MCP tools connect models, data sources, and external capabilities around the Model Context Protocol, enabling different AI clients to reuse standardized tools. The page organizes servers, clients, directories, and development components, compares protocol compatibility, authentication, permission boundaries, deployment methods, maintenance status, and support for real workflows.
Inbox AI is an AI automation tool for Mac users that enables AI conversations, handling emails, capturing messages, and triggering custom workflows through voice or text. It can build voice assistants that perform actions such as drafting messages, remembering messages, discussing screen text, rephrasing content, replying to messages, searching web pages, opening apps, running shortcuts, using MCP tools, conditional branching, and voice transcription. The product supports 13+ AI providers, can bring their own API keys or use a native model, with a one-time purchase and 7-day trial model. It is suitable for connecting personal knowledge, email, and desktop actions into triggerable assistant flows, with manual confirmations still recommended for key actions.
FeedHive is an AI social media management and automation platform. The core positioning of the official website is to put content creation, publishing, automation, and analysis into the same social media workbench, and provide online processing capabilities around multi-platform publishing, AI content assistance, scheduling, social media automation, and account growth analysis. It's more suitable for creators, brands, and agencies who need to manage multiple social media channels, and before using it, you should check whether your account, material licensing, data source, language support, export format, and payment boundaries match your way of working. For scenarios involving portraits, voices, finance, law, medical care, recruitment, or public information, it is also necessary to retain the manual review link, and use the generated results as auxiliary judgments, rather than directly replacing professional opinions or formal conclusions.
Dify is a team-oriented agency workflow builder. The homepage of the official website clearly states that capabilities such as autonomous agents and RAG pipelines can be developed, deployed and managed, so it is not a single model call panel, but a more application-level AI orchestration and delivery platform. Judging from the information currently verifiable on the official website, the entrance, core capabilities and application boundaries of such products are relatively clear, and they are not just the landing page of conceptual packaging. When you really try it out, the most noteworthy thing is not the slogan itself, but whether it can smooth down a specific task, such as organizing recordings into minutes, turning text into pictures, turning lyrics into songs, connecting advertising processes, or turning internal knowledge into an assistant that can be asked and answered. Only by putting it into a real workflow will it be easier to determine whether it is worth using it for a long time.
Databar.ai is a platform designed around sales and GTM data enrichment. The homepage of the official website directly writes Enrich your CRM with 100+ Data Sources, and emphasizes AI agents, verified people and company data, personalized outbound flows and go-to-market data engine. The product positioning is very clear. It is not a simple data table tool, but is more inclined to supplement high-quality contact and company data for sales, growth and outreach processes, and is suitable for teams that need to do CRM enrichment and outbound on a scale. Judging from the information currently verifiable on the official website, its target tasks, applicable objects and product boundaries are relatively clear, and it is more suitable for people who already have clear usage scenarios to start directly, rather than treating it as a universal tool without boundaries.
Composio is a tool connection platform for AI agents and automated workflows. The homepage of the official website focuses on instant tool invocation, delegation authorization, sandbox environment and access to thousands of applications, indicating that its core is not to build a single model, but to solve how agents can safely, stably, and expansively invoke external tools. For people who do AI agents, automate processes, and multi-application collaboration, it is more like a layer of connected infrastructure. Compared with accepting applications and processing authorizations one by one, Composio emphasizes abstracting these repetitive tasks in a unified manner. Judging from the information that can be confirmed on the official website, its product boundaries and target tasks are relatively clear, making it more suitable for people who already have corresponding workflows or usage scenarios to start directly, rather than treating it as a universal tool that can do everything.
Claude Skills Hub is a third-party skills marketplace that collects and distributes Claude skills. The homepage of the official website clearly regards Claude's skills market, browsing discovery and download skills as core purposes, indicating that the focus of this product is not to make a general AI portal, but to gather the process around specific tasks. It solves the problems of Claude's skills being scattered, difficult to find, and difficult to compare, making it easier for users to discover the skill pack that suits them. For Claude heavy users, developers, efficiency players, and people who pay attention to the skill ecosystem, if they do encounter such problems repeatedly, Claude Skills Hub will be easier for them to fall directly into daily work than general-purpose tools.
Alai is an AI presentation maker, and its official website emphasizes the possibility of creating high-quality presentations with AI and generating slides from tools like Claude, Manus, and others through Alai MCP. The page mentions turn content into slides, AI has all the context, you have all the control, and entrances such as Pricing, Blog, API, etc., which are suitable for founders, product managers, consultants, students, and business teams to quickly organize ideas, documents, or existing content into editable presentations. Use it as a presentation structuring and visual first draft tool, focusing on facts, figures, interpage logic, brand templates, and audience scenarios; If you're connecting to an MCP or API, also verify the permissions and accuracy of incoming content from external AI tools.
Alma by OlivaresAI is a memory layer that provides persistent memory for AI, with official website descriptions that allow preferences, facts, decisions, and patterns to be preserved across conversations, and supports web apps, VSCode extensions, MCP servers, and REST APIs. It offers capabilities like context assembly, Soul Engine v2, environments, smart search, memory export, BYOK, Voice, and Image Studio for users who want their AI assistant to remember projects, styles, and work contexts for a long time.
aitrips.io is a map-first intelligent trip planning tool that allows you to put places on an interactive map, combine weather, traffic routes, collaborative editing, and mobile access to plan your trip, and support allowing users to save their own AI directly to the itinerary through MCP. It's suitable for travel planners, remote teams, families, and those looking to manage their routes with AI, bringing inspiration, places, dates, and routes together into a collaborative itinerary board. After the planning is completed, it is still necessary to check the opening hours, traffic changes, hotels and ticket information of attractions; Its advantage is that it brings together maps, weather, routes, collaboration, and MCP access to help itineraries be easier to adjust and save.
Agent Skills (agentskills.me) is an Agent Skills Skills Directory and Installation Navigation Station for AI Agents. It focuses on a reusable skill set based on the SKILL.md specification. Agent Skills supports the discovery and selection of skills for Claude Code, Cursor, OpenCode, Gemini CLI, Codex CLI and other platforms, and provides clear installation guidelines, such as copying SKILL.md to a specified skills folder or one-click installation through the command line. Through classified browsing, skill details pages and download entrances, Agent Skills helps developers manage skill packs more efficiently and expand agent capabilities. It is suitable for building pluggable workflow and automation capabilities stacks under the MCP ecosystem.
Skillstore is an AI skills market for Claude, Codex and Claude Code, focusing on the distribution of reusable skills with "security audit + one-click installation". Skillstore accumulates skills in the form of standardized packages through automated security scanning and versioning management, making it convenient for developers to quickly discover, install and share Agent Skills for code review, test generation, refactoring optimization, document writing and security inspection. High-frequency scenarios. Skillstore also supports submitting skills and triggering security audit and audit processes, allowing teams to build skills libraries and skill stacks more controllably, improve the reliability and maintainability of agent expansion capabilities, and adapt to pluggable capabilities in the MCP ecosystem.
SkillsMP is an Agent Skills Market and Aggregate Directory for AI Programming Assistants. It mainly collects and organizes a large number of Agent Skills from GitHub to help developers discover, filter and install reusable skills faster. SkillsMP opens standards around SKILL.md and is compatible with tools such as Claude Code, OpenAI Codex CLI, and ChatGPT, allowing skills to precipitate best practices, workflow, and code specifications in a unified structure. Through classified navigation, author and popularity screening, quality indicators and search capabilities, SkillsMP makes it easier to reuse and combine skills such as code review, test generation, automated submission, and project scaffolding in AI programming scenarios. SkillsMP also provides documentation and interface instructions to facilitate teams to integrate skill management into engineering processes and continuously improve AI programming efficiency and delivery quality.
ClawHub is a skills registration and distribution platform for AI agents. It focuses on a "versioned skill warehouse", allowing developers to manage skill packages like managing dependencies. ClawHub supports browsing, installing and publishing skill packs, and provides a searchable skill catalog and popular selections to quickly find suitable agent capability modules. ClawHub emphasizes that versions can be rolled back and stably iterated, and cooperates with the command-line one-click installation process to reduce skills access costs and improve the usability of agents in automated tasks, tool calls, and workflow orchestration. For building a pluggable capability system based on MCP, ClawHub can also serve as an entrance to the skills ecosystem, helping teams reuse and govern AI agent skills more efficiently.
KiloClaw is a managed AI office assistant from Kilo that focuses on intelligent execution experiences that require no installation, rapid deployment, and continuous on-line. KiloClaw can read emails, manage calendars, monitor projects, work on documents, and interact through popular communication channels such as Telegram and Slack, allowing users to integrate AI office capabilities directly into existing workflows without having to learn a new user interface. As an AI office product that emphasizes task execution rather than simple question answering, KiloClaw is suitable for information organization, process automation, schedule management, and multi-step task collaboration, helping individuals and teams complete their daily tasks more efficiently.
EvoLink is a unified AI model access gateway for developers and enterprises, which can aggregate and call dialogue, image, video, and music models from multiple major service providers through a single EvoLink API, reducing the cost of multi-platform integration. EvoLink emphasizes OpenAI-compatible interfaces and low migration barriers, provides intelligent routing and failover, improves production environment stability, and helps teams control costs in real time with usage statistics and transparent billing. For teams that need to build AI applications, AI office automation, or multi-model capability orchestration, EvoLink serves as the core infrastructure that integrates model selection, availability, and cost optimization into a single set of APIs and consoles.
MuleRun is an online marketplace for AI agents and AI applications, allowing users to select and directly run different agents according to the scene for tasks such as content creation, office efficiency, data, and marketing, just like visiting an app store. MuleRun also provides MuleRun MCP cloud service capabilities, allowing developers to call multiple MCP services using API keys, integrate agent tools into their workflows and products, and bill points based on the call consumption. Through the "release-price-monetize" mechanism, MuleRun also supports creators to put their self-developed agents on the shelves for sale, and continue to obtain real usage data and revenue, making MuleRun an AI Agent Marketplace and MCP platform that takes into account both use and creation.
Pi (Presentation Intelligence) is a one-stop AI office presentation creation platform, Pi focuses on one-click generation of PPT and interactive presentation documents: as long as you enter a sentence or upload document materials, Pi can automatically produce presentation content with reasonable structure, pictures and texts, and unified layout. Pi supports multi-terminal adaptive display, allowing the same content to be smoothly switched between different lengths, devices, and formats. At the same time, it provides brand-specific agents and style theme control to help teams stably output presentations with consistent brand tones. Focusing on collaboration scenarios, Pi supports multi-person co-creation, intelligent mapping, knowledge space (uploading or linking databases), and provides API/MCP access methods to facilitate the integration of Pi into enterprise content production and presentation workflows, and improve the production efficiency of reports, training, event promotion, and project reports.
XiaoZhi AI is an open-source AI hardware project and console service for developers and hardware vendors, focusing on low-latency voice conversations and scalable agent capabilities. Based on the Model Context Protocol (MCP), Xiaozhi AI connects speech recognition, intent understanding, memory and tool calling in series, and adapts to a variety of common chips and development boards, making it convenient and quick to make products such as emotional companionship, smart home control, desktop voice assistants, and in-vehicle robots. Through the Xiaozhi AI console, users can create agents, configure roles and behaviors, and complete device binding and management, making Xiaozhi AI more worry-free from prototyping to mass production access.
Kilo Code is an open-source AI programming agent extension for VS Code, focusing on the integration of "architecture-coding-debugging". Built-in Orchestrator, Architect, Code, and Debug modes can automatically disassemble tasks, generate implementations, locate and fix errors. It supports on-premises and cloud large models, OpenRouter and its own API Key, and is compatible with MCP Marketplace and common development processes. Definition: Kilo Code is an end-to-end AI programming tool that completes the process from solution to delivery within VS Code, suitable for individuals and teams to efficiently implement complex projects, reduce repetitive labor and hallucinatory code.
Alibaba Cloud Bailian is a one-stop large model service platform for enterprises and developers, supporting access to mainstream models such as Tongyi Qianwen series, DeepSeek, and Kimi, and is compatible with OpenAI API calling methods for rapid integration. The platform provides key functions such as model fine-tuning, knowledge base Q&A, agent creation, plug-in integration, RAG retrieval enhancement, and contextual memory management, and supports visual construction and multi-model hybrid calling. Developers can access through Python and Java SDKs to call models for tasks such as text generation, image processing, code generation, and search Q&A. Bailian's built-in security mechanisms, including data encryption, permission control, and AI content governance, are suitable for building AI applications such as intelligent customer service, office assistants, search engines, and content production, and support privatization deployment and enterprise-level operations.
HiMCP.ai is an AI tool integration platform focused on Model Context Protocol (MCP), bringing together over 11,000 MCP servers across various fields such as AI inference, content generation, data analysis, and browser automation. The platform provides developers with unified MCP client and server resources, supports seamless integration with mainstream AI assistants such as Claude, Cursor, and Cline, simplifying the discovery, deployment, and invocation process of AI tools. HiMCP.ai connects AI models with external data sources, APIs, and systems through standardized protocols, improving the scalability and collaboration efficiency of AI applications, making it suitable for building RAG systems, automated workflows, and multimodal AI applications.
MCP.so is an MCP (Model Context Protocol) resource hosting platform created by domestic developer idoubi, aiming to help developers and AI application users discover, share, and use various MCP services, thereby enhancing the connectivity and utility of large language models (LLMs). The platform provides a comprehensive list of MCP servers, covering various features such as file system access, database operations, web automation, map services, and more. Users can quickly find the MCP services they need through keyword searches, and support multi-dimensional filtering by function, protocol type, and other dimensions. The platform encourages users to submit their own MCP server projects and participate in discussions and feedback, fostering the common development of the community. MCP.so also recommends a variety of MCP client tools, such as Claude Desktop, Cherry Studio, Cursor, etc., to help users access and use MCP services more conveniently.
API Tracker's MCP Servers page brings together over 100 official and community-released Model Context Protocol (MCP) servers. The page provides presentation tools by category (e.g., database, browser automation, search engine, blockchain, etc.), making it easy for developers to quickly discover and compare contextual services that can be integrated with large language models (e.g., Claude, Cursor, Windsurf, etc.). Each MCP server comes with integration status, documentation, and platform support information to help developers efficiently access external APIs in IDE and AI Agent environments. This catalog is suitable for technical teams seeking high availability, standardized deployment, and rapid tool integration, making it an essential resource for building AI toolchains.
MCP Servers is an open-source server aggregation platform focused on Model Context Protocol (MCP), bringing together thousands of official and community-built MCP servers covering databases, browser automation, cloud services, search engines, communications, file systems, and more. The platform supports seamless integration with AI clients such as Claude, Cursor, VS Code, and Windsurf, helping developers quickly access external tools and data sources for large language models (LLMs). MCP Servers provides standardized interfaces and tool discovery mechanisms, supports local deployment and remote calling, and is suitable for building RAG systems, AI assistants, automated workflows, and other application scenarios, significantly improving the scalability and collaboration efficiency of AI applications.