"Vite" matching MCP servers:

Enables ChatGPT to consult Claude, Gemini, and Grok concurrently through their local CLIs, forwarding identical prompts and returning each provider's answer independently with persistent threads and targeted retries.

An MCP server that answers typed noul/choice/score questions about a given state with probability distributions and confidence, for routing, escalation, and gating decisions. It runs on pluggable backends (local Needle 3 or Laya models, or any OpenAI-compatible endpoint) and logs every decision so recorded ground truth can be used to track calibration.

Lets assistants send the same test prompts to as many as four text models across OpenRouter, Amazon Bedrock, Google Vertex AI and Microsoft Foundry, then automatically grade each answer with a judge model, rule checks and a policy gate. Returns scored leaderboards with letter grades, per-response strengths and weaknesses, latency, throughput and estimated cost, plus downloadable PDF and CSV reports.

Enables AI clients to generate Perchance images and manage user keys via a lightweight MCP server that fits in 512MB RAM by offloading browser-based Turnstile solving to an external solver service.

Multi-broker trading MCP server for Claude AI, unifying Kite, Groww, and Dhan with 40+ technical indicators, real-time trading, portfolio management, and Cloudflare Workers support.

A lightweight topological arbitration MCP server for multi-agent clusters, using Topological Data Analysis to resolve decision conflicts and enable consensus among agents.

RailRouter Lite is a real, production-ready MCP server implementing the Model Context Protocol. It exposes one tool: route_payment. This tool intelligently routes payments to the optimal rail (Stripe MPP, Coinbase x402, or Google AP2) in real time, choosing based on cost, latency, and success rate. Every decision is logged to a Cloudflare D1 database, creating compounding routing intelligence

Enables MCP clients to analyze images through DeepSeek's vision model using three input methods: local image files, external image URLs, and uploaded file IDs.

Enables a self-hosted AI workspace with persistent sessions, agent run/step execution logs, unified search across conversations and knowledge, and discovery/invocation of local and remote MCP tools.

An MCP server that enables Claude Code to concurrently consult Codex and Gemini as a 'military advisor', merging their perspectives to form a final solution.

Enables AI-assisted coding workflows to validate code changes through an adversarial debate between the coding agent and a critic LLM, surfacing only deadlocked decisions for human review.

MCP server providing tools to interact with Vibe Marketolog agent API for landing page audit, cost tracking, and account status, with call logging and caching.