workbuddy-ai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WB_INTL_NODE | No | Explicit node.exe path for the Windows .bat helpers. | |
| WB_AI_MCP_LOG | No | Set to 1 to output MCP server debug logs to stderr (never prints tokens). | |
| WB_INTL_PROXY_KEY | No | If set, require Authorization: Bearer <key>. | |
| WB_INTL_PROXY_LOG | No | Set to 1 to output proxy request logs (no tokens or bodies). | |
| WB_INTL_PROXY_HOST | No | Proxy bind address, default 127.0.0.1. | |
| WB_INTL_PROXY_PORT | No | Proxy port, default 8787 (re-run register-models.js after changing). | |
| WB_AI_CHAT_TIMEOUT_MS | No | Chat timeout, default 600000 (10 min). | |
| WORKBUDDY_AI_AUTH_FILE | No | Override the desktop credential file path. | |
| WORKBUDDY_AI_ELECTRON_BIN | No | Override WorkBuddyAI.exe path (when auto-discovery fails). |
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 |
|---|---|
| wb_ai_modelsA | 列出 WorkBuddy AI（国际版）当前账号可用的全部模型。返回对话模型名单（含积分倍率、上下文窗口、推理档位、是否支持图片）以及图像/视频等非对话模型。模型 ID 可直接用于 wb_ai_chat 的 model 参数。 |
| wb_ai_chatA | 调用 WorkBuddy AI（国际版）的任意模型完成一次对话补全。model 取自 wb_ai_models。国际版网关强制流式返回，本工具已聚合为完整文本；推理模型的思考过程会放在 reasoning 字段。 |
| wb_ai_statusA | 查看 WorkBuddy AI（国际版）连接状态：登录账号、令牌有效期、剩余积分、本地凭据文件与 App 版本信息。不发起任何模型调用。 |
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 3 tools
The three tools have clearly distinct purposes: listing available models, performing a chat completion, and checking account/connection status. No overlap in operation or expected inputs, so an agent can easily select the right tool.
All tools use the same `wb_ai_` prefix followed by a concise noun describing the resource or action. The pattern is predictable and readable, with no mixed casing or verb-style inconsistencies.
Three tools is a well-scoped minimal surface for an AI gateway wrapper: discovery, execution, and status/authentication. Each tool earns its place, and there is no redundant or thin filler.
The core lifecycle for using the service is covered: discover models, invoke a model, and verify connection/credits. Minor gaps exist around explicit login/token refresh and multi-turn conversation management, but these are not required for the stated one-shot completion purpose.