# Intelligent assistant

The Flow MCP Server is a model context protocol server designed for the Flow blockchain, providing standardized interfaces for blockchain data access and operations, and supporting functions such as balance query, domain name resolution, script execution, and transaction submission.

CRIC Property AI MCP Server is a server implementation based on CRIC's intelligent AI assistant for the property industry, providing functions such as industry information, hot questions, and knowledge base search, and supporting two access methods: SSE and Stdio.

Lark MCP is an AI assistant framework based on Feishu. It realizes function calls and message processing through reverse Feishu protocol, supports custom function registration and automatic matching calls. There's no need to configure a robot, and you can directly use your personal Feishu account as an AI assistant.

The Perplexity MCP Server is an intelligent research assistant that uses Perplexity's AI model to provide automatic query complexity detection and optimal model routing functions, supporting three tools: search, reasoning, and in - depth research.

The Yushan Data API service provides enterprise - related data query functions, is compatible with the MCP protocol, and supports quickly querying enterprise basic information, overseas investments, change records, software copyrights, trademarks, litigation, and abnormal business operation information through LLM.

The Perplexity MCP Server is an intelligent research assistant that uses Perplexity's dedicated AI model to automatically detect query complexity and route requests to the most appropriate model for the best results. It supports three tools: search, reasoning, and in - depth research, suitable for query tasks of different complexities.

The Clay MCP Server is a simple model context protocol server designed for the Clay platform, providing functions such as contact search, interaction record query, statistics acquisition, and contact management. It supports quick deployment via Smithery or manual installation and configuration.

MCP OpenVision is an image analysis server based on OpenRouter's vision models, providing image analysis capabilities for AI assistants.

The MCP iCal Server is a natural language-based macOS calendar management tool that enables conversational calendar operations through the Model Context Protocol, supporting event creation, querying, modification, and multi-calendar management.

A project management tool that connects LLMs with Plane.so, supporting project and task management through the API

The enhanced version of the Todoist MCP server is a service that implements the Model Context Protocol (MCP), integrating Claude with Todoist and supporting the management of tasks, projects, sections, and labels using natural language.

An MCP server that integrates Claude with Todoist, supporting task management through natural language, including functions such as creating, querying, updating, completing, and deleting tasks.

Mianshiya MCP Server is an interview question search API service compatible with the MCP protocol, allowing intelligent agent assistants to quickly access and retrieve interview questions.

A personalized 'Model Context Protocol' (MCP) server has been released. It's similar to JARVIS but with a more distinct style and supports handling complex problems.

Mianshiya MCP Server is an interview question search service compatible with the MCP protocol. It is integrated through the Java SDK, supports multiple intelligent agent assistants to quickly access, and provides question retrieval functions.

An integrated service that allows you to directly search for and purchase Amazon products through the Claude AI assistant

OpenManus is an open-source project that allows users to realize various ideas without an invitation code. It was built by members of the MetaGPT team in 3 hours. It provides a simple implementation that allows users to create their own intelligent agents and supports multiple languages and configurations. The project welcomes suggestions, contributions, and feedback. Future plans include better planning, real-time demonstrations, playback functions, RL fine-tuning models, and comprehensive benchmarking.