"Recent three-day weather forecast for Beijing" matching MCP servers:

Enables AI agents to synthesize and play short summaries aloud while keeping full answers on screen, with queued speech and stop control using online natural voices or offline synthesis.

Enables AI clients to watch and hear videos from local files or YouTube, Vimeo, and Loom links by returning timestamped key frames, a transcript, a contact sheet, and a combined timeline, with all processing done locally.

Lets AI assistants understand what you're working on — current screen content, recent dictation, clipboard, and saved notes — running entirely on your own machine with nothing sent to the cloud.

Enables MCP clients such as Claude Code, Cursor, and VS Code to generate speech through three MiMo TTS models: nine built-in voices (with singing and style/audio tags), voices designed purely from a text description, and voices cloned from a local mp3/wav sample. Audio is streamed and written only inside a sandboxed output directory, with non-overwriting filenames.

Enables an AI assistant to have its recent code actions summarized aloud through system speakers, using offline native voices or cloud neural voices. It supports asynchronous playback and voice listing so users can hear what the agent did without reading the full response.

Analyze an hour-long YouTube video sentence by sentence in three minutes, and extract the information you need from the screen. Open-source local MCP server for AI clients.

Read-only MCP server for Telegram that enables reading messages and transcribing voice, audio, and video notes via the Telegram API for use with Codex and Claude Code.

Exposes the program's push-to-talk transcript history to MCP clients such as Claude Desktop and Claude Code, letting them fetch recent or latest transcripts, query results by time window, range, or ISO timestamp, search text, look up records by id, and read counts, runtime status, or clear history. Each result carries millisecond-precision hold start/end timestamps alongside the transcribed text.

Enables spoken questions about disease outbreaks reported to India's IDSP, returning short read-aloud answers on what's circulating, where diseases hit hardest, seasonal peaks, and trends across 16 diseases and 764 districts. It also tells users when data is too sparse to forecast instead of guessing.

Enables an assistant to turn noisy speech into three confirmable action candidates, then execute only the user-selected candidate after a one-time nonce is verified through a paired device. It also records consent receipts and supports Alexa+ account linking and card-based interaction.

Enables Arabic- and English-speaking newcomers to a US city to find halal and Middle Eastern food, mosques, groceries and clinics, get daily prayer times, learn the exact English for everyday situations, and generate a seven-day settling-in plan, all by voice. Every result returns structured content plus a ready-to-read speech string in the user's language.

Self-hosted WhatsApp management over Model Context Protocol, exposing a streamable HTTP MCP endpoint with 30 tools for session/QR pairing, messaging, media storage, and optional on-CPU voice note transcription via whisper.cpp.

Enables AI agents to place approved outbound calls to Indian (+91) phone numbers, deliver a message, and ask up to 8 questions in Hindi, English, or other Indian languages, then return a summary, per-question answers, transcript, and recording link. Also lets agents check remaining minutes and review recent call history.

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.

Enables voice-driven monitoring of a home honeypot network through Alexa+, including status checks, recent activity summaries, evidence-chain verification, incident report generation, and device naming. It also surfaces high-severity alerts and maps attacks to MITRE ATT&CK.

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.

Feedback ingestion for AI agents. Record your screen and talk; your agent does the rest — files the bugs, writes the spec, builds the backlog.

Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, using free self-hosted pieces (pjsua2 + whisper.cpp + Linphone). No paid telephony, no extra API key.

Enables spoken conversations with Claude on a Mac: Claude speaks through speakers, listens to the user's natural replies, and transcribes them locally. No audio leaves the computer, and it includes tools for voice setup and a hands-free voice mode.

Enables AI video dubbing by letting users submit video URLs for dubbing into Russian, English, or Spanish while preserving original speakers' voices through voice cloning, plus job status and cost estimation tools.