mcp-zentao
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ZENTAO_URL | Yes | 禅道应用根地址，例如 https://zentao.example.com | |
| ZENTAO_ENTRY | No | GET 模式的相对入口，默认为 index.php | index.php |
| ZENTAO_PASSWORD | Yes | 禅道登录密码 | |
| ZENTAO_USERNAME | Yes | 禅道登录账号 | |
| ZENTAO_REQUEST_TYPE | No | 请求类型，支持 GET 或 PATH_INFO，默认为 GET | GET |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 48 tools
Many tools have overlapping purposes, such as the multiple export functions (exportItems, exportStory, exportBug, exportStoriesBySearch) and the numerous analysis/generation utilities (generateStorySummary, generateBugSummary, analyzeStoryComplexity, analyzeBugPriority, analyzeTaskWorkload, generateCodePromptFromStory, generateTestPromptFromBug, generateCodeReviewChecklist). Tools like getStoryRelatedBugs and getBugRelatedStory likely refer to the same relationship, creating confusion.
The naming uses a loose verb_noun pattern, but with mixed verb styles and no coherent convention. Synonyms like get/fetch, search/export, and analyze/generate are used interchangeably. There is also inconsistent camelCase and batch prefixes (e.g., updateTask vs batchUpdateTasks) without a clear systematic structure.
48 tools is excessively heavy for a single server. While ZenTao is a broad domain, many tools are near-duplicates (multiple export variants, numerous analysis helpers) that could be consolidated. The count appears inflated with convenience wrappers rather than essential distinct operations.
The set covers fetching and updating tasks/bugs/stories but lacks core lifecycle operations like createStory, updateStory, deleteBug, or closeTask. Test case creation exists but no update/delete, and there is no createTestTask. The heavy emphasis on analysis and export leaves gaps in standard CRUD workflows, causing incomplete coverage.