dokpod

An AI knowledge vault that indexes UI screenshots, specs, and videos via MCP to stop token burn in Cursor and Claude

От сообществаРаботаетНужен API-ключГлобальныйБесплатноТолько чтение

Что умеет

List User Documents: List all documents in the user's Dokpod vault. Returns titles, tags, chunk counts, and status.
Semantic Search: Search the user's document vault semantically. Returns only the most relevant chunks (minimal tokens).
Find Documents By Name: Find vault files by exact or partial filename. Use when the user mentions a specific file name, PDF title, or screenshot name.

Нужен API-ключ из настроек сервиса

An AI knowledge vault that indexes UI screenshots, specs, and videos via MCP to stop token burn in Cursor and Claude

Список инструментов сервера (10)

Технические названия из tools/list. Нужны только разработчикам.

list_user_documents	List all documents in the user's Dokpod vault. Returns titles, tags, chunk counts, and status.
semantic_search	Search the user's document vault semantically. Returns only the most relevant chunks (minimal tokens).
find_documents_by_name	Find vault files by exact or partial filename. Use when the user mentions a specific file name, PDF title, or screenshot name.
get_chunk	Retrieve a specific chunk by document_id and chunk_id.
summarize_document	Get the summary and metadata for a document without loading all chunks.
compare_documents	Compare two documents using summaries and key chunk excerpts.
list_media	List images and videos in the user's vault with summaries and metadata.
semantic_search_media	Search images and videos semantically. Returns captions, frame descriptions, or transcript segments — minimal tokens.
get_media_description	Get full AI-generated description for an image or video (captions, frames, transcript).
get_relevant_frames	For a video, return only the frame descriptions most relevant to a query (low token usage).

dokpod: подключить к Claude, ChatGPT, Cursor · Connectors.fun