Latest MCP Servers

Provides a native Svelte 5 data grid with a headless core and a ready‑to‑drop render component, offering row‑ and column‑virtualization, Excel‑style filtering, inline editing, grouping, pivot, and server‑side data handling.

Provides an open-source MCP server that makes an Obsidian vault searchable and writable from any AI client, supporting hybrid BM25‑vector search, provenance tracking, and auto‑link discovery.

Generate vertical podcast clips with AI‑driven face tracking, burned‑in captions, and a fully integrated content workflow that stays on‑device.

Provides a Windows‑first, local‑first bridge that lets AI coding agents safely invoke and orchestrate creative desktop applications such as ComfyUI, Blender, AutoCAD/DXF, Photoshop, Illustrator, and CapCut/Jianying through a standardized MCP stdio server and UXP/Node proxy layers.

Provides a one‑stop solution for Chinese and Western divination, generating comprehensive charts (八字, 紫微, 星盘, 六爻, 梅花, 奇门, 大/小六壬, 塔罗, 雷诺曼, 灵签, 择日) together with structured data and AI‑ready prompt text. Available through a web UI, public REST API, MCP server, and a reusable skill for AI agents.

A Python-native library that replicates Stata and R econometrics workflows, providing unified APIs, structured result objects, validation metadata, and MCP server integration for causal inference and applied statistics.

Provides a CLI, skill definition, and MCP server for automating Godot Engine tasks with structured JSON output, supporting both headless project manipulation and live runtime control.

Ingest Chinese content from platforms such as Douyin, Bilibili, Xiaohongshu, WeChat Official Accounts, X/Twitter, and podcasts, automatically transcribe videos, enrich with summaries, tags, and insights, and store the result as structured Markdown in an Obsidian vault with an MCP server for agent‑wide retrieval.

Orchestrates multiple AI agents locally to plan, implement, test, review, and iterate on code while enforcing TDD and integrating SonarQube, all without incurring per‑token API fees.

Provides 35 MCP tools for terminal control, screen reading, layout management, and orchestrating multiple AI agents such as Claude, Codex, Gemini, and Cursor within a cmux multiplexed environment.

Provides a local Model Context Protocol (MCP) server that enables AI clients to control real browsers via DrissionPage for web navigation, data extraction, form automation, and monitoring.

Enables AI clients to perform real‑time cybersecurity reconnaissance directly from a local server, automating WHOIS, DNS, port scanning, SSL inspection, header analysis, tech‑stack detection, CVE lookup and more.

Enables LLMs to interact directly with Couchbase clusters, offering a suite of tools for cluster health, schema discovery, KV document operations, query execution, and performance analysis.

Compose AI agents, RAG pipelines, and MCP servers in a single declarative YAML file and run them locally, in containers, or in production without writing custom code.

Parse, view, query, edit, and export IFC, IDS, BCF, pointclouds and other AEC data directly in the browser, on a server, or in a desktop app, using a Rust‑based WASM core and WebGPU rendering.

Provides MCP endpoints that expose DeepSeek chat and reasoner models, supporting multi‑turn sessions, function calling, streaming, cost tracking, thinking mode, JSON output, and optional multimodal input.

Debug and analyze JavaScript code running in real Chrome pages, with persistent login state, zero script injection and layered anti‑detection, enabling AI coding assistants to perform genuine reverse‑engineering workflows.

Provides AI agents with a discovery layer to locate, evaluate, and install MCP servers from the Official Registry, Glama, and Smithery, delivering trust signals and ready‑to‑use configuration snippets.

Provides AI‑callable tools for football, Formula 1, and cricket, enabling Monte Carlo World Cup bracket simulations, pit‑stop strategy recommendations, and constraint‑based Dream11 fantasy‑team optimisation.

Enables Claude Desktop to browse Hacker News, retrieve story details, and read comments through a set of MCP tools, presenting clean‑formatted content for better readability.

Provides a professional Python framework that standardizes MCP server development, automatically converting FastAPI endpoints into AI-callable tools while supporting interface‑implementation separation and flexible dependency injection.

Generate a customized AI agent harness for any repository, complete with a repo‑aware CLI, MCP server, scoped memory, governance policies, and out‑of‑the‑box support for Claude Code, OpenAI Codex, pi.dev, Hermes, OpenClaw, and RVM.

Enables AI-driven generation, editing, verification, and simulation of mechanical designs using build123d/OpenCASCADE geometry and CalculiX analysis, while preserving editable parameters, stable topology pointers, and full provenance in a reproducible .aieng package.

Provides a Model Context Protocol server that exposes a rich set of dbt‑related tools—SQL execution, semantic‑layer queries, discovery APIs, dbt CLI commands, admin operations, code generation, lineage analysis, and product documentation retrieval—so AI agents can safely interact with dbt projects and platforms.

Provides CLI-based fuzz testing for MCP servers, covering tool arguments, protocol request types, and various transports while offering safety controls and detailed reporting.

Explore the Rijksmuseum’s artwork collections through AI‑driven conversation, using enriched metadata for semantic and full‑text search, provenance analysis, similarity comparisons, and spatial reasoning.

Provides remote access to a self‑hosted ChromaDB instance via MCP, letting Claude and other AI assistants share the same vector memory across desktop, mobile, and code environments.

Provides a Model Context Protocol server that lets Claude AI drive Dassault Systèmes CATIA V5 through natural‑language commands, exposing more than 50 CAD operations via COM automation.

Provides a Model Context Protocol server that enables natural‑language interaction with WordPress sites, exposing content, taxonomy, media, users, comments, plugins, and read‑only database queries as programmable tools.

Enables AI agents to search, read, and extract content from large PDFs without overflowing their context windows, supporting keyword and semantic search, OCR, table and image extraction, and correct reading order for multi‑column and CJK layouts.

A unified, production‑ready multi‑agent platform offering a Python SDK, CLI, Studio server, and desktop application, supporting meta‑agent orchestration, over 15 LLM providers, hierarchical memory, avatar/group chat, skill ecosystem, safety sandbox, and IM gateway.

Provides a persistent Model Context Protocol server that enables AI agents to conduct autonomous penetration testing on Linux distributions such as Kali and Parrot OS.