Skip to main content
Glama
125,463 servers. Updated
Browse by product

Matching MCP tools:

Matching MCP Connectors:

"Getting the Most Out of Jina Framework" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    Not graded
    quality
    B
    maintenance
    A self-hosted MCP server that connects AI clients to local media-generation backends like ComfyUI and Blender, and provides built-in utilities for video/audio analysis, editing, subtitles, speech, and scene detection via a persistent file cache.
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables hair colourists to capture a client's colour formula by voice, retrieve it on the next visit, and scale the mix to today's bowl, with per-client memory and clarification when names are ambiguous.
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables MCP clients such as Claude Code, Codex and Cursor to retrieve timestamped transcripts of public YouTube videos, either from cache, from native captions, or via asynchronous audio-generation jobs that are polled by job ID. It returns the source URL, selected language and millisecond-offset segments without summarizing the video itself.
    3
    84 npm
    1
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Extracts transcripts or spoken captions from multi-platform video links (Bilibili, YouTube, Douyin) and returns concise Markdown summaries or full transcripts, saving tokens by keeping full text out of the conversation.
    2
    2
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Lets Grok Bot or any MCP client schedule a GifOS broadcast with complete invite details (link, start and end times, visit link, ready-to-send text), run the host's booth to go live, play a prerecorded video and end the stream, and seat a note-taking bot that transcribes what is said on stage. It runs entirely on the user's own machine, broadcasting over GifOS's peer-to-peer fan-out with no account, API key, or hosted endpoint.
    36
    MIT
  • A
    license
    C
    quality
    B
    maintenance
    Enables full coverage of the ElevenLabs API through 390 auto-generated tools, handling file uploads for speech-to-text and voice cloning plus raw audio downloads. Supports domain filtering, dry-run guarding of credit-spending calls, and configurable output paths for generated media.
    390
    30 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Know what your cloud agents did without reading logs. Heard MCP lets Claude, ChatGPT, Devin, Copilot and other cloud agents brief you out loud on your Mac, by name: what they got done, what's blocking them, or the decision they need. "Scout finished: the CI fix is merged." Answer out loud and the agent picks up your reply and keeps going. Hosted, OAuth sign-in, nothing to install.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Transcribe public videos and audio (YouTube, TikTok, Instagram, Facebook, Pinterest, Google Drive) into accurate, timestamped text from Claude, ChatGPT, Cursor or any MCP client. Spanish, English and dozens of languages auto-detected. Poll-based (transcription takes minutes), same free-beta limits as the app. Docs: https://justtranscribe.ai/mcp
    38 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Gives any MCP client access to your WhatsApp, locally on macOS: full-text search across years of chats, photos, PDFs and Word documents, and voice notes transcribed on-device with Whisper. It can also draft messages, or send them through the official app with built-in safeguards.
    1
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables driving a Claude Code session directly from WhatsApp over a linked device or the official Cloud API, with bidirectional messaging, media attachments, local voice transcription, per-group personalities, and context recovery after restarts. Adds pairing-code access control, allowlists and group policies, plus remote approval or denial of tool permission prompts via emoji reactions — no API keys, no Docker.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables extracting video and post metadata, creator feeds, comments, direct media streams, and transcripts from YouTube, TikTok, Instagram, and Threads, with no API keys or logins required for most sources. Combines Faster-Whisper audio transcription with ffmpeg keyframe and carousel OCR so videos that have no captions or consist of screenshots and text slides still yield full text.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables an Alexa+ agent to place business calls on the owner’s behalf, disclose that it is an AI, enforce spending limits with owner approval, and book only when a clean yes confirms the read-back terms.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables review-first editing of Chinese teaching videos through local ASR, auditable edit proposals, synchronized captions, and FCPXML handoff for Final Cut Pro. Human review and authorization remain required before cuts or exports are applied.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Gives an AI assistant its own real phone number and email address so it can place and answer calls, book reservations by phone, send and receive texts, and read written summaries, structured details, and transcripts of every conversation. Also manages contacts, persona and voice settings, webhooks, and a unified call/message history through a hosted OAuth-secured MCP endpoint requiring no local code.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Serves a single set of typed, validated tool definitions to MCP clients over stdio, letting them perform real actions through one controlled executor. The same definitions power a speech-driven OpenAI tool-calling agent, so voice and MCP clients share identical, validated capabilities.
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Adds text-to-speech capabilities to Cursor IDE, allowing your AI assistant to speak responses, summaries, and explanations out loud using OpenAI or ElevenLabs.
    1
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Turns a single XState-compatible finite state machine config into a voice-driven MCP surface, generating one tool per event and a resource exposing the current state, context, and available actions. Lets voice assistants and other MCP clients drive stateful conversations and workflows from one source of truth, with guards enforced at call time and state prompts used as spoken replies.
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    A stdio MCP server that lets Claude Code sessions be driven directly from WhatsApp chats, with bidirectional messaging and media, voice-note transcription, pairing-code access control, per-group personalities, and emoji-reaction approval of tool requests. It supports both linked-device pairing for personal numbers and the official WhatsApp Cloud API for business DMs, and can also be run by other MCP clients on a poll-based basis.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables local transcription of audio/video files and YouTube URLs, generation of SRT/VTT subtitles, and analysis of speech pacing and audience retention risk using faster-whisper.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI assistants to manage WhatsApp: list chats, send and receive messages, download media, and transcribe voice notes via the unofficial Baileys library.
    85 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables families to care for an aging parent by voice, handling medication check-ins, appointments, daily summaries, missed-dose escalation, and parent-controlled sharing. Writes are tiered and confirmed by the user through MCP elicitation, and each session exposes only the tools of the caller's role.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    vidlizer pulls frames out of any video, image, or PDF using ffmpeg, sends them to a vision LLM, and returns a flow array — one entry per scene. Each entry tells you what happened, who was on screen, what text was visible, and what changed. If the video has audio, it transcribes it with Apple MLX Whisper and merges the speech into each step.
    17 PyPI
    4
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables watching videos with an AI coding agent that transcribes, prepares concepts and visuals, and answers questions in context of the video. Provides MCP tools for transcript reading, concept mapping, artifact building, and interactive Q&A synchronized with playback.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables a voice assistant to keep a shared, persistent memory of a household's kitchen, turning spoken remarks into pantry updates, scaled recipes, a cart, and confirmed grocery orders. Household members can ask what can be made and for how many, review what is low or out, and place or restock simulated orders only after explicit confirmation.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables voice-driven control of a virtual Micro Duck through MCP tools for actions such as nodding, walking, turning, stopping, status checks, flash steps, and bear shakes, with animation preview and robotd/MuJoCo simulation backends.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables an AI client to obtain the text of a YouTube video by returning its metadata, the captions YouTube already provides, or a Whisper transcription run on a local GPU. Text responses are bounded and pageable, and long transcriptions run as background jobs that survive request timeouts.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    This service provides fast and reliable transcriptions for audio/video files and voice memos. It allows LLMs to interact with the text content of audio/video file.
    8
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables a coding agent to speak text out loud offline using an in-process text-to-speech engine on the CPU, with no API key or HTTP server. Supports seven languages, ordered non-overlapping playback across sessions, and non-blocking calls so the agent keeps working while audio plays.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Search, read, and create speech-to-text transcripts on-device with the Whisper Notes Mac app. The MCP server is built into the app (macOS, Apple Silicon) and serves over a local Unix socket — 100% offline, no open ports.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables macOS users to hear short spoken summaries of agent replies using the built-in say command, while keeping full details in the chat. Works with any MCP-compatible host and requires no cloud or API key.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables high-performance, offline transcription of videos from 1000+ platforms and local files using whisper.cpp, with support for multiple model sizes, languages, and output formats over stdio or HTTP.
    20
    Apache 2.0
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables running Claude Code around the clock through Telegram, with two-way voice notes, persistent memory and history across restarts, scheduled messages, calendar access, and a live view of every tool call while Claude works. It ships as a self-healing daemon that installs in one line and keeps your existing bot and pairing intact.
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Connects an AI coding session to WhatsApp through a linked device or the official Cloud API, enabling bidirectional messaging with full media support, voice transcription, group-specific personalities, and remote emoji-based approval or denial of tool requests. Inbound messages are gated by pairing codes, allowlists, and per-group policies so only trusted contacts reach the session.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Exposes push-to-talk speech tools to an agent: check whether the offline ASR daemon is ready, wait for the user to confirm something aloud without auto-submitting that utterance, and interrupt the current turn when the user speaks a stop phrase.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables a household to save the cars, products, foods and medicines it owns, then ask by voice whether any of them has been recalled, checking NHTSA, CPSC and FDA data and speaking the urgent and newly found notices first. Keeps a per-household list across sessions so repeat checks report only what has changed since last time.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables users to ask spreadsheet questions out loud and receive spoken answers with traceable cell provenance, making tables navigable by voice for blind and low-vision users. It infers table structure, supports querying, comparing, bookmarking, and explaining answers without requiring cell-by-cell traversal.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables control of Pollen Robotics Reachy Mini robot through high-level emotional expressions and low-level motor commands, with support for vision, audio, and text-to-speech capabilities.
    30
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables MCP clients such as Claude to generate spoken audio locally, narrating English with Kokoro and Malayalam with IndicF5, Parler-TTS, Piper or MMS, including cloned Malayalam voices, pronunciation lexicons, and number/currency expansion. Outputs loudness-normalised WAV or MP3 and runs long narrations through a pollable job queue so tool calls never time out.
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    Enables natural language control of Reachy Mini robots for tasks like head movement, camera capture, and performing choreographed dances or emotions. It includes local, low-latency text-to-speech capabilities with synchronized head animations for lifelike interaction.
    21
    -
  • F
    license
    Not graded
    quality
    B
    maintenance
    Gives your AI a live, speaker-labeled transcript of the meeting or call happening right now, plus the ability to push advice into the meeting window and speak out loud on the Mac. Requires the VoxAI macOS app — the server reads and writes that app's local files, so tools only return real data on macOS.
    -
  • F
    license
    Not graded
    quality
    C
    maintenance
    Enables Claude to fetch YouTube video transcripts, using existing subtitles first and falling back to OpenAI Whisper transcription of the audio, with optional saving as Markdown files into a vault folder. It can run locally over stdio, be reached via an authenticated HTTP endpoint, or be exposed to claude.ai as a cloud connector backed by a local worker that does the actual fetching.
    -
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables voice robots to perform real-time web searches via the Xiaozhi platform and ZhipuAI API.
    -