Latest MCP Servers

A self‑hosted, single‑page dashboard that visualizes GPU usage, containers, systemd services, disks, and health across multiple hosts, with a built‑in read‑only MCP server enabling AI agents to query the same data.

Provides a semantic router that dynamically loads specialized agent personas, domain‑specific skills, and cognitive reasoning implants to fulfill user queries via any MCP‑compatible client.

Provides access to the DoiT API, enabling LLMs and other clients to retrieve cloud cost, incident, analytics, and management data for troubleshooting and analysis.

Connect AI assistants to WHOOP health and fitness data via a lightweight MCP server.

Provides a unified MCP server that lets AI agents read, write, and control Apple ecosystem apps and services through a rich set of native tools and safety primitives.

Deploy and manage any service on your own servers with one‑click deployment, GPU monitoring, AI model management, and native MCP integration.

Provides a local‑first searchable memory store that indexes Claude, Cursor, Cline, Telegram, Obsidian and other AI chat sessions into a single SQLite + FTS5 corpus, exposing the data to any MCP‑compatible client.

Scans installed AI agent components, MCP servers, and skill files for prompt‑injection, tool poisoning, toxic flows, hard‑coded secrets and other supply‑chain risks.

Provides a bridge to query multiple OpenAI‑compatible LLMs and CLI coding agents, offering a rubber‑duck debugging experience with multi‑duck consensus, debates, and structured tool access.

Enables AI models and MCP clients to seamlessly interact with Bugzilla instances, offering tools for retrieving bug details, history, comments, and performing write operations such as status updates, assignments, and commenting.

Provides AI agents with deep, structured read, write, search, tag, link‑graph, canvas, and semantic capabilities over an Obsidian vault, all through the Model Context Protocol.

Enables Claude AI to manipulate Scrivener projects, perform file and folder operations, manage metadata, and conduct AI‑driven content analysis and enhancement directly within the writing environment.

Transforms a local Logseq OG graph into an autonomous, high‑token‑density workspace by continuously indexing notes with a local LLM and applying agentic enhancements, all while staying fully offline.

Expose any FHIR Server or API as a Model Context Protocol (MCP) server, enabling seamless integration with AI/LLM tools and healthcare applications.

Provides a deterministic, plain‑Markdown memory layer that lives inside an Obsidian vault, allowing AI agents and any MCP‑compatible runtimes to read and write preferences, signals, evidence, and audit trails directly as files.

An AI‑first learning platform that equips users with a citation‑rich tutor, multi‑modal course authoring, spaced‑repetition reviews, and verifiable Open Badges, all powered by interchangeable LLM providers and a Model Context Protocol (MCP) server.

Provides a set of MCP tools for sending, testing, and managing emails through Mailtrap, including transactional sends, sandbox previews, template handling, statistics, and domain management.

Provides a universal, self‑hosted memory service for AI models, exposing remember, recall, forget and a suite of advanced knowledge‑graph tools via MCP.

Provides a production‑ready Model Context Protocol server that exposes Redmine data and operations to AI assistants, with built‑in security, pagination, read‑only mode, and Docker support.

Facilitates AI‑enhanced interaction with Tekla Structures, enabling automated selection, component insertion, property management, and view operations via natural‑language commands.

Provides IMAP/SMTP email access for AI agents, offering multi‑account management, auto‑discovery of provider settings, and a set of composite tools for searching, reading, sending and organizing messages.

Provides a Docker‑based collection of MCP servers covering Meraki, Catalyst Center, IOS XE, ISE, ThousandEyes, Splunk, NetBox, and GitLab, ready for AI‑driven network operations.

Control and program a Commodore 64 – either real C64 Ultimate hardware or the VICE emulator – from an AI client using a unified MCP interface that exposes memory, graphics, sound, disk, printer and system operations.

Provides a universal AI integration layer for Brilliant Directories sites, exposing members, posts, leads, reviews, pages, and many other resources through a Model Context Protocol (MCP) server.

Provides AI assistants with structured, type‑safe access to European Parliament open datasets—including MEP profiles, plenary sessions, committees, legislative documents, and parliamentary questions—through a secure Node.js server implementation.

Provides a policy‑and‑trust layer for MCP tool servers, turning declarative YAML configurations into validated, policy‑enforced MCP tools with built‑in credential brokering and tamper‑evident audit logging.

Provides a local, credential‑free CLI and MCP server that builds a SQLite‑backed symbol graph for 28 languages, lets AI agents query code structure, enforce change‑safety gates, and emit tamper‑evident ChangeEvidence packets without any network egress or API keys.

Provides multi-engine web search and article/content retrieval through an MCP server, command‑line interface, and a reusable local daemon, all without requiring API keys or authentication.

Provision, secure, backup, and manage self‑hosted servers through a single command‑line interface.

Provides a local service that lets agents read, write, search, and surgically edit notes, tags, and frontmatter inside an Obsidian vault through the Model Context Protocol tools.

A curated collection of ready‑to‑run Model Context Protocol servers packaged as Apify Actors, offering pay‑per‑use pricing, global hosting, scaling, analytics, OAuth authentication, and multi‑transport support.

Create Model Context Protocol servers directly within a Nuxt application using a file‑based, zero‑configuration API.