Latest MCP Servers

Open-source antivirus for AI agents that blocks risky tools, secret exposure, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

A bridge that wraps Claude Code, Gemini, and Codex CLIs and exposes them as MCP tools, enabling any MCP‑compatible client to delegate work, request second opinions, or run independent reviews without custom glue for each CLI.

OpenAI‑ and Anthropic‑compatible LLM inference server built on Apple's MLX, optimized for Apple Silicon and reliable tool calling in coding agents.

Provides a unified API to orchestrate and provision compute capacity across AWS, Azure, Google Cloud, Kubernetes, and custom back‑ends, accessible through a CLI, REST interface, MCP server, and native SDKs for six programming languages.

Provides a unified command‑line interface to scan, protect, and manage AI agents and MCP servers for credential leaks, shadow AI, unsigned configurations, and ungoverned agents, then automatically routes each finding to the appropriate remediation tool.

Provides durable, hybrid retrieval memory for AI agents, supporting dense vector, SPLADE sparse, and Neo4j graph contexts, with workspace and agent scoping, all deployable via Docker Compose.

Exposes Nextcloud files, calendar, notes, Deck, contacts, Tables, Talk, and mail as read‑only tools for AI assistants, enforcing user permissions and never modifying or deleting data.

Provides persistent project context for xAI Grok via a URL‑based MCP server that serves the IANA‑registered .faf format with zero configuration.

Provides always‑current official Claude documentation inside Claude Code through a lightweight metadata‑only plugin. The repository stores only a 3 MB manifest and a prose‑free search index; every page is fetched on‑demand directly from Anthropic’s servers, ensuring fresh content without redistributing any documentation text.

Enables AI assistants to read Brightspace course information—grades, due dates, assignments, announcements, rosters, syllabus, and other content—through the Model Context Protocol, while never modifying any data.

A practical, copy‑paste‑ready guide for using Claude Code, covering installation, prompt engineering, slash commands, skills, hooks, subagents, MCP integration, and agent‑team workflows for developers ranging from beginners to power users.

Provides bounded, read‑only access to HEC‑RAS project and plan metadata through the public RAS Commander Python API, enabling LLMs such as Claude Desktop or Claude Code to query project information without needing the HEC‑RAS executable.

Provides web_search and web_fetch capabilities via an MCP server, enabling AI assistants to query the internet and retrieve page content, with optional Google Gemini search and proxy support.

Generate, edit, render, and analyze music programmatically using text‑based commands, enabling AI agents to compose and perform tracks live.

Enables AI assistants to query the Smithsonian Institution’s Open Access collections, retrieving object and archive records, exhibition details, and media links through simple tool calls.

Open-source manufacturing ERP, MES and QMS platform that unifies quoting, material requirements planning, inventory, shop‑floor execution, quality management and lot/serial traceability in a single Postgres schema with a REST API and built‑in MCP server. Deploy on Carbon Cloud or self‑host on any VPS/AWS environment.

Enables AI‑driven development across desktop, VS Code, and CLI by indexing codebases, persisting hybrid memory, and orchestrating specialized agents to automate coding, testing, and deployment tasks.

Enables clients to interact with InfluxDB 3 via MCP, providing tools for querying, schema discovery, data ingestion, and administrative operations across Core, Enterprise, Cloud Serverless, Cloud Dedicated, and Clustered deployments.

A server that hosts a collection of Zoo-built utilities, exposing them through the Model Context Protocol for easy integration with clients, IDEs, and automation tools.

Provides a suite of MCP servers that expose the baramundi Management Suite REST API to AI assistants, enabling automated management of endpoints, jobs, software, compliance and other resources.

Manages SSH, RDP, VNC, and web sessions across macOS, Windows, and Linux with an encrypted credential vault and a built‑in MCP server that AI agents can drive through tool calls.

Provides adaptive memory for AI agents and teams, combining hybrid semantic‑keyword search with a self‑learning neural memory graph that improves automatically as searches are performed.

Provides a local MCP server that loads specialized agent personas, domain skills, shared rules, and cognitive reasoning implants, enabling clients to connect through stdio processes or a shared macOS HTTP service.

Convert PDFs, Word, PowerPoint, HTML, email and over 40 other formats into clean, LLM‑ready Markdown and back, with a Python API and powerful CLI.

Provides a self‑hosted Python MCP server that enables compatible AI chatbots to act as powerful agents on the host machine, executing commands, manipulating files, running tests, managing Git, Docker, browsers, databases, and more, with secure token‑based access via Tailscale or direct localhost URLs.

Provides transcripts, chapters, metadata, subtitles and single video frames from YouTube and ten other video platforms to AI assistants via a Model Context Protocol (MCP) server.

Curates plugins, skills, MCP servers, patch/profile layers, orchestrators, and UIs for DeepSeek Harness, enabling visualization, PPT generation, coding, agents, and auto-research loops.

Provides reference implementations of Model Context Protocol servers that enable standardized, language‑agnostic interactions with Oracle cloud services and products.

Provides a deterministic repository scanner that produces structured evidence for code intelligence, enabling static analysis, secret detection, dependency‑vulnerability checks, API endpoint mapping, and integration with MCP servers, dashboards, and GitHub Actions.

Provides open‑source, accountant‑reviewed tax guides that AI models can cite when answering tax‑related queries, ensuring answers are backed by current jurisdictional rules and credited experts.