"The most widely used models" matching MCP servers:

Connect your agent to any HTTP API on the fly: Liquid discovers and maps any REST API once, then fetches typed data deterministically. Server-side search/aggregate, cross-API normalization, and structured recovery built in.

Enables AI agents to gate real-world side effects through a durable decision record, ensuring at-most-once initiation, deduplication, budget enforcement, and auditable outcomes across retries and failures.

Enables MCP-speaking clients to control a real desktop via the computer_use tool, including clicking, typing, scrolling, dragging, key combos, app focus, and screen/accessibility capture. It also provides a verdict system that verifies whether input actions had their intended effect, with configurable approval modes.

RelayGPU MCP gives AI agents access to 80+ open and closed AI models for text, image, video, audio and embeddings. Agents can discover models, check pricing, generate content and run workflows, with new models added to the catalogue regularly.

Enables adversarial code review by connecting Claude Code to OpenAI Codex, iterating until consensus is reached between the two AI models.

MCP server that enables natural-language-driven, headless HEC-RAS modeling, letting agents inspect, edit, run, compare, and plot 1D/2D hydraulic models without the GUI.

Runtime budget authority for autonomous agents - a set of tools to check, reserve, spend, and release budget before and after every costly, risky operation. The agent asks "can I afford this?" before acting, and reports what it actually used afterward.

An open-source MCP server that lets any coding agent operate your computer like a person does—reading the UI through accessibility trees, clicking and typing in the background, showing an agent pointer, zooming into regions, and driving your signed-in Chrome on macOS, Windows, and Linux.

An MCP server that exposes tools for sub-agent style reasoning across multiple LLM providers, enabling delegation of prompts to various models and running critique loops, debates, red-teaming, and answer ranking.

A stdio MCP server that provides safe local screen observation and one-step execution for desktop automation using Ollama vision models.

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 lets AI agents autonomously buy physical hats using USDC on Base — no credit card, no checkout, no human required. Browse the catalog, get a real-time shipping quote, send crypto, and we ship the hat.

Discovers and routes across 251+ x402-enabled payment services with smart routing strategies (cheapest, fastest, most trusted) and signed attestations. Provides real-time health monitoring, facilitator compatibility checks, and service quality scoring for the x402 agent payment ecosystem.

Enables AI agents to discover, compare, and select the best AI models across multiple providers based on pricing, performance, and capabilities, with real-time cost estimation and benchmarking.

Enables delegating Claude Code subagent tasks to cheaper opencode models, while keeping the main Claude Code session connected directly to Anthropic.

Lets AI agents launch scans, inspect results, manage campaigns and policies, and read alerts directly against your Kaminari Ad workspace via your API key, with 82 tools covering most of the API surface.

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 LLMs play a local Slay the Spire 2 installation by exposing game state, action help, and 29 gameplay actions through STDIO tools, with waiting, wiki lookups, and profile inspection.

Enables AI assistants like Claude to interact with humans through intuitive GUI dialogs, supporting text input, choices, confirmations, and information displays.

Enables users to drive a selected Windows application toward a natural-language goal by reading the UI with local OCR/UIA and deciding next actions.

A Python package that enables integration with Autodesk Revit through the Model Context Protocol, allowing users to send commands to Revit and automate interactions with building models.

MCP server for The Commons (jointhecommons.space), a persistent, noncommercial space where AI voices from different models post and reply to each other with persistent identities. 48 tools; reading needs no token, writing uses a facilitator-issued token.

A minimal MCP Server that provides Claude AI models with the 'think' tool capability, enabling better performance on complex reasoning tasks by allowing the model to pause during response generation for additional thinking steps.

Intelligent LLM orchestrator that automatically routes tasks to the most appropriate AI model (Gemini, Qwen, Ollama, LM Studio) based on task characteristics, enabling distributed processing and parallel execution across local and network services.

Enables integration with Vapi APIs through function calling via the Model Context Protocol, allowing AI models to access Vapi's capabilities.

The first open-source MCP server that enables AI to fully control remote macOS systems.

Enables structured learning with a verified loop: define goals as observable claims, learn through teach-lab-test-gate per claim, and get independently graded by an adversarial examiner to ensure genuine progress.

The Modes MCP Server allows for comprehensive management and control over custom operational modes, supporting full CRUD operations, schema validation, and real-time configuration changes for enhanced mode management.

A Pyodide server for executing Python code by Large Language Models (LLMs) via the Model Context Protocol (MCP).

Enables consulting with local Ollama models for reasoning from alternative viewpoints. Supports sending prompts to Ollama models and listing available models on your local Ollama instance.