Swift MCP SDK

Official Swift SDK for the [Model Context Protocol][mcp] (MCP).
Overview
The Model Context Protocol (MCP) defines a standardized way
for applications to communicate with AI and ML models.
This Swift SDK implements both client and server components
according to the [2025-11-25][mcp-spec-2025-11-25] (latest) version
of the MCP specification.
Table of contents
- Requirements
- Installation
- Client Usage
- Basic Client Setup
- Transport Options for Clients
- Tools
- Resources
- Prompts
- Completions
- Sampling
- Elicitation
- Roots
- Logging
- Error Handling
- Cancellation
- Progress Tracking
- Advanced Client Features
- Server Usage
- Basic Server Setup
- Tools
- Resources
- Prompts
- Completions
- Sampling
- Elicitations
- Roots
- Logging
- Progress Tracking
- Initialize Hook
- HTTP Request Context in Handlers
- Graceful Shutdown
- Transports
- Authentication
- Client: Client Credentials Flow
- Client: Authorization Code Flow
- Client: Custom Token Provider
- Client: Custom Token Storage
- Client: private\_key\_jwt Authentication
- Client: Endpoint Overrides
- Server: Serving Protected Resource Metadata
- Server: Validating Bearer Tokens
- Platform Availability
- Debugging and Logging
- Additional Resources
- Changelog
- License
Requirements
- Swift 6.0+ (Xcode 16+)
See the Platform Availability section below
for platform-specific requirements.
Installation
Swift Package Manager
Add the following to your Package.swift file:
Then add the dependency to your target:
Client Usage
The client component allows your application to connect to MCP servers.
Basic Client Setup
> [!NOTE]
> The Client.connect(transport:) method returns the initialization result.
> This return value is discardable,
> so you can ignore it if you don't need to check server capabilities.
Transport Options for Clients
Stdio Transport
For local subprocess communication:
HTTP Transport
For remote server communication:
Tools
Tools represent functions that can be called by the client:
Resources
Resources represent data that can be accessed and potentially subscribed to:
Prompts
Prompts represent templated conversation starters:
Completions
Completions allow servers to provide autocompletion suggestions for prompt and resource template arguments as users type:
You can also provide context with already-resolved arguments:
Completions work for resource templates as well:
Sampling
Sampling allows servers to request LLM completions through the client,
enabling agentic behaviors while maintaining human-in-the-loop control.
Clients register a handler to process incoming sampling requests from servers.
> [!TIP]
> Sampling requests flow from **server to client**,
> not client to server.
> This enables servers to request AI assistance
> while clients maintain control over model access and user approval.
Elicitation
Elicitation allows servers to request structured information directly from users through the client.
This is useful when servers need user input that wasn't provided in the original request,
such as credentials, configuration choices, or approval for sensitive operations.
> [!TIP]
> Elicitation requests flow from **server to client**,
> similar to sampling.
> Clients must register a handler to respond to elicitation requests from servers.
Client-Side: Handling Elicitation Requests
Register an elicitation handler to respond to server requests:
Common use cases for elicitation:
- **Authentication**: Request credentials when needed rather than upfront
- **Confirmation**: Ask for user approval before sensitive operations
- **Configuration**: Collect preferences or settings during operation
- **Missing information**: Request additional details not provided initially
Roots
Roots define the filesystem boundaries that a client exposes to servers. Servers discover roots by sending a roots/list request to the client; clients notify servers when the list changes.
> [!TIP]
> To use roots, declare the roots capability when creating the client.
Logging
Clients can control server logging levels and receive structured log messages: