"Building voice agents and controlling SIP phones" matching MCP servers:

Agent Toolkit for Mercado Pago

An MCP server for AI voice synthesis with an inline audio player, allowing users to give their AI assistant a custom cloned voice using DashScope or ElevenLabs.

Enables Claude to generate, rewrite, de-AI, and transform text into a specific human voice, primarily the operator's own, using stylometric and AI-detector gates.

Provides real-time access to Japanese building standards laws and regulations from e-Gov API, helping prevent AI hallucinations by validating citations against original legal texts.

MCP server for Cursor that generates text responses via Yandex GPT and converts them to speech using Yandex SpeechKit TTS, enabling voice replies to user messages.

Enables AI assistants to delegate specific tasks to specialized sub-agents (e.g., test-writer, code-reviewer). Supports both Cursor and Claude Code with custom agent definitions.

Voice Mode for Claude Code

Enables orchestrating multiple specialist Claude Code agents as a team, with live visualization and agent-to-agent messaging.

Enables MCP clients to speak by running local voice models using Chatterbox Turbo TTS or Kokoro TTS, with support for voice cloning, paralinguistic tags, and multiple voices.

Enables AI assistants to synthesize speech with custom or cloned ElevenLabs voices and display an inline audio player with waveform visualization, transcript toggle, and dark mode support.

nexus-agents makes your AI coding tools work together intelligently. It coordinates Claude, Codex, Gemini, and OpenCode — routing each task to the best model using data-driven algorithms, validating outputs through multi-model consensus voting, and continuously improving through outcome-driven learning. Connect it to any MCP-compatible editor (Claude Code, Cursor, VS Code) and it handles the rest.

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.

Enables running AI agents via OpenAI-compatible APIs with custom system prompts, models, and queries. Supports persistent memory, preset agents, and multi-step workflows like pipelines and swarms.

The simplest way to bridge and collaborate across AI Agent sessions like Claude Code, Codex, Gemini, or Cursor. It allows your agents to combine their strengths to solve your most difficult tasks without leaving their current context.

Local voice toolkit over MCP: transcribe audio to text in 25 languages, synthesize speech in 9, and list available voices and languages. Runs fully on-device — no API keys, no cloud.

Enforces brand writing guidelines in Claude Code by analyzing Markdown files for violations and offering on-demand readability analysis and automated term fixes through MCP tools.

Enhances Claude Code's Task tool with session resumption and independent agent execution, allowing autonomous subagents from .claude/agents/ with true parallel batch support.

Enables AI assistants to speak with realistic cloned voices via ElevenLabs TTS on Cloudflare Workers, supporting 29 languages and inline audio playback on both desktop and mobile.

MCP server that provides a real-time project management board with cards, sprints, comments, and docs, enabling coding agents to query and edit project state.

Enables AI assistants to speak aloud by generating and playing audio through the system output. Supports multiple TTS providers, playback queue management, and configurable voice profiles.