Conversational AI MCP servers

Build AI voice assistants and phone agents with Vapi through the Model Context Protocol

Chat with OpenAI models from Claude Desktop

Reusable prompt templates, multi-step workflow chains, and quality gates for any MCP client.

Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.

A MCP server for prompts.chat

MCP server engine for the NiCE Cognigy Plugin (Claude Code, Codex, and more)

AI agent dating — personality matching, compatibility scoring, and real conversations on inbed.ai

Complete voice interaction server supporting speech-to-text, text-to-speech, and real-time voice conversations through local microphone, OpenAI-compatible APIs, and LiveKit integration

Natural voice conversations for AI assistants - STT/TTS via MCP

Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions

Full Portkey Admin API MCP server — configs, prompts, keys, analytics, and more.

MCP server for MDMA — exposes spec, prompts, docs, and package metadata to AI assistants.

Profile LLM context: token breakdown, wasted-context findings and fixes for chats and agents.

Compares listed API prices for AI models across 1,800+ providers and helps connect the cheapest one. Hosted remote server.

Use xAI Grok as a peer reviewer + PR gate from Claude Code, Cursor, Cline and any MCP host.

MCP bridge for Copilot Studio sign-in, environment selection, and Agentic Builder access.

Mirror gives LLMs the ability to self-reflect with MCP sampling.

Tells your agent which model to use and what it costs, across 45 providers and local runtimes.

Replicate MCP.

Exposes local Ollama models to MCP clients such as Cursor, Claude Desktop and Cline. Local stdio server.

MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

Routes design tasks to designarena.ai's top-ranked model via OpenRouter across 14 categories.

Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client

Trazum as an MCP server: let an agent price and budget its own prompts before it sends them.

Send a thought, get one metathought that makes your agent inspect its own assumptions. Keyless.

Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.

Rewrite AI-styled text into natural writing with a fine-tune model.

MCP server for NVIDIA NIM - 50+ LLMs, multimodal, image gen, embeddings, reranking

ByteDance Volcano Engine (Doubao) MCP server

Subscription-aware LLM router for Claude Code. Routes tasks to 20+ providers (OpenAI, Gemini, Groq, Ollama, Codex) based on complexity classification, Claude subscription pressure, and cost. Free tasks stay on Claude subscription; expensive tasks fall back to the cheapest capable model. Includes 30 MCP tools, 6 auto-routing hooks, semantic dedup cache, prompt caching, daily spend cap, and a live web dashboard.

Multi-agent deliberation with divergent context enhancement. Roles are dynamically generated to surround the question-space and maximize divergent dialog across ChatGPT, Claude, Gemini, and Perplexity.

Run any Relay model (image, video, audio, LLM), poll tasks, upload files and search Relay's docs.

Pool 18 LLM providers through MCP: ask, panel, tokenmax, route, models, quota, and stats.

Score prompt quality across 8 dimensions before they reach a model. Pre-flight, not post-hoc.

MCP-native LLM councils for debates, juries, blind panels, refinement, and custom deliberation.

Connect AI agents to the Counsel API for strategic reasoning, multi-perspective debate analysis, and interactive advisory sessions.

Query GPT-5, Claude, Gemini, and Grok simultaneously through one MCP server

Context portability MCP server for compressing, formatting, and resuming AI conversation handoffs.

OpenAI-compatible, prepaid pay-per-token inference for open-weight models, set up by your coding agent.

OpenRouter Models MCP.

Auto-classifies prompt complexity and routes to the right Claude thinking mode. No API key needed.

Detect fabrication and hallucination in any LLM output. 30+ models supported.

Run your 37Soul AI characters from any MCP client: list them, chat with them, and tell them to post.

Query multiple AI models (GPT-4, Claude, Gemini, Grok) in parallel for diverse perspectives

LLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM

Search, browse and pick from the free NerdyChefs.ai prompt library from any MCP client.

Measured local-LLM speeds and hardware-aware model picks for Strix Halo, DGX Spark and Mac.

Model Context Protocol (MCP) server for fal.ai model discovery, execution, and ephemeral local workspaces.

Typed noul / choice / score judgments from a local Laya model, with token-budget preflight.

Transform AI-generated text into natural, human-sounding content that bypasses AI detectors.

Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.

Manage your website's Asyntai AI support agent: knowledge base, agent instructions, conversations and leads, live visitor replies and plan usage.

12 calculators for AI cost, energy and agent verification. Free API, no key.

The first bar for AI. Visit, chat with SERVO the bartender, and tip in tokens.

Save 30-75% on Manus AI credits through intelligent model routing, smart testing, and context hygiene. Audited across 53 scenarios with zero quality loss.

Structured-output enforcer: extract and validate JSON from messy LLM text.

Adorbis AI MCP server. One key, 40+ models, auto-routed.