doctrove
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DOCTROVE_DEBUG | No | Enable debug logging. Set to 'true' to enable. Default 'false'. Can be set via --debug. | false |
| DOCTROVE_CONFIG | No | Path to a JSON configuration file. Default none. Can be set via --config. | |
| DOCTROVE_CACHE_TTL | No | Cache lifetime in seconds (0-86400, 0 disables cache). Default 600. Can be set via --cache-ttl or --no-cache for 0. | 600 |
| DOCTROVE_INDEX_URL | No | Remote index URL. The URL of the directory containing index.json. If not set, offline mode uses the built-in index. Can be set via --index-url. | |
| DOCTROVE_TIMEOUT_MS | No | Remote index fetch timeout in milliseconds. Default 15000. Can be set via --timeout-ms. | 15000 |
| DOCTROVE_LOCAL_INDEX | No | Path to a local index JSON file. Defaults to the built-in data/index.json. Can be set via --local-index. | data/index.json |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| catalog_lookupA | 检索文档目录：按库/框架的名称或描述查找条目，返回带相关度评分与命中信号的候选列表。当不确定库的规范 id 时，先调用本工具；后续用返回的 id 调用 doc_extract。结果按评分降序，评分依据：名称精确/前缀/别名命中 > 摘要词元命中 > 流行度微调。 |
| catalog_releasesA | 查看条目的可用版本清单与推荐版本。支持 "latest"、精确版本号（如 "5.1.0"）与前缀（如 "5" 或 "5.1" 或 "5.1.x"）。先于 doc_extract 调用可确定目标版本是否可用。 |
| doc_extractA | 提取文档：按条目 id、版本与聚焦点（focus）取回相关文档片段，片段按相关度评分降序。focus 建议一次只描述一个概念（如 "路由参数"），跨概念问题分多次调用。version 缺省取最新稳定版；支持精确版本号与前缀（如 "4"）。返回中包含 releaseNote 说明版本选择依据、source 标注数据来源。 |
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 3 tools
Each tool serves a clearly distinct role: lookup finds the canonical ID, releases lists available versions, and extract fetches documentation content. Their purposes are complementary with no overlap, and the descriptions explicitly indicate when to use each tool.
Two tools follow the 'catalog_' prefix pattern, while the third uses 'doc_'. This is a minor deviation, but the verbs (lookup, releases, extract) are consistently descriptive and make the tool purposes clear despite the prefix mismatch.
With only three tools, the server is tightly scoped to its purpose of documentation retrieval. Each tool is essential to the workflow, and the count is within the well-scoped range for a specialized server.
The set covers the full pipeline from discovering the correct entry and checking version availability to extracting focused documentation fragments. There are no obvious dead ends or missing operations for the server's stated purpose.