Latest MCP Servers

Production‑grade TypeScript template for building Model Context Protocol servers with declarative tools, robust error handling, dependency injection, pluggable authentication, optional OpenTelemetry, and seamless support for both local execution and Cloudflare Workers edge runtimes.

Converts any MCP server into a Claude Skill, achieving up to 90% context savings while keeping tool functionality external to the model.

A comprehensive setup for Claude Code, Claude Desktop, and OpenAI Codex that provides ready‑to‑use commands, agents, hooks, and pre‑configured MCP servers to streamline daily development workflows.

Provides semantic vector search and progressive loading of Claude Agent Skills for any MCP‑compatible AI assistant.

Build, manage, and query relational graphs from CSV/Parquet, convert natural language to PQL, and obtain predictions, evaluations, and explanations from KumoRFM without any training.

Enables AI assistants to execute Apex code, run SOQL/SOSL queries, manage metadata, and automate development workflows within Salesforce orgs via the Salesforce CLI.

Provides an AI‑enhanced server that translates natural‑language queries into ServiceNow REST API calls, handling incidents, changes, requests, knowledge articles, private tasks, and CMDB configuration items with OAuth 2.0 security.

Enables CAP services to be exposed as Model Context Protocol servers, turning OData entities, actions, and functions into AI‑accessible resources, tools, and reusable prompt templates.

Provides a robust server that bundles Nmap, Go/Dirbuster, Nikto, John the Ripper and additional utilities to streamline professional penetration testing workflows.

Provides a Model Context Protocol server that equips agentic AI tools with UI5‑specific project scaffolding, API reference retrieval, guideline access, project metadata extraction, version info, and linting capabilities.

Provides real-time console access, visual debugging, design system extraction, and auditing for Figma files and plugins, supporting both cloud and local deployment.

Aggregates web data via Tavily's Search and Crawl APIs, structures the results for LLM-friendly markdown generation.

Install, manage, and develop Model Context Protocol (MCP) servers via a client‑agnostic command‑line interface.

Provides a unified, enterprise‑ready gateway and registry that centralizes AI development tools, enforces OAuth authentication, supports dynamic tool discovery, and applies fine‑grained access control for both autonomous agents and coding assistants.

Provides an MCP interface for AI assistants to manage OpenStack resources such as compute, images, identity, networking, and block storage.

Provides a streamlined foundation for building Model Context Protocol (MCP) servers in Python, facilitating AI‑assisted development of MCP tools.

Provides an MCP server that enables developers to connect to RedNote (XiaoHongShu) for creating, reading, updating, and deleting notes through a simple RESTful API.

Provides AI agents and chatbots with direct access to ModelScope’s ecosystem, enabling image generation, resource discovery, and contextual information via MCP.

Enables AI assistants to retrieve SonarQube code quality metrics, issues, security hotspots, and analysis results through the Model Context Protocol.

Provides an all-in-one sandbox environment that combines Browser, Shell, File operations, MCP services, and VSCode Server inside a single Docker container, enabling unified, secure execution for AI agents and developers.

Enables real-time interaction with Jupyter notebooks, allowing AI to edit, document, and execute code for data analysis, visualization, and multimodal output.

Provides a self‑hostable web interface that unifies discovery, configuration, and management of MCP servers while turning AI conversations into searchable, versioned organizational knowledge.

Provides an MCP server that integrates with FFmpeg to handle media processing tasks such as transcoding, format conversion, streaming, and other video/audio manipulations.

Provides a unified server that aggregates multiple Model Context Protocol (MCP) servers into a single endpoint, simplifying configuration, lowering resource consumption, and offering a standardized interaction layer for AI assistants.

Enables bidirectional integration of large language models with ROS‑enabled robots, allowing natural language commands and real‑time access to robot state, topics, services and parameters.

Transforms AI coding agents into structured development partners by applying battle‑tested engineering workflows, preserving project context across sessions, and automatically generating documentation and decision logs.

Provides a Model Context Protocol server that enables AI agents to query Langfuse trace data for enhanced debugging and observability.

Provides an MCP server that enables agents to create, manage, and execute end‑to‑end tests, search documentation, and handle environments through Octomind APIs.

Indexes local codebases into a Neo4j graph, providing AI assistants with rich context for code queries and analysis.