transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely short (one sentence) but under-specified. It lacks structure and fails to provide essential details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 parameters and an output schema, the description is grossly incomplete. It does not cover return values or parameter usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the input schema. With 0% schema description coverage, it fails to explain parameters like top_n, start_date, end_date.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it queries a summary of material shortage/bottleneck, which is a specific verb and resource. However, it does not differentiate from sibling tools like query_delivery_risk, and the scope is vague.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. No context on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query_mft_ordersC
查询金蝶云苍穹生产工单列表。
| Name | Required | Description | Default |
|---|---|---|---|
| end_date | Yes | ||
| start_date | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits such as side effects, authentication needs, or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no unnecessary words. However, it is minimal.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has two required parameters and no param documentation, the description is insufficient for an agent to use it correctly. The presence of an output schema helps but does not compensate for missing parameter details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, and the description does not explain the meaning, format, or constraints of the start_date and end_date parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: querying a list of production work orders in Kingdee Cloud Cangqiong. It uses a specific verb and resource. However, it does not distinguish itself from sibling tools like query_sale_orders.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus its siblings, nor any context about prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query_sale_ordersC
查询金蝶云苍穹销售订单列表。
| Name | Required | Description | Default |
|---|---|---|---|
| end_date | Yes | ||
| start_date | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits such as read-only nature, authentication requirements, rate limits, or pagination behavior. The description carries the full burden but fails to provide this essential context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (single sentence), but it is under-specified for a tool with two required parameters and no other context. While brevity is good, it sacrifices necessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (list query with date range), the description is incomplete. It lacks explanation of the output format, behavior when no data, and date format expectations. The output schema exists but is not described, so the agent lacks full understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, meaning no parameter descriptions in the schema. The tool description does not add any meaning to the two date parameters (start_date, end_date) beyond their names. No format, example, or constraints are given.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it queries a list of sales orders (specific verb and resource). The name and description together make the purpose obvious, and it is distinct from sibling tools like export_so_mo_report or query_delivery_risk.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance provided on when to use this tool versus alternatives, nor any prerequisites or conditions. Only a single sentence stating what it does.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query_so_mo_relationB
查询销售订单与生产工单的关联关系,包含完工状态、交货风险和领料情况。
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| end_date | Yes | ||
| start_date | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It accurately describes the function as a query, but lacks details on default limits, possible pagination, or read-only nature. The behavior is implied but not fully transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that immediately states the purpose and included aspects. No redundant words; every part contributes to understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks essential details for a query with date range and optional limit parameters. It does not explain how parameters filter results, nor does it mention default limit or output structure (despite having an output schema). The description is insufficient for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. However, it does not explain the parameters (start_date, end_date, limit) or how they relate to the output content. The description adds no value beyond the schema titles.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries the relationship between sales orders and production work orders, listing three included aspects (completion status, delivery risk, material picking). It distinguishes from siblings like query_delivery_risk and query_material_shortage by focusing on the SO-MO relationship.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is used to retrieve SO-MO relations but does not explicitly state when to use it over alternatives like query_delivery_risk or export_so_mo_report. No exclusions or conditional usage are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
6 tool updates
v0.1.2- First observed
export_so_mo_report - First observed
query_delivery_risk - First observed
query_material_shortage - First observed
query_mft_orders - First observed
query_sale_orders - First observed
query_so_mo_relation
TDQS
Scored across 6 tools
Each tool targets a distinct aspect: sales orders, production orders, their relation, material shortages, delivery risks, and a report export. No overlapping purposes.
Five tools use the consistent 'query_' prefix with noun phrases, but 'export_so_mo_report' deviates with 'export_' instead of 'query_', introducing minor inconsistency.
Six tools is well-scoped for a domain focused on querying and reporting in a manufacturing/sales context. Each tool serves a clear purpose without excess.
The set covers key query and reporting needs: orders, relations, risks, shortages, and an export. Missing CRUD operations, but for a read-only/reporting server, this is appropriate.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
중소 제조기업용 ERP 조회 전용 MCP 서버(재고·매출·채권·수주/발주·회계). 쓰기 도구 없음.
MCP server for querying and analyzing data from ad platforms, analytics tools, and spreadsheets
Read-only MCP server for searching Japan government procurement bid information from the KKJ portal.
MCP server for Product Management
Related MCP Servers
- AlicenseAqualityAmaintenanceMCP server for Kingdee K3Cloud ERP that enables AI assistants to query and operate ERP data via natural language through the Model Context Protocol.1572Apache 2.0
- AlicenseNot gradedqualityBmaintenanceMCP server for SAP S/4HANA via the ADT API, enabling querying and reading SAP systems with production write protection.2MIT
- FlicenseNot gradedqualityBmaintenanceMCP server that enables AI platforms to search products, customers, and warehouses, and prepare and submit sales orders to a fixed ERP endpoint with per-session bearer authentication.-
- AlicenseBqualityCmaintenanceMCP server for Kingdee Cloud (K3Cloud) ERP that enables AI assistants to query and operate ERP data through natural language, supporting bills, metadata, and read/write operations.81Apache 2.0