gh-autostar
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | GitHub token used to authenticate. If omitted, the server reads the gh CLI login state (e.g. via gh auth token). | |
| GH_AUTOSTAR_HOME | No | Overrides the default config file location (~/.gh-autostar/config.json). | ~/.gh-autostar/config.json |
| GH_AUTOSTAR_MODE | No | Temporarily override the mode (auto, confirm, or dry-run), e.g. GH_AUTOSTAR_MODE=dry-run. | auto |
| GH_AUTOSTAR_DISABLED | No | Temporarily disable gh-autostar, e.g. GH_AUTOSTAR_DISABLED=1. | |
| GH_AUTOSTAR_DAILY_CAP | No | Temporarily override the daily star cap, e.g. GH_AUTOSTAR_DAILY_CAP=3. | 10 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
gh-autostar 已启用：当你在本次会话中"实际用到"某个 GitHub 仓库时，调用 ensure_starred 给它点一个 star，作为对开源作者的支持。
"实际用到"指：克隆仓库、把它装成依赖、读它的源码/README、抓取它的文档、采纳它的方案作为答案的落地方案。
规则：
同一个仓库每轮对话只需调用一次；工具自身幂等，重复调用不会产生副作用。
只在确实用到时调用。不要为了凑数去遍历搜索结果、trending 或依赖树批量点星。
调用时尽量带上 reason（一句话说明用途），便于用户事后回溯。
返回"未点星 xxx：已达今日上限 / 黑名单 / dry-run / 已点过"都是正常结果，不要重试，也不要换个写法绕过策略。
不要主动向用户汇报每一次点星；只在 failed 时说明，或用户问起时再讲。
用户明确表示"别点星"后，本轮对话不要再调用 ensure_starred。
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
| Name | Description |
|---|---|
| ensure_starredA | 当你在本轮对话中实际使用、阅读或采纳了某个 GitHub 仓库时调用，为该仓库点一个 star。幂等，可安全重复调用。 |
| check_starA | 查询某个 GitHub 仓库当前是否已被当前账号点星（同时检查 GitHub 远端与本地账本）。只读操作。 |
| unstarB | 撤销对某个 GitHub 仓库的星标（误点或用户要求取消时使用）。 |
| star_statusA | 查看自动点星的状态：总开关、模式、今日已用配额、账号登录情况、黑名单等。 |
| list_recent_starsA | 列出最近的点星记录（审计用），包含时间、仓库、来源与原因。 |
| configure_autostarB | 修改自动点星配置：开关、模式、每日上限、白名单/黑名单增删。用户要求"别点星了""只给某几个仓库点"时使用。 |
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 6 tools
Each tool maps to a distinct action: starring (ensure_starred), verifying (check_star), removing (unstar), configuring (configure_autostar), and two read-only views. The only mild overlap is between star_status (global config/state) and list_recent_stars (history log), but the descriptions make the boundary clear enough.
Most names follow verb_noun (check_star, list_recent_stars, configure_autostar), but ensure_starred uses a past-participle form, unstar is a bare verb, and star_status leads with a noun. The conventions are mixed yet still readable and predictable enough to infer intent.
Six tools cover the full lifecycle of a narrow, well-defined domain without redundancy. Each tool earns its place: act, verify, undo, inspect state, audit, and configure.
Star/unstar/check plus status, audit history, and configuration covers the core lifecycle with no dead ends. Minor gaps exist—no batch operations and no dedicated query for current whitelist/blacklist contents beyond what star_status exposes.