Client and server packages
The package workspace contains dedicated `client` and `server` areas for developers implementing both sides of an MCP connection.
The official TypeScript SDK for building Model Context Protocol servers and clients. It provides a repository-organized foundation for MCP development, with separate client, server, core, middleware, documentation, and example areas.
The Model Context Protocol TypeScript SDK is the official TypeScript SDK for MCP servers and clients. Hosted in a public GitHub repository, it provides the project structure and source packages used by developers implementing MCP software, with separate areas for client, server, shared core, middleware, codemod, documentation, examples, and tests.
Its core purpose is to give TypeScript teams an official starting point for building MCP clients and servers. The repository includes supporting documentation and examples, but the supplied source does not provide enough detail to state a complete list of transports, integrations, setup commands, or protocol capabilities.
The package workspace contains dedicated `client` and `server` areas for developers implementing both sides of an MCP connection.
`core` and `core-internal` packages provide distinct locations for shared SDK foundations and internal implementation code.
A dedicated `middleware` package is included for organizing middleware-related SDK code rather than mixing it into the client or server packages.
The repository includes a `codemod` package and a `server-legacy` package, indicating separate locations for code transformation work and legacy server support.
Dedicated `docs` and `examples` directories give users project guidance and reference implementations to consult while evaluating or building an MCP project.
The repository includes a `test` workspace plus contribution, security, versioning, roadmap, and dependency-policy documentation for working with the project itself.
A TypeScript developer can use the official server package as the starting point for an application that exposes MCP functionality.
An application that needs to act as an MCP client can work from the repository’s dedicated client package instead of maintaining an unrelated client implementation.
Developers evaluating MCP can use the project’s documentation and examples directories to inspect the structure and approach used by the official SDK.
Teams working with older server code can investigate the separate legacy-server and codemod areas when planning maintenance or migration work.
It is the official TypeScript SDK for Model Context Protocol servers and clients, maintained in the public `modelcontextprotocol/typescript-sdk` GitHub repository.
The repository is organized for both use cases, with separate `client` and `server` packages.
The repository contains dedicated `docs` and `examples` directories. The supplied evidence does not include their detailed contents, so consult the current files for setup and implementation guidance.
No. The supplied repository listing confirms the SDK’s main package areas but does not provide a complete transport or integration inventory. Those details should be checked in the current SDK documentation.
sequel.sh
Sequel is an AI data analyst and secure data layer for agents. It connects databases, warehouses, analytics platforms, spreadsheets, and SaaS tools so Claude, Cursor, ChatGPT, and other MCP-capable agents can answer questions using shared data connections and definitions.
workato.com
面向企业级智能体 AI 的集成与编排平台
platform.claude.com
Claude Platform gives developers programmatic access to Claude models and managed agent infrastructure for building agents and applications. It includes a REST API, official client SDKs, a web Console, and documentation for direct integrations.
learn.microsoft.com
Semantic Kernel is Microsoft’s public GitHub software project for integrating large language model technology into applications. The repository includes implementation and documentation directories for .NET, Python, and Java development.
callmejones.github.io
Blender Agent Bridge is a Blender extension and localhost MCP server that lets MCP-capable AI clients inspect Blender scenes, collect visual evidence, and make reversible edits. It is intended for users who want agent-assisted Blender workflows with explicit controls over trust and changes.
www.pipecat.ai
Pipecat is an open-source Python framework and ecosystem for building real-time voice and multimodal AI agents. It helps developers compose pipelines that coordinate speech, language, vision, video, text, tools, and telephony transports.