#client

The new purpose-built IDE to harness magic

The second fastest AI chatbot™

🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.

5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .

Call MCP Server Tools Online

Lutra is the first MCP compatible client built for everyone

ChatMCP is an AI chat client implementing the Model Context Protocol (MCP).

API client built for AI agents. MCP tools for creating collections, running requests, chaining flows, mocking APIs, and exporting CI workflows. Zero cloud dependency.

PI client built for AI agents. MCP tools for creating collections, running requests, chaining flows, mocking APIs, and exporting CI workflows. Zero cloud dependency.

MCP Peek is a local-first desktop app to inspect, run, and proxy MCP servers. Connect any server over stdio or HTTP/SSE, browse its full catalog of tools, resources, and prompts with token-cost estimates, run tools through auto-generated forms, and capture live request/response traffic with the built-in proxy.

Conduit is a local-first gateway that puts every MCP server behind one endpoint shared by all your AI coding tools (Claude, Cursor, VS Code, Codex, and more). Set up and authenticate each server once, then connect every client to Conduit instead of re-adding servers everywhere. Keys stay in your OS keychain (never in client configs), lazy discovery exposes just 3 meta-tools so your agent's context stays small no matter how many servers you add, and you can toggle servers on/off live without restarting the client. Proxies both local (stdio) and remote (http/SSE) servers, with a built-in audit log and tool playground. No Docker, no cloud, no account. Free and open source (MIT). Windows, macOS, and Linux.

Unified inbox MCP for WhatsApp, Telegram, Email, voice — read/send messages, search conversations, manage contacts, query knowledge graph, and trigger AI agents through natural language.

MCP server for Faster Fixes. Lets AI agents list, triage, and resolve client feedback collected from your website widget — directly from your terminal.

A transparent desktop overlay that gives your AI agent a visual presence on screen. Your AI picks its own body from a library of avatars, colors, and expressions or draws it's own in SVG. Windows, $4.99, 7-day free trial, no account required.

Share documents securely, track who views them, and manage your finances — all through AI. Create sharing links with password protection, email gates, NDA agreements. Get real-time analytics: page heatmaps, viewer engagement, download tracking. Full invoicing with estimates, clients, companies, products. Personal & business accounting: transactions, transfers, multi-currency, batch receipts. 15+ tools with granular OAuth 2.1 scopes.

One app to manage all your MCP servers across every AI client.

Give your AI agent unblockable browser access. Aluvia routes traffic through premium mobile carrier IPs to bypass 403s, CAPTCHAs, and WAFs automatically.

GitScrum Studio MCP server for AI-powered project management. 29 tools covering tasks, sprints, time tracking, invoicing, proposals, client workflows, analytics, standups, wikis, and discussions. Supports 160+ operations with built-in OAuth device flow authentication.

A Model Context Protocol (MCP) server that provides secure SSH capabilities for AI assistants, enabling remote command execution, SFTP file transfers, and port forwarding with comprehensive security controls. Features: - 🔐 Secure SSH Command Execution - Execute commands on remote servers with granular security controls - 🛡️ Host Allowlisting - Only connect to pre-configured, trusted servers - 📁 SFTP File Operations - Upload, download, list, and delete files on remote servers - 🌉 SSH Port Forwarding - Create secure tunnels to access remote services - 🔄 Connection Pooling - Persistent connections with automatic management - 🔑 SSH Key Authentication - Secure authentication using SSH private keys - ⚙️ SSH Config Integration - Import servers from your existing SSJ config file - ✅ Command Allowlisting - Restrict which commands can be executed - 📦 Named Services - Pre-configured port forwarding services for common use cases - 🎯 Command Templates - Reusable parameterized commands with variable substitution

Unlock MCP for your whole team in Slack with a single install. Unlike most MCP clients, Runbear enables multiple users to utilize MCP servers with only one Slack installation. You can build Slack bots and connect any MCP services along side with built-in 2,000+ MCP servers with just clicks.

Kash.click management assistant. Connect your assistant to your business complete sales history, clients, payments, tax information, employees, points of sales.

Agentic assistant that handles the complexity while you focus on results. With MCP support and advanced Orchestrator/Agent capabilities, BB connects to hundreds of external data sources & tools and breaks down complex tasks for maximum efficiency.

AI workspace platform that provides unified access to multiple frontier AI models, assistants with persistent memory, and integrated tools for web search, document analysis, code creation, and data visualization. Features team collaboration capabilities, screen sharing for context, voice interaction, and MCP integrations for connecting external apps and services. Designed for individuals, teams, enterprises, and educational institutions who want to avoid vendor lock-in while maintaining secure, collaborative AI workflows across different models and tools.

A comprehensive MCP server for Kanboard project management that provides tools for managing projects, tasks, users, comments, files, and more through the Kanboard API. Key Features: Project management (create, update, delete, list projects) Task management (create, update, delete, move, search tasks) User management (create, update, delete users) Comment system (create, update, delete comments) File management (upload, download, delete files) Swimlane and column management Tag management Metadata handling Search functionality Supported Kanboard API Methods: 50+ methods covering all major Kanboard functionality Language: Go License: MIT (as shown in your LICENSE.md) Requirements: Built executable (kanboard-mcp.exe for Windows) Kanboard instance with API access API credentials (API key or username/password) This MCP server provides a complete interface to Kanboard's project management capabilities through the Model Context Protocol, making it easy to integrate Kanboard functionality into AI assistants and other MCP-compatible applications.

Warp is the fastest way to build with multiple AI agents—from writing code to shipping it. The best overall coding and terminal agent.

Build and automate your own AI team. Just like building a website with vibe coding, build your AI team the same way. Automation, analytics, execution — your custom AI agents handle it all for you. Zentrun lets you vibe-code real, executable AI agents. With a single sentence, you create actions that run, remember, analyze, and evolve — powered by MCP and designed for automation at scale.

QuerySculptor is a GraphQL query builder designed for AI agents that provides 26 structured tools via the Model Context Protocol (MCP). Instead of generating complex GraphQL queries from scratch, AI agents can build queries step-by-step with real-time validation, schema introspection, and error prevention. It works with Claude, Cursor, and other MCP clients, using Redis for session management and featuring a live demo with the Pokemon API. The tool transforms the traditional error-prone approach of raw GraphQL generation into a guided, conversational workflow perfect for AI assistants and chatbots.

Simple MCP client with config for servers

Rails Engine with MCP compliant Spec.

Desktop app that automatically scans and blocks malicious MCP traffic in AI apps like Cursor, Claude, VS Code and Windsurf.

Node.js mcp server for iRacing data api

a light weight version of mcp sdk inspired by official model context protocol sdk, NOW focus on sse only no stdio

Simple MCP SDK in Java

A CLI host application that enables Large Language Models (LLMs) to interact with external tools through the Model Context Protocol (MCP).

This comprehensive learning resource provides two complete tutorials for mastering Model Context Protocol (MCP) development with Rust. From beginner-friendly introductions to production-ready enterprise applications, these tutorials guide you through every aspect of building robust MCP servers.

本项目实现了一个兼容 OpenAI API 格式的 MCP-Client服务，允许通过标准的 OpenAI API 接口与本地 MCP-Server进行交互。

本项目实现了一个兼容 OpenAI API 格式的 MCP-Client服务，允许通过标准的 OpenAI API 接口与本地 MCP-Server进行交互。

LLM & MCP desktop for AI models

Simple MCP client using Gradio with locally run MCP servers.

MCP server for advanced baseball analytics (statcast, fangraphs, baseball reference, mlb stats API) with client demo

TypeScript client library and utilities for remote Model Context Protocol (MCP) servers

MCP Client & Server

This open-source curriculum is designed to teach the concepts and fundamentals of the Model Context Protocol (MCP), with practical examples in .NET, Java, TypeScript, JavaScript and Python.

Support connecting E2B via MCP, with custom server and client, without the need for tools like the Claude app, Cursor, etc.

AWS API/lambda hosting MCP client server that queries bedrock LLM using MCP hosted tools

A Model Context Protocol (MCP) server that provides calculator functionality for MCP clients.

This repository implements an MCP (Model Context Protocol) server that exposes various functionalities on an Azure Blob Storage account. It is based on the MCP SDK from Anthropic, which can be found at:

MCP server exposing SSH control for Linux servers via Model Context Protocol.

A scriptable and powerful UI-Chat-Application for chatting with most Gen-AI LLMs

an MCP client written in angular/typescript using Claude.ai for integration with ApiLogicServer server executions

🚀 mcp-use is a TypeScript library that makes it easy to connect LangChain.js-compatible LLMs with MCP servers. Build powerful, flexible AI agents with dynamic tool access and multi-server support.

MCP Agents is an AI-powered browser automation tool that lets you interact with websites using natural language. Built with Streamlit, OpenAI, and Puppeteer via the Model Context Protocol (MCP), it supports multi-step navigation, interaction, and content extraction—all with simple text commands.

MCP client/server example using qwen3

Lightweight MCP client that uses a local Ollama LLM to query multiple MCP servers defined in config.json

This Go implementation allows MCP clients that only support local (stdio) connections to connect to remote MCP servers with authentication support.

这是一个MCP客户端，让你轻松配置各个大模型，对接各种MCP Server而开发。This is an MCP client that allows you to easily configure various large models and develop interfaces with various MCP servers.

Relay16 is a modern Nostr social client that integrates AI-powered tools through MCP servers for enhanced social media experiences.

A demonstration of a MCP server showcasing dynamic tools and resources.

An MCP server that enables uploading videos to YouTube through Claude Desktop or any MCP-compatible client

MCP client and server with command line chat interface using Anthropic

Using Azure OpenAI perform series of tasks using mcp server

Simple MCP Server & Client Sample (with Gemini Function Calling)

The MCP Docs Server is a Node.js implementation of a Model Context Protocol (MCP) server that provides a powerful tool to search and retrieve up-to-date documentation snippets from popular AI/ML libraries. It leverages the Serper API to perform Google searches restricted to specific documentation domains, extracts meaningful content using web

小智 & Cursor 的 MCP 启动器 - MCP For Cursor&xiaozhi。打包成可执行文件。Turn MCP server into an executable file

MCP server for Baserow API integration - Enable AI assistants to interact with Baserow databases

Let AI agents interact with your API

Example of a MCP implementation using TypeScript and OAuth.

Versatile library for the Model Context Protocol (MCP), primarily designed for handling authentication.

Turn any API spec into AI-accessible tools instantly.

A Model Context Protocol server that facilitates interaction with the Solana blockchain, built using the Ping Agent Kit. (

基于Spring AI 封装了 mcp-client 服务，目的使web网页智能体也能通过 stdio 和 HTTP SSE（Server-Sent Events） 与 MCP Server 进行交互。项目实现了自动化的连接管理机制，包括自动初始化连接、健康检查、超时关闭以及链接复用等功能

MCP Chatbot powered by Anthropic Claude. Delivering on‐demand literature search and summarisation for academics and engineers

MCP Playground: Experiment with Anthropic's Claude & Model Context Protocol. Chat, connect servers, test tools.

This is an MCP client that allows you to easily configure various large models and develop interfaces with various MCP servers. 这是一个MCP客户端，让你轻松配置各个大模型，对接各种MCP Server而开发。

A web-hosted AI chat platform available at moopoint.io, designed for developers and advanced users to interact with multiple large language models (LLMs) through a single, unified interface. The platform allows seamless integration with custom MCP servers and gives users secure control over their own API keys for providers such as OpenAI, Anthropic, and others.

MCP-smallest-ai

The AI toolkit for the AI developer

A simple MCP server

Mirror of

⚡ Chat MCP Client for Remote hosted MCP Servers (with Composio) and locally hosted MCP servers. 📡

A Python-based client for interacting with Model Context Protocol (MCP) servers using Ollama. Features include multi-server support, dynamic model switching, tool management, and a rich terminal interface.

Mirror of

Demos of MCP servers and client for a quick start

Gres is a minimalist AI command server for agents and developers. Snap pages, grab sites, source docs, and ask anything. One interface, zero fluff.

MCP tutorials and content

Bridge Tufin APIs to AI workflows: An open-source REST server with RBAC for SecureTrack and SecureChange integration.

A web client for managing MCP servers and tools

TypeScript client for interacting with MCP (Model Context Protocol) servers

MCP Gateway and Registry

The AI toolkit for the AI developer

A personal template for building MCP servers and clients.

Run your MCP Kit servers in local clients like Claude Desktop

MCP server for my CV(Resume)

MCP Client which serves as bridge between mcp servers and local LLMs running on Ollama, Created for MCP Servers Developed by Me, However other MCP Servers may run as well

CLI & API for MCP management and execution

his is a Node.js command-line application that integrates with GitHub via the Model Context Protocol (MCP) server and OpenAI's API.

LLM chat app for integration tests using llama-stack-client, llama, Ollama, MCP, Tools

A simple MCP (Model Context Protocol) server that provides weather alert information for US states, leveraging the National Weather Service (NWS) API. It also includes an example client application that demonstrates how to interact with the MCP server using the mcp_use library.

This project 🌐 is a robust implementation of the Model Context Protocol (MCP), designed to facilitate seamless integration and interaction with various documentation sources. It provides tools for querying and extracting relevant information from documentation, making it an essential resource for developers working with libraries

Client for communicating with MCP-Recon-Server

An agent playground (without authentication) in a single repo for fastest turn around cycles during experiments.

A simple .NET implementation of an MCP (Model Context Protocol) Client and Server example. This project demonstrates how to create and interact with an MCP server using custom tools, natural language prompts, and standard I/O transport.

Simple Multi-Server MCP Client with LangChain

A C# implementation of dynamic configured MCP client manager that connects to multiple MCP servers

A working example of your own agents from the scratch and using it with the mcp servers from scratch

Build your own mcp server with spring ai

Basic demo for a MCP client & server