Plugin & Skill Manager
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| open_skill_managerA | 扫描技能并打开管理器。启用自动采集时增量读取本机日志的宿主工具事件，只保存调用标识和时间，不保存正文。 |
| check_recording_statusA | 只读检查已有采用和插件调用账本，返回总数与最近接收时间。不写测试事件、不读取聊天、不证明其他会话已经接入；空账本不等于没有实际活动。 |
| configure_auto_captureA | 按用户要求启停跨会话本地日志采集并设置 5 至 3600 秒检查间隔。启用后读取 sessions 和 archived_sessions 的真实 MCP 调用事件；仅保存标识与时间。配置在本机持久化，不调用模型、不联网、不自动确认 Skill 采用。 |
| check_plugin_statusA | 通过官方 app-server plugin/installed 读取已安装插件版本和启用状态，不拉取远程市场目录，不扫描活动日志。 |
| import_usageA | 读取本机 Codex sessions 和 archived_sessions 日志，增量提取显式标记与读取请求。只将信号、来源定位和读取位置写入独立持久数据目录中的 usage-index.json，不保存聊天正文，不联网。 |
| query_usageA | 查询已有 Skill 索引与插件账本；启用自动采集时先增量接收本机宿主调用事件。时间需带时区，包含起点、不包含终点。 |
| record_plugin_callsA | 实际调用插件工具后就近合批记录，每项一次调用尝试（失败也计）；id 使用调用 ID 或事先生成的 UUID，记录重试沿用，新的实际调用使用新 ID。plugin 为工具所属插件命名空间，如 github；tool 为完整 mcp__codex_apps__github_get_repo 名称。仅记录已发生调用，不记录发现、计划或历史补记。不传参数或结果正文，与 Skill 采用分开。 |
| record_skill_useA | 采用技能时批量记录。id 为新批次唯一 ID（重试沿用）；skills 为技能名、插件名:技能名或准确路径，可重复，每项计一次。不用于历史补记或仅阅读审计。 |
| save_skill_noteA | 保存用户提供的本地备注和保留标记，不修改技能文件或启停状态。需基于当前文件指纹和备注版本，冲突时拒绝覆盖。 |
| preview_skill_archiveA | 只读预览用户技能目录的归档范围与影响，不执行移动。系统和插件内容不可归档。 |
| preview_skill_restoreB | 只读核对已归档技能并生成恢复预览；原位置已有内容时拒绝覆盖。 |
| execute_skill_planA | 仅在用户已针对该具体预览明确要求执行后调用。按一次性预览令牌移动用户技能目录，保留恢复记录；系统和插件只读。 |
| cancel_skill_planA | 使尚未执行的归档或恢复预览失效，不修改技能文件。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| dashboard |
TDQS
Scored across 13 tools
Tools split into recognizable areas (capture config, log import/query, recording, notes, archive/restore), but boundaries between import_usage, open_skill_manager, query_usage, and check_recording_status are subtle because several involve local log/ledger ingestion or inspection. Descriptions help, but an agent could hesitate between querying existing data vs. incrementally importing more host events.
All tool names use snake_case and a consistent verb-first pattern such as configure_auto_capture, check_plugin_status, record_plugin_calls, preview_skill_archive, and cancel_skill_plan. There is no disruptive mixing of camelCase or vague standalone verbs.
Thirteen tools is within a reasonable range for a plugin/skill management surface that includes capture configuration, usage import/query, recording, notes, and archive/restore lifecycle operations. Each tool maps to a concrete action or safety boundary.
The surface covers usage ingestion/query, call recording, skill notes, plugin status checks, and skill archive/restore previews and execution. However, plugin lifecycle operations such as install/update/enable/disable are absent, and direct skill enable/disable or richer skill management operations are not exposed.