#128 · Primary category： LLM Application Frameworks
swift-sdk
The official Swift SDK for Model Context Protocol servers and clients.
Project last updated：05/07/26
GitHub Stars
1.5K
Forks
231
Contributors
18
License
Other
Why we included this project
If you build with Swift, this is the official SDK for connecting your apps to AI models over the Model Context Protocol, and it covers both ends of that connection. The client side lets an app call a model, while the server side publishes your own commands for assistants to use, with transports, authentication flows, and cancellation handled for you. Because it tracks the current protocol specification and is the reference implementation, it gives Swift teams a maintained baseline instead of a third-party port that follows its own conventions. On Apple platforms or backend services, that means you can add model interoperability without hand-rolling JSON-RPC plumbing.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform