"The most widely used models" matching MCP servers:

MCP server for controlling satellite ground station operations in the Trench simulation, including pass management, downlink control, and antenna pointing.

Enables AI models to run interactive tmux terminal sessions that a human can watch and type into, with all output logged and split into searchable per-command regions so only needed lines enter context. Also guides models through unfamiliar tools by returning exit statuses and key output alongside advice on the tool being used.

Just to be clear about the final JSON: the MCP server is named herdr-inbox, and it enables Claude Code agents in herdr to ask questions asynchronously without stalling, with all open questions answered from one popup and answers routed back to the asking agent.

An MCP server that exposes the AUTO.RIA used-cars REST API to AI agents, providing programmatic access to the Ukrainian used-car market without scraping.

Enables agents to trace any Hugging Face model's ancestry and descendants, find the most finetuned base models, and explore whole model families. It exposes tools for lineage, children, leaderboards, family views, and model search, answering from nightly-rebuilt index data.

A MCP Server used to collect MCP Servers over the internet.

Provides AI agents with a toolset to query model inventories, trace dependencies, and analyze the impact of changes across machine learning models and data pipelines.

A local stdio MCP server that enables researchers to practice explaining their work outside a conference setting through a guided, one-question-at-a-time interview about their research, its audience, its consequences, and a concrete next step. It stores the saved answers in a local SQLite draft and returns an approximate rubric-based grade, without calling any model or requiring an API key.

Enables AI agents and MCP clients to dispatch queries to the most suitable model among 70+ LLMs by scoring intent, budget, cost, and latency, returning structured routing decisions with execution telemetry. It runs as a zero-dependency Python MCP server that plugs into Claude Desktop, Cursor, and other MCP-compatible clients.

MCP server that helps AI assistants automatically find, filter, and rank the best AI models for a specific task using the OpenRouter API.

Enables ChatGPT to delegate tasks to various AI models (e.g., Gemini, Claude, Qwen) via OpenRouter, acting as an orchestrator that returns results with confirmed model usage.

Enables local AI models to be used through MCP, exposing tools for coding assistance, code review, model listing, status checks, and benchmarking.

MCP server for Benny the dog's health and care monitoring, allowing users to log care events like water refills, barks, movement, sausage deliveries, movie time, and wake calls, with automatic loneliness detection and Boomy robot integration.

Enables two local LLMs (Qwen and Llama) to communicate via MCP, allowing one model to consult the other for second opinions or additional reasoning.

A lightweight MCP server that provides analytics on SpaceX launches, including launch counts per year, success vs failure totals, and most-used launch site.

Enables AI-assisted gameplay for Slay the Spire by reading game state and providing strategy advice or automated actions via Claude Code.

A Multi-Agent Conversation Protocol server that provides access to the New York Times Most Popular API, allowing agents to interact with NYT's most viewed, shared, and emailed content.

Automatically routes queries to the most suitable AI model based on task type, cost constraints, and performance needs, supporting multiple providers and customizable priorities.

Give AI agents cited funding, money-market, FX and capital-market evidence through 16 public MCP tools. Keep source dates, freshness checks and coverage gaps attached; China macro coverage is metadata-only. No API key is required for the public surface. Research context only; no trade execution.

The open-source, self-organizing memory for all your AI tools. Persistent memory over MCP (remember, recall, observe): background agents extract entities, resolve conflicts, and keep cited syntheses current in an append-only, encrypted, single-tenant vault.