Kingdee MCP Server
Related Servers
Alternatives to Kingdee MCP Server
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to query and operate Dingjie ERP system via natural language, covering procurement, sales, and material management.2-
- 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
- AlicenseNot gradedqualityBmaintenanceEnables read-only, natural-language queries of Kingdee ERP data such as revenue and inventory cost, along with local Excel report exports.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to safely query Kingdee Cloud Galaxy ERP with read-only mode, write confirmation gates, and full audit logging.AGPL 3.0
- AlicenseAqualityAmaintenanceMCP server for Kingdee K3Cloud ERP that enables AI assistants to query and operate ERP data via natural language through the Model Context Protocol.15172 PyPI88Apache 2.0
- AlicenseAqualityDmaintenanceEnables AI assistants to interact with ECOUNT ERP through natural language, providing tools for products, inventory, sales, purchases, and more.2324 npm3MIT
TDQS
Scored across 81 tools
While individual tool descriptions are detailed, the sheer number (81) and overlapping names (e.g., multiple query tools for similar domains like purchase orders vs. purchase order progress) cause confusion. Some tools appear to have nearly identical purposes (e.g., kingdee_query_transfer_apply and kingdee_query_stock_transfer_apply). Agents may struggle to select the correct tool despite good descriptions.
All tools follow the kingdee_ prefix with predominantly verb_noun pattern (e.g., query_*, save_*, audit_*). Use of snake_case is consistent. Minor deviations exist like 'kingdee_usage_report' and 'kingdee_usage_stats' which are noun_noun, and 'kingdee_create_and_audit' which uses 'and'. Overall, consistency is high.
81 tools is excessive for a single MCP server. While covering a large ERP domain, the number overwhelms the tool surface. A more modular approach (e.g., separate servers for purchasing, sales, inventory, etc.) would improve clarity and reduce cognitive load for agents. The count is borderline high.
The server covers a wide range of Kingdee operations: CRUD for bills (save, submit, audit, unaudit, delete), queries for many document types (purchase, sales, inventory, production, assets), push operations, and audit logs. Minor gaps exist, such as missing update tools for specific entities (e.g., assets only have save, no update) and no delete for non-bill entities. Overall, it is comprehensive for the stated domain.