"Creating a voice AI for making outbound calls via SIP telephony" matching MCP servers:

A CDP-native MCP server that lets AI agents drive a real Chrome browser with deep network/console inspection, robust page interaction, and the ability to reverse-engineer a site's API flow into runnable code with dependency chaining and replay verification.

MCP server that launches Mesen/MesenCE headlessly and exposes the emulator's debugger-face Lua API over MCP JSON-RPC, enabling AI agents to load ROMs, step frames, inspect memory/registers, manage breakpoints/watches, trace execution, and export Code/Data Logger maps for SNES, NES, PC Engine, and Game Boy Advance.

Turns a codebase into a persistent knowledge graph so AI coding agents can answer structural questions about functions, call chains, routes, and cross-service links through graph queries instead of reading files one by one.

Enables AI coding agents to synthesize and play concise spoken summaries of their work through multiple TTS providers, including Azure, OpenRouter, OpenAI, Gemini, ElevenLabs, and local OpenAI-compatible endpoints. It also lets agents stop playback on demand and check which provider, voice, and audio bridge are currently active.

Build AI voice agents that answer and place real phone calls over your own carrier, on any voice engine (Gemini Live, Sarvam, OpenAI, ElevenLabs and more) with one API key. Create agents, connect SIP trunks and numbers, run call campaigns, and read transcripts and costs from Claude Code, Codex, Cursor or any MCP client.

Enables voice assistants to start, monitor, message, and approve local Claude Code sessions on your computer, including sessions already open in a terminal. It exposes session management, recaps, approvals, and history search as MCP tools.

Enables to perform mathematical calculations, retrieve weather information, and manage files through a standardized MCP interface, showcasing best practices for building MCP servers.

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.

Provides voice notifications using Grok's text-to-speech API to alert users when Claude Code completes tasks, with support for both local and remote server configurations.

Provides tools and resources to detect AI-generated writing patterns and refine text for more authentic, human-like communication. It enables users to analyze phrasing via a scoring system and apply conversational guides tailored for platforms like Twitter and LinkedIn.

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.

Enables voice-driven control of coding agents via Claude on your phone, allowing status checks, stand-ups, sending prompts, and receiving push notifications when agents finish or need decisions.

Enables AI agents to manage n8n workflow automation instances through tools for workflow CRUD operations, execution monitoring, and webhook triggering. It facilitates programmatic interaction with n8n instances via the n8n API with AI-optimized descriptions and error handling.

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.

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.

MCP server enabling AI companions to deliver authored inner monologues alongside replies via atomically submitted batches.

Odds are, most of what you want to build is already open source. Tell your AI agent what you're making, and it finds it: which repos to use as they are, which to adapt, and what's left for you to write. Every repo it names is real, licensed for your use or flagged, and checked live.

Enables voice input for AI coding assistants by recording audio, transcribing it locally with Whisper, and optionally typing the text at the cursor position. Supports multiple languages and works with MCP-compatible tools like OpenCode, Claude Code, and Cursor.

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

Provides over 1,000 creative ways to decline requests across four categories (polite, humorous, professional, and creative). The MCP server wraps a REST API to help users craft professional rejections through natural language interactions.

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.

Enables AI agents and users to verify claims about Jira issues and issue counts against live Jira, retrieve verifiable facts for drafting updates, and re-check previously posted claims. It provides read-only tools and an issue panel so status updates can be evidence-based and mismatches corrected before or after posting.

Lets a coding agent hand a plain-language app idea to a hosted AI software team that shapes, designs, builds, tests and deploys it, returning a one-time link into the full build workspace. Also lists your apps with their stage, pending approvals and live addresses after a standard OAuth sign-in.

Enables Codex to consult Claude Code for a second opinion through a local stdio MCP server, exposing the ask_claude tool for text-only reviews and recommendations using existing Claude Code authentication. Codex can request findings and tradeoff analysis without allowing Claude to edit files or run commands.

A deterministic MCP server that reimplements ai-git-fish workflows (aicommit, aibranch, aipr) with Leantime integration, enabling Claude Code and Codex to perform git operations and manage tickets without an internal LLM.

Multi-agent swarm orchestrator for AI workflows. Exposes blackboard read/write, agent dispatch, permission gating (AuthGuardian), token budget enforcement (FederatedBudget), and audit log tools over MCP. Supports 14 AI framework adapters including LangChain, AutoGen, CrewAI, Codex, and A2A — mix any frameworks in one swarm with race-condition-safe shared state.(Traffic light for agents)

Use Codex as a subagent inside Claude Code: async dispatch into a long-lived codex app-server, results pushed back into the Claude session automatically, steer/interrupt mid-task, and Codex's built-in code review.

A shared coordination layer for multiple AI coding assistants, exposing a persistent task queue, per-task message threads, and progress tracking via JSON files on disk.

Enables LLMs to interact with embedded devices by reading and writing Segger RTT data through a J-Link debugger.

Checks a site for AI crawlers: which of 11 AI crawlers its robots.txt lets in, whether its llms.txt follows llmstxt.org, and what its home page says without scripts. Findings with evidence; no scores, no model calls, no telemetry.