"The most widely used models" matching MCP servers:

This MCP server searches Google's public ads database and uses AI to analyze ad images/videos, with intelligent caching for performance.

Enables searching, comparing, and inspecting AI models by pricing, context window, and capabilities via the models.dev catalog.

Enables searching and analyzing Facebook's public ads library for any brand, including ad images, text, and video analysis.

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.

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

A persistent memory system for Large Language Models (LLMs) that enables continuous learning and knowledge retention across sessions through the Model Context Protocol (MCP).

Enables AI agents to fetch and pack the most relevant files from any GitHub repository for a given query, within token limits. Works with Claude Desktop, Cursor, Windsurf, and VS Code Copilot.

Enables AI agents and MCP clients to estimate VRAM footprint and tensor parallelization requirements for quantized llama.cpp models, returning structured outputs without external dependencies.

Tarot card meanings for love, and answers to the most-asked love questions, in 22 languages.

Provides instant access to a searchable knowledge base of 16,000+ community-driven troubleshooting solutions for common coding problems. Includes community feedback and smart ranking to help AI assistants find the most effective solutions.

An MCP server that runs The Fortuneteller's Hand, a solo journaling tabletop RPG where Claude runs the table, casting Omens and reading the cards.

Provides local, deterministic scoring and detailed auditing of text for AI-writing patterns via two read-only tools, with no network calls or language models.

Furl folds repeated tool output into a hash-addressed marker, keeps the line that matters, and returns any original byte-exact the moment the agent asks for it. No summary. No guessing. Nothing thrown away.

Delegates coding tasks to your locally installed pi CLI, inheriting providers, models, and extensions, with persistent sessions and cancellable calls.

Securedact MCP is a local-first privacy layer for MCP-compatible AI workflows. It detects, reviews, redacts, and audits sensitive information before approved sanitized content is used downstream.

Per-unit cost of 13 back-office tasks done by a person vs by software, in the US, Greece and Ukraine, with an official statistic behind every hourly wage. Bundled data, works offline.

An MCP server that connects language models to a Wazuh SIEM cluster, enabling read-only plain-language queries, schema inspection, field coverage analysis, and decoder testing.

Read-only MCP server for GenieLocker that exposes tools for service status, commercial inventory, live quotes, recipe search, and credit pricing, without enabling purchases or model inference.

An implementation of the Model Context Protocol that provides AI models with standardized access to Kaltura's media management capabilities including uploading, retrieving metadata, searching, and managing categories and permissions.

MCP server for Python build123d to help AIs develop and reason about 3D models and CAD