BusyBee MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BUSYBEE_API_KEY | Yes | Your BusyBee API key (starts with sk-). Required for the local stdio server; hosted HTTP transports accept the same key via Authorization: Bearer, X-API-Key header, or ?api_key= query parameter. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_platformsA | 列出可用的平台、每个平台支持哪些操作，以及该怎么选。首次使用先调这个。 |
| search_creatorsA | 按关键词搜索社媒账号/达人。返回 id、handle、昵称、粉丝数、简介——拿到 handle 或 id 后再用 get_creator / list_creator_posts 深入。 |
| search_postsB | 搜索内容：给关键词，返回帖子/视频列表（统一字段：作者、文案、时间、点赞/评论/播放）。适合“某个话题最近在火什么”。 |
| get_creatorA | 查单个账号的详情（粉丝数、简介、作品数）。creator 填 handle（如 @nasa 去掉@）或平台 id。 |
| list_creator_postsC | 拉某个账号最近发布的作品列表。creator 填 handle 或平台 id。 |
| get_postA | 查单条内容的详情。post_id 填平台的内容 id；TikTok/抖音也可传视频链接里的数字 id。 |
| get_commentsA | 拉某条内容的评论列表（统一字段：评论人、内容、点赞、时间）。拿到评论后用 get_comment_insights 出结论。 |
| get_trendingB | 拉平台热搜/热榜（目前支持抖音）。适合做选题和热点追踪。 |
| get_comment_insightsA | 评论洞察：先拉样本评论再本地聚合，直接给结论——情绪分布、提问占比、高频词、高赞评论。比原始评论更适合回答“用户到底在说什么”。 |
| check_balanceA | 查当前 API Key 的账户信息与余额（美元）。调用前可以先看一眼，避免跑到一半余额不足。 |
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 10 tools
Each tool targets a distinct resource and action: creator search vs. creator detail, keyword post search vs. per-creator post listing, and raw comments vs. aggregated comment insights are clearly separated. The descriptions explicitly guide follow-up tool usage, leaving little ambiguity about which tool to select.
All tools use a consistent snake_case verb_noun pattern: list_platforms, search_creators, get_creator, search_posts, list_creator_posts, get_post, get_comments, get_trending, get_comment_insights, check_balance. Verbs are predictable and resource names are clear.
At 10 tools, the set is well-scoped for a social media analytics server. Each tool covers a meaningful part of the workflow: platform discovery, creator research, post search, comment analysis, trends, and account balance.
The read-only analytics surface is largely complete: discovery, search, detail retrieval, comment sampling and insights, trending topics, and balance checks are all present. Minor gaps exist around cross-entity aggregate insights, such as creator-level or post-level analytics analogous to get_comment_insights.