After 4 months of intensive improvement, I’m thrilled to announce that SwiftMCP 1.0 is feature-complete and prepared so that you can use.
For these simply becoming a member of, SwiftMCP is a local Swift implementation of the Mannequin Context Protocol (MCP). The aim is to supply a dead-simple method for any developer to make their app, or elements of it, out there as a robust server for AI brokers and Giant Language Fashions. You’ll be able to learn the official specification at modelcontextprotocol.io.
I did a SwiftMCP 1.0 Function Pace Run on YouTube, if that’s what you favor.
The Core Concept: Your Documentation is the API
Earlier than diving into options, it’s essential to grasp the philosophy of SwiftMCP. The framework is constructed on the precept that your current documentation must be the first supply of fact for an AI. By utilizing normal Swift documentation feedback, you present all of the context an AI wants to grasp and use your server’s capabilities.
/**
Provides two numbers and returns their sum.
- Parameter a: The primary quantity so as to add
- Parameter b: The second quantity so as to add
- Returns: The sum of a and b
*/
@MCPTool
func add(a: Int, b: Int) -> Int {
a + b
}This code reveals the only use case. The @MCPTool macro inspects the add perform and its documentation remark. It robotically extracts the principle description (“Provides two numbers…”), the descriptions for parameters a and b, and the outline of the return worth, making all of this data out there to an AI shopper with none further work.
Server Options: Exposing Your App’s Logic
These are the capabilities your Swift software (the server) exposes to a shopper.
Instruments: The Basis of Motion
Instruments are the first approach to expose your app’s performance. By adorning any perform with @MCPTool, you make it a callable motion for an AI. A very good software is well-documented, handles potential errors, and supplies clear performance.
// Outline a easy error and enum for the software
enum TaskError: Error { case invalidName }
enum Precedence: String, Codable, CaseIterable { case low, medium, excessive }
/**
Schedules a activity with a given precedence.
- Parameter title: The title of the duty. Can't be empty.
- Parameter precedence: The execution precedence.
- Parameter delay: The delay in seconds earlier than the duty runs. Defaults to 0.
- Returns: A affirmation message.
- Throws: `TaskError.invalidName` if the title is empty.
*/
@MCPTool
func scheduleTask(title: String, precedence: Precedence, delay: Double = 0) async throws -> String {
guard !title.isEmpty else {
throw TaskError.invalidName
}
// Simulate async work
strive await Job.sleep(for: .seconds(delay))
return "Job '(title)' scheduled with (precedence.rawValue) precedence."
}This instance demonstrates a number of key options without delay. The perform is async to carry out work that takes time, and it throws a customized TaskError for invalid enter. It makes use of a CaseIterable enum, Precedence, as a parameter, which SwiftMCP can use to supply auto-completion to purchasers. Lastly, the delay parameter has a default worth, making it non-obligatory for the caller.
Sources: Publishing Learn-Solely Information
Sources permit you to publish information that purchasers can question by URI. SwiftMCP provides a versatile system for this, which will be damaged down into two predominant classes: function-backed sources and provider-based sources.
Perform-Backed Sources
These sources are outlined by particular person features embellished with the @MCPResource macro. If a perform has no parameters, it acts as a static endpoint. If it has parameters, they should be represented as placeholders within the URI template.
/// Static Useful resource: Returns a server information string
@MCPResource("server://information")
func getServerInfo() -> String {
"SwiftMCP Demo Server v1.0"
}
/// Dynamic Useful resource: Returns a greeting for a person by ID
/// - Parameter user_id: The person's distinctive identifier
@MCPResource("customers://{user_id}/greeting")
func getUserGreeting(user_id: Int) -> String {
"Good day, person #(user_id)!"
}The getServerInfo perform is a static useful resource; a shopper can request the URI server://information and can all the time get the identical string again. The getUserGreeting perform is dynamic; the {user_id} placeholder within the URI tells SwiftMCP to count on a worth. When a shopper requests customers://123/greeting, the framework robotically extracts “123”, converts it to an Int, and passes it to the user_id parameter.
Supplier-Primarily based Sources (like information)
For exposing a dynamic assortment of sources, like information in a listing, you possibly can conform your server to MCPResourceProviding. This requires implementing a property to find the sources and a perform to supply their content material on request.
extension DemoServer: MCPResourceProviding {
// Announce out there file sources
var mcpResources: [any MCPResource] {
let docURL = URL(fileURLWithPath: "/Customers/Shared/doc.pdf")
return [FileResource(uri: docURL, name: "Shared Document")]
}
// Present the file's content material when its URI is requested
func getNonTemplateResource(uri: URL) async throws ->
[MCPResourceContent] {
guard FileManager.default.fileExists(atPath: uri.path) else {
return []
}
return strive [FileResourceContent.from(fileURL: uri)]
}
}This code reveals the two-part mechanism. First, the mcpResources property is named by the framework to find what sources can be found. Right here, we announce a single PDF file. Second, when a shopper really requests the content material of that file’s URI, the getNonTemplateResource(uri:) perform is named. It verifies the file exists after which returns its contents.
Prompts: Reusable Templates for LLMs
For reusable immediate templates, the @MCPPrompt macro works identical to @MCPTool. It exposes a perform that returns a string or PromptMessage objects, making its parameters out there for the AI to fill in.
/// A immediate for saying Good day
@MCPPrompt()
func helloPrompt(title: String) -> [PromptMessage] {
let message = PromptMessage(function: .assistant,
content material: .init(textual content: "Good day (title)!"))
return [message]
}This instance defines a easy immediate template. An AI shopper can uncover this immediate and see that it requires a title parameter. The shopper can then name the immediate with a selected title, and the server will execute the perform to assemble and return the totally fashioned immediate message, able to be despatched to an LLM.
Progress Reporting: Dealing with Lengthy-Working Duties
For duties that take time, you possibly can report progress again to the shopper utilizing RequestContext.present, which prevents the shopper from being left at the hours of darkness.
@MCPTool
func countdown() async -> String {
for i in (0...30).reversed() {
let performed = Double(30 - i) / 30
await RequestContext.present?.reportProgress(performed,
whole: 1.0, message: "(i)s left")
strive? await Job.sleep(nanoseconds: 1_000_000_000)
}
return "Countdown accomplished!"
}On this perform, the server loops for 30 seconds. Contained in the loop, reportProgress is named on the RequestContext.present. This sends a notification again to the unique shopper that made the request, which may then use the progress worth and message to replace a UI factor like a progress bar.
Consumer Options: The Consumer is in Management
Whereas SwiftMCP is a server framework, it totally helps the highly effective capabilities a shopper can provide. The shopper holds quite a lot of management, and your server can adapt its conduct by checking Session.present?.clientCapabilities.
Roots: Managing File Entry
The shopper is in full management of what native information the server can see. When a shopper provides or removes a root listing, your server is notified and might react by implementing handleRootsListChanged().
func handleRootsListChanged() async {
guard let session = Session.present else { return }
do {
let updatedRoots = strive await session.listRoots()
await session.sendLogNotification(LogMessage(
degree: .information,
information: [ "message": "Roots list updated", "roots": updatedRoots ]
))
} catch {
// Deal with error...
}
}This perform is a notification handler. When a shopper modifies its record of shared directories (or “roots”), it sends a notification to the server. SwiftMCP robotically calls this perform, which may then use session.listRoots() to get the up to date record and react accordingly, for instance, by refreshing its personal record of accessible information.
Cancellation: Stopping Duties Gracefully
If the shopper is exhibiting a progress bar for that countdown, it also needs to have a cancel button. The shopper can ship a cancellation notification, and your server code should be citizen and verify for it with strive Job.checkCancellation().
Elicitation: Asking the Consumer for Enter
Elicitation is a robust interplay the place the server determines it wants particular, structured data. It sends a JSON schema to the shopper, and the shopper is answerable for rendering a type to “elicit” that information.
@MCPTool
func requestContactInfo() async throws -> String {
// Outline the info you want with a JSON schema
let schema = JSONSchema.object(JSONSchema.Object(
properties: [
"name": .string(description: "Your full name"),
"email": .string(description: "Your email address",
format: "email")
],
required: ["name", "email"]
))
// Elicit the knowledge from the shopper
let response = strive await RequestContext.present?.elicit(
message: "Please present your contact data",
schema: schema
)
// Deal with the person's response
swap response?.motion {
case .settle for:
let title = response?.content material?["name"]?.worth as? String ?? "Consumer"
return "Thanks, (title)!"
case .decline:
return "Consumer declined to supply data."
case .cancel, .none:
return "Consumer cancelled the request."
}
}This software demonstrates the three steps of elicitation. First, it defines a JSONSchema that specifies the required fields (title and e-mail). Second, it calls elicit on the present request context, sending the schema and a message to the shopper. Third, it waits for the person’s response and makes use of a swap assertion to deal with the totally different outcomes: the person accepting, declining, or canceling the request.
Sampling: Utilizing the Consumer’s LLM
Maybe probably the most fascinating function is Sampling, which flips the script. The server can request that the shopper carry out a generative activity utilizing its personal LLM. This permits your server to be light-weight and delegate AI-heavy lifting.
@MCPTool
func sampleFromClient(immediate: String) async throws -> String {
// Test if the shopper helps sampling
guard await Session.present?.clientCapabilities?.sampling != nil else {
throw MCPServerError.clientHasNoSamplingSupport
}
// Request the technology
return strive await RequestContext.present?.pattern(immediate: immediate) ?? "No response from shopper"
}This code reveals how a server can leverage a shopper’s personal generative capabilities. It first checks if the shopper has marketed help for sampling. In that case, it calls pattern(immediate:), which sends the immediate to the shopper. The shopper is then answerable for operating the immediate via its personal LLM and returning the generated textual content, which the server receives as the results of the await name.
What’s Subsequent?
My imaginative and prescient is for builders to combine MCP servers instantly into their Mac apps. My API.me non-public app does precisely this, exposing a person’s native emails, contacts, and calendar via a neighborhood server that an LLM can securely work together with. I’m pondering if I ought to put this on the app retailer or probably open supply it. What do you assume?
It has been numerous work, and it’s lastly prepared. SwiftMCP 1.0 is right here.
I’m very a lot wanting ahead to your suggestions. Please give it a strive, try the examples on GitHub, and let me know what you assume. I hope to see you construct some wonderful issues with it.
Oh and for those who haven’t watched it but, I actually advocate watching my demonstration of all the brand new options:
Associated
Classes: Updates
