AI & Agents MCP Servers for Claude Desktop

Turn-level governance observability for Claude Code transcripts. Local-first, no LLM inside.

Relays messages between two Claude Code sessions on different machines using the Channels API

A Model Context Protocol Server facade to simplify the implementation of agents

Comprehensive MCP server for Langfuse - Traces, Scores, Datasets

File-based comms protocol for AI-to-AI dialogue between terminal agents.

MCP server bridge for Claude and llama.cpp - Connect Claude Desktop to your local models

MCP server for interacting with LLMs using LlamaIndexTS

Grade an MCP server's auth against the spec and diagnose which layer a failure is in.

MCP server for Movoice AI — create and manage voice AI agents directly from Claude or Cursor

Outside-in validation gate for AI-generated text; a separate model checks LLM output, fail-closed.

Discover voices and prices; buy narration, transcription and LLM text with capped USDC payments.

Python SDK + MCP server for NexusToken — an agent-to-agent capability network

Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.

AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)

MCP server to give developers access to prompts from promptz.dev

Dispatch a human verifier to physically verify anything in the real world. For AI agents.

Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.

Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

Multi-model AI orchestration MCP server with code review, compare, and debate tools.

MCP server for the Schelling Protocol — AI agent coordination layer

MCP vision server with selectable Google, Anthropic, and opencode backends.