lamatok-mcp
MCP server for LamaTok TikTok data API — auto-generates 20+ tools from the live OpenAPI spec (users, videos, hashtags, music, comments). Local stdio via npx -y lamatok-mcp, requires only LAMATOK_KEY.
README
lamatok-mcp
MCP server for LamaTok — TikTok data API. Available on npm: lamatok-mcp.
Auto-generates MCP tools from the LamaTok OpenAPI spec at startup, so every non-deprecated GET endpoint is exposed without hand-written wrappers. Tools map 1:1 to REST endpoints (GET /v1/user/by/username → get_v1_user_by_username).
Get 100 Free API Requests
Sign up with this link and get 100 free LamaTok requests — no credit card required. Enough to wire up the MCP server, try a few prompts in Claude/Cursor/Codex, and evaluate the data quality before committing.
Quick start
- Get an API key at lamatok.com.
- Add the server to your AI assistant.
- Ask your assistant something like:
- "Get the TikTok profile for @nasa."
- "List the last 10 videos by user_id 6707206320333226502."
- "Find recent TikTok videos for the hashtag
photography."
Claude Code
claude mcp add lamatok -e LAMATOK_KEY=your-api-key -- npx -y lamatok-mcp
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"lamatok": {
"command": "npx",
"args": ["-y", "lamatok-mcp"],
"env": {
"LAMATOK_KEY": "your-api-key"
}
}
}
}
Cursor / Windsurf
Same shape as Claude Desktop — put the block under mcpServers in the app's MCP config file.
Zed
Add to ~/.config/zed/settings.json:
{
"context_servers": {
"lamatok": {
"command": "npx",
"args": ["-y", "lamatok-mcp"],
"env": {
"LAMATOK_KEY": "your-api-key"
}
}
}
}
OpenAI Codex
Append to ~/.codex/config.toml:
[mcp_servers.lamatok]
command = "npx"
args = ["-y", "lamatok-mcp"]
[mcp_servers.lamatok.env]
LAMATOK_KEY = "your-api-key"
Tools
Tools are generated at startup from the live LamaTok OpenAPI spec, so the list always matches the current API. ~19 tools across these groups (sizes as of this writing):
| Group | Tools | Examples |
|---|---|---|
v1/user |
9 | get_v1_user_by_username, get_v1_user_by_id, get_v1_user_medias |
v1/media |
8 | get_v1_media_info_by_id, get_v1_media_comments |
v1/hashtag |
2 | get_v1_hashtag_medias_recent |
Each tool name mirrors its endpoint (GET /v1/user/by/username → get_v1_user_by_username). Your assistant can call tools/list over MCP to get the full, up-to-date list with parameter schemas. /sys, Legacy, and System tag groups are excluded by default.
Configuration
| Variable | Description | Required |
|---|---|---|
LAMATOK_KEY |
Your LamaTok access key (sent as x-access-key header) |
yes |
LAMATOK_URL |
Base URL. Default: https://api.lamatok.com |
no |
LAMATOK_SPEC_URL |
OpenAPI spec URL. Default: ${LAMATOK_URL}/openapi.json |
no |
LAMATOK_TAGS |
Whitelist: only include operations with these tags (comma-separated) | no |
LAMATOK_EXCLUDE_TAGS |
Blacklist: additional tags to exclude (on top of Legacy, System, /sys) |
no |
LAMATOK_TIMEOUT_MS |
Per-request timeout for API calls. Default: 30000 |
no |
LAMATOK_SPEC_TIMEOUT_MS |
Timeout for the startup spec fetch. Default: 60000 |
no |
LAMATOK_MAX_RESPONSE_BYTES |
Max bytes read from each API response. Default: 10485760 (10 MB) |
no |
LAMATOK_MAX_SPEC_BYTES |
Max bytes read from the OpenAPI spec. Default: 8388608 (8 MB) |
no |
Legacy, System, and /sys tags are excluded by default. Deprecated operations are also skipped.
If LAMATOK_URL points to a host other than api.lamatok.com, the server prints a warning on startup — your key will be sent there, so only use it for a self-hosted or proxied LamaTok.
How it works
AI Assistant ←stdio→ lamatok-mcp ──https──> api.lamatok.com
│
└─ fetches /openapi.json once on startup,
builds one MCP tool per GET endpoint
Tool arguments map to the endpoint's query and path parameters. The response body is returned as-is (JSON text). Non-2xx responses are surfaced as tool errors with the HTTP status and body.
Development
git clone https://github.com/subzeroid/lamatok-mcp.git
cd lamatok-mcp
npm install
npm run build
LAMATOK_KEY=your-key node dist/index.js
Run in watch mode:
LAMATOK_KEY=your-key npm run dev
Run tests (unit + stdio smoke tests against a local mock server, no network/API key required):
npm test
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。