Skip to main content
Glama
125,075 servers. Updated
Browse by product

Matching MCP tools:

Matching MCP Connectors:

"영상 (videos/images)" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    A
    quality
    B
    maintenance
    Persistent knowledge-base MCP server. Semantic search with source citations over saved YouTube videos, podcasts, articles and PDFs — one endpoint for every MCP-capable AI client.
    28
    Elastic 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    Self-hosted video intelligence pipeline that turns video into structured, citable, queryable JSON scene graphs, enabling AI assistants to analyze and search across video libraries without re-processing.
    12 npm
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Transforms YouTube videos into a persistent, structured knowledge base using transcripts and visual frame analysis, enabling knowledge compounding and natural language querying.
    166
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables an AI assistant to upload local images and videos to a memory service and later ask natural-language questions about everything stored. Runs locally over stdio and returns answers with their sources.
    63 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to build and manage local-first graph maps of .onion links and Markdown posts, including nodes, documents with images, connections, search, autolayout, and import/export through 32 tools.
    GPL 3.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables Claude to automatically extract entities and relationships from URLs, PDFs, and YouTube videos to build structured knowledge graphs in Neo4j. It supports custom schemas, academic citation extraction, and community detection for advanced research and content analysis.
    Apache 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides a visual memory and attention layer for AI agents, enabling indexing of images and videos and then searching, inspecting, tracking, and retrieving the right frame in milliseconds via MCP tools.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables Claude to search, organize, and revisit posts saved across multiple platforms from one local SQLite store over MCP, including full-text search, unseen-item digests, notes, tags, and saving public web pages or YouTube videos.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that gives AI assistants a local YouTube memory: transcribe videos, store and search transcripts, follow subscriptions, and generate summaries, timestamped highlights, and digests, all on your machine with no cloud or API keys.
    54 PyPI
    7
    MIT
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables transforming YouTube videos into a persistent, searchable knowledge base by extracting transcripts, analyzing scene-change frames with vision models, and compiling wiki pages that compound across videos. It also exposes these capabilities as an MCP server so clients like Claude, Copilot, and others can query the resulting knowledge through natural language.
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    A personal memory MCP server for Claude Code that stores and retrieves memories via natural language, supporting text, images, files, and secrets with vector search.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Turns YouTube videos into a persistent, searchable wiki knowledge base by extracting transcripts, scene-change frames described by a vision model, and LLM-compiled entities, topics, and concepts that merge across videos. Exposes keyword-narrowed wiki pages and a table of contents to MCP clients so their own models can reason over the accumulated knowledge.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables transforming YouTube videos into a persistent, structured knowledge base by extracting transcripts and scene-change frames, then reasoning over compiled wiki pages for agentic search through MCP clients.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables ingesting YouTube videos to build a persistent, cross-referenced wiki from transcripts and vision-analyzed frames, then supports agentic search and question answering through MCP clients like Claude and Copilot.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to ingest YouTube videos and query a persistent, compounding wiki built from transcripts and visual scene analysis, with agentic search over merged entities, topics, and concepts. It exposes this knowledge base as an MCP server so clients like Claude and Copilot can search and reason over the wiki.
    -
  • F
    license
    Not graded
    quality
    C
    maintenance
    Connects your Noverload saved content library to AI assistants, enabling search, access, and management of saved YouTube videos, articles, PDFs, and other content. Features advanced search modes, action item tracking, and goals management through natural language.
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    Builds a searchable knowledge base from YouTube video transcripts with hybrid semantic and keyword search. Allows LLM assistants to search, organize, and retrieve timestamped information from videos you've watched.
    3
    -
  • A
    license
    A
    quality
    B
    maintenance
    This MCP server enables AI agents to store memories with sensory fingerprints and automatically surface relevant recollections when incoming cues such as location, time, text, images, or audio align, alongside explicit recall and forgetting tools.
    4
    7
    40 PyPI
    Apache 2.0
  • A
    license
    A
    quality
    A
    maintenance
    Standalone MCP server for Obsidian vaults - hybrid search (FTS5 + vector + cross-encoder reranking), images and PDFs in agent-readable form, Kanban-aware tasks (Tasks-plugin + Dataview formats), structured memory with topic recall, fine-grained read/write tools for optimal token efficiency, and link graph support. Run locally, self-host, or one-click deploy for remote access. OAuth 2.1.
    16
    33
    38
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Your agent seeks what search can't find. A self-hosted perception MCP server that transcribes speech, reads behind logins, sees images and video frames, crosses languages, and remembers.
    18
    161 PyPI
    100
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Self-hosted memory for your AI, kept in your own git repo: Markdown and HTML it reads and writes, beside PDFs, office files, images and JSON it reads as they are. 30 tools to search, read, write and file notes. Every change is attributed to a person or an AI, an agent's work undoes in one step, any note reads as it was on any date. Flags contradictions. Runs over stdio or as a server with OAuth.
    31
    1,578 PyPI
    6
    AGPL 3.0
  • A
    license
    A
    quality
    B
    maintenance
    Search your X (Twitter) bookmarks and likes by meaning, including text inside images and full X Articles, from a local library built by the free SomedayX Mac app. Read-only and off by default.
    4
    1
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    A Model Context Protocol (MCP) server for interacting with TriliumNext via its ETAPI. Enables LLMs to create, read, update, and organize notes, including embedding images and files directly into note content.
    20
    71
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Global reptile & exotic pet knowledge base. 633 species, AI identification, genetics calculator, 12-dimension care, health diagnosis, pricing, provenance. Free 9 tools, 10 req/min.
    9
    2
    MIT
  • A
    license
    B
    quality
    C
    maintenance
    Enables AI agents to read Logseq notes, journals, tasks, pages and blocks—including embedded screenshots as viewable images—directly from the on-disk graph. It works read-only with Logseq closed and no network access, snapshotting the database so nothing can be modified.
    8
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI clients like Claude, ChatGPT, and Cursor to search, read, and write back to one cross-model Markdown library of saved articles, videos, PDFs, notes, and conversations. Hosted remote server with OAuth 2.1 or Agent-key auth and read_only, edit, or full permission tiers.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables users to pin lessons, claims, and open questions about physical objects to the places they live, then resume that thread later from any phone or assistant through three tools: observe, ask, and commit. Matching runs on host-authored text descriptions and user-named places, so no images are stored and identity survives switching devices, apps, or models.
    3
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables MCP clients to search, reopen, and inventory a local corpus of AI chat-history JSON files, including fetching stored message images and corpus freshness status, all without any network calls. It also lets clients save conversations and durable memories, with an optional read-only mode that blocks writes.
    70 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Imagine you could hand Claude a filing cabinet of your documents and say "remember all of this." Later you just ask questions, and Claude answers from what it remembers — citing which document each fact came from. That's Memorised them All. It's a small add-on (an MCP server) for Claude Desktop and Claude Code that: Reads your files — PDFs, Word/Excel/PowerPoint, web pages, images (with OCR), ev
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Connects an MCP client to your private Curatively vault so the agent can semantically search, read (images included), filter and list your saves, pull related items and reference packs, and save photos, links or notes with an editable note. Everything stays private and per-account, with read-only or read-and-save access and no ability to publish or delete.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables ingesting YouTube videos into a persistent wiki knowledge base by combining transcripts with scene-change frame analysis, then answering questions over the compiled pages via full-text search and agent reasoning. Serves raw candidate pages and a wiki table of contents to MCP clients so their own model can reason without requiring an API key.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables saving URLs, local files, plain text, and platform content (WeChat, X, YouTube, PDF, images, audio/video, Telegram) as structured Markdown knowledge cards in an Obsidian vault, with optional AI-powered classification and tagging.
    6
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables querying and retrieval of structured video summaries from a SQLite knowledge base through Claude or Cursor, supporting search, precise matching, and tag-based filtering.
    42
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Aggregates a person's watched videos, listened tracks, likes, bookmarks and follows across dozens of services into their own Cloudflare deployment, so an AI agent can search those records, compute long-term and recent taste profiles, find similar items, and keep notes backed by evidence. It is self-hosted, owner-only, and designed for personal assistants rather than coding tasks.
    AGPL 3.0
  • A
    license
    Not graded
    quality
    Not graded
    maintenance
    Enables any MCP-capable agent to write and maintain its own wiki of small linked markdown pages with a typed ontology, storing, indexing and retrieving them through keyword (BM25) search plus ontology-graph traversal, typed-relation management, page reads and writes, linting and listing. It also offers an optional vision tool that extracts objects and text from images so text-only models can learn from screenshots, charts and scans.
    MIT