Skip to main content
Glama
125,439 servers. Updated
Browse by product

Matching MCP tools:

Matching MCP Connectors:

"web sear" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables ChatGPT on the web to generate and play spoken audio through an embedded player, exposing a speak tool that renders text with selectable styles and scenes via configurable text-to-speech providers. It routes each request across ElevenLabs, Cartesia, Azure Speech, and DashScope in a configured failover order, picking providers by language and scenario.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI assistants to listen to audio files on the local machine by transcribing speech offline with Whisper, analyzing music and sound (tempo, pitch, melody, key, loudness), and rendering spectrogram images that vision-capable models can inspect.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to submit Instagram, TikTok, YouTube, Pinterest, X, Facebook, or other web links and receive captions, timestamped voiceover transcripts, and on-screen text extracted from the video.
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    A FastMCP server that exposes a locally-hosted llama.cpp LLM as MCP tools, plus utilities for weather, news, web fetching, file I/O, and more. Enables MCP-compatible clients to use a local GGUF model for text generation without external APIs.
    1
    -
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables voice robots to perform real-time web searches via the Xiaozhi platform and ZhipuAI API.
    -
  • F
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents and applications to send audio notifications with text-to-speech, message streaming, agent-to-agent conversations, and web push notifications through a persistent message store and MCP integration.
    1
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    Votars is the world's smartest multilingual meeting assistant, designed for voice recording, transcription, and advanced AI processing. It features real-time translation, intelligent error correction, AI summarization, smart content generation, and AI discussions. The Votars app is available on Web,
    28
    -
  • A
    license
    A
    quality
    B
    maintenance
    Exposes DeepSeek's standalone web search, page fetch, OCR, speech-to-text, and text-to-speech APIs as MCP tools so any MCP client can call them directly without a model round-trip. Returns numbered search results, Markdown page content with offset paging, per-page OCR text, transcripts, and audio files written to disk.
    5
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Wraps a set of cloud OpenAPI capabilities — text-to-image generation, streaming speech synthesis, audio file transcription with timestamps and speaker labels, object-storage upload with presigned download URLs, and web/image search — as standardized MCP tools. This lets MCP-capable AI clients such as Claude Code, Cursor, and Cline invoke these services directly through natural language, with per-tool credential configuration.
    5
    97 npm
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI agents to search what was said in local video and audio files and indexed web videos, returning matching files, exact timestamps, passages, and links, with everything processed offline on the user's machine.
    4
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables a clinician's spoken visit to be captured and turned into a grounded, dose-free care plan that families can query through Alexa+, using extractive quotations, safety gates, and 12 tools over Streamable HTTP.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables a voice-first study mentor that remembers each learner across sessions, teaching at their level, running spoken quizzes graded on what was actually said, and building exam-aware study plans and morning briefings with overnight preparation. It also supports read-only Google Classroom sync, web research with sources, invite-only quiz battles between homes, and parent-visible safeguards for younger students.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Lets an AI agent put the image, sketch, or 3D model it is working on onto an iPad web canvas, where you circle, mark, and annotate it with an Apple Pencil, add voice notes, and send your marks, words, and exact pointed-at location back to the agent. This closes a visual feedback loop so agents can iterate on visuals without you having to describe them in text.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to read videos from YouTube links, web pages, media URLs, or local files by returning timestamped transcripts, labelled frame contact sheets, and lossless audio or spectrograms. Also searches YouTube, channels, pages, and folders to find videos worth reading.
    MIT