目录 / Linkedmash
MCP
需 API Key
未评级
已上架
Linkedmash
Enable AI assistants to manage LinkedIn bookmarks with advanced filtering, searching, and pagination capabilities. Access bookmark counts and details filtered by read status, media type, author, tags, and date ranges. Seamlessly integrate Linkedmash bookmark management into your AI workflows using this MCP service.
该来源不提供完整文件导出(国内平台多为平台内托管),仅存元数据与原链
接入信息
- 传输形态
- http
- 鉴权方式
- 需 API Key(需要配置:LINKEDMASH_API_KEY)
- 端点
https://linkedmash.run.tools
该服务需要凭证,请按官方文档申请后替换占位符
{
"mcpServers": {
"Linkedmash": {
"headers": {
"Authorization": "Bearer \u003cYOUR_KEY\u003e"
},
"url": "https://linkedmash.run.tools"
}
}
}
能力清单
| 工具 | 说明 |
|---|---|
| list_bookmarks | List bookmarks with optional filtering and pagination. IMPORTANT: Use this tool (with the 'author' parameter) when the user asks to show posts by a specific author, find posts from someone, or filter by author name. The 'author' parameter supports fuzzy matching of author names. |
| search_bookmarks | Search through a user's LinkedIn bookmarks using either keyword (text) search or semantic (meaning-based) search. Supports all list_bookmarks filters, full-text search via the q field, and semantic search via the vector_search_term field for natural language or topic-based queries. IMPORTANT: At least one of 'q', 'vector_search_term', or 'author' must be provided. If the user asks to find posts by a specific author (e.g., 'Show posts by John Doe', 'Find posts from Suresh sambantham'), use the 'author' parameter instead of putting the author name in the 'q' field. Use 'q' for searching post content, not for filtering by author. |
| get_bookmark_count | Get the total count of bookmarks with optional filtering |
| list_labels | List all user's labels/tags |
| add_labels | Add labels to bookmarked posts. Either label_id or label_name must be provided. |
| remove_labels | Remove labels from bookmarked posts. Either label_id or label_name must be provided. |
| setup_vector_store | Initialize the vector store for semantic search. CRITICAL: When vector/semantic search fails with 'Vector Store Not Setup' error and you offered the user options to either initialize or use keyword search, and the user responds with 'first', 'option 1', 'yes', 'initialize', 'set it up', 'init', 'setup', 'go ahead' or similar confirmation, you MUST immediately call this tool. ALWAYS check your previous message in the chat history to confirm the user is responding to your options. Do NOT re-run the search tool - just call this tool. After calling this tool, inform the user that setup has started and may take a few minutes. This is an async operation that may take a few minutes to complete for large bookmark collections. |
纠错与举报(发现条目失效、署名有误或涉及侵权?)
提交举报 / 纠错
侵权举报经核验成立后,我们会即时下线该条目并删除已存的内容副本。