- Kotlin 98%
- TypeScript 1.7%
- Shell 0.3%
| Filename | Latest commit message | Latest commit date |
|---|---|---|
# Refactor integration test infrastructure, fix and enable tests with ts-client - Refactor TypeScript integration test infrastructure to support parallel execution and real I/O operations. - Extract reusable TypeScriptClient component - Migrate some tests from `runTest` to `runBlocking` for tests that spawn actual processes and communicate over real network connections. ## Key Changes - Extract `TypeScriptClient` class for managing TS client processes - Move client scripts to integration-test/src/jvmTest/typescript/client/ - Migrate typescript: `myClient.ts`(2) → `sse-client.ts`, `stdio-client.ts` - Automate TypeScript dependency installation in static initializer - Enable JUnit parallel execution (dynamic strategy, concurrent mode) with test timeout of 2 minutes - Replace `mutableListOf` with `ConcurrentLinkedQueue` for thread-safe notification handling - Migrate integration tests from `runTest` to `runBlocking` **Rationale:** Integration tests that spawn real TypeScript processes, establish actual HTTP/SSE connections, and manage server lifecycles require real-time I/O behavior. The runTest framework's virtual time is designed for fast unit tests with simulated timing, not for integration scenarios where external processes and network communication must occur in real time. Parallel execution requires thread-safe data structures (ConcurrentLinkedQueue) to safely collect notifications from multiple concurrent test instances. - Add `EmbeddedServer.actualPort()` extension to get bound port - Standardize kotlin.time.Duration usage across test utilities - Update processUtils.stopProcess() to accept Duration parameter - Replace RuntimeException checks with idiomatic check() calls - Revert `--rerun-tasks` flag to Gradle workflows for reliable builds ## Motivation and Context Integration tests with typescript client are now broken. Enabling parallel test execution will force writing thread-safe independent tests and will highlight problems faster. ## How Has This Been Tested? CI ## Breaking Changes <!-- Will users need to update their code or configurations? --> ## Types of changes <!-- What types of changes does your code introduce? Put an `x` in all the boxes that apply: --> - [x] CI Update - [x] Test Fix ## Checklist <!-- Go over all the following points, and put an `x` in all the boxes that apply. --> - [x] I have read the [MCP Documentation](https://modelcontextprotocol.io) - [x] My code follows the repository's style guidelines - [x] New and existing tests pass locally - [ ] I have added appropriate error handling - [ ] I have added or updated documentation as needed ## Additional context Follow up for #477 |
||
| .github | ||
| buildSrc | ||
| conformance-test | ||
| docs | ||
| gradle | ||
| integration-test | ||
| kotlin-sdk | ||
| kotlin-sdk-client | ||
| kotlin-sdk-core | ||
| kotlin-sdk-server | ||
| samples | ||
| test-utils | ||
| .editorconfig | ||
| .gitignore | ||
| AGENTS.md | ||
| build.gradle.kts | ||
| CODE_OF_CONDUCT.md | ||
| CONTRIBUTING.md | ||
| gradle.properties | ||
| gradlew | ||
| gradlew.bat | ||
| LICENSE | ||
| README.md | ||
| settings.gradle.kts | ||
MCP Kotlin SDK
Kotlin Multiplatform implementation of the Model Context Protocol (MCP), providing both client and server capabilities for integrating with LLM surfaces across various platforms.
Overview
The Model Context Protocol allows applications to provide context for LLMs in a standardized way, separating the concerns of providing context from the actual LLM interaction. This SDK implements the MCP specification for Kotlin, enabling you to build applications that can communicate using MCP on the JVM, WebAssembly and iOS.
- Build MCP clients that can connect to any MCP server
- Create MCP servers that expose resources, prompts and tools
- Use standard transports like stdio, SSE, and WebSocket
- Handle all MCP protocol messages and lifecycle events
Samples
- kotlin-mcp-server: demonstrates a multiplatform (JVM, Wasm) MCP server setup with various features and transports.
- weather-stdio-server: shows how to build a Kotlin MCP server providing weather forecast and alerts using STDIO transport.
- kotlin-mcp-client: demonstrates building an interactive Kotlin MCP client that connects to an MCP server via STDIO and integrates with Anthropic’s API.
Installation
Add the new repository to your build file:
repositories {
mavenCentral()
}
Add the dependency:
dependencies {
// See the badge above for the latest version
implementation("io.modelcontextprotocol:kotlin-sdk:$mcpVersion")
}
MCP SDK uses Ktor, but does not come with a specific engine dependency. You should add Ktor client and/or Ktor server dependency to your project yourself, e.g.:
dependencies {
// for client:
implementation("io.ktor:ktor-client-cio:$ktorVersion")
// for server:
implementation("io.ktor:ktor-server-netty:$ktorVersion")
}
Quick Start
Creating a Client
import io.modelcontextprotocol.kotlin.sdk.client.Client
import io.modelcontextprotocol.kotlin.sdk.client.StdioClientTransport
import io.modelcontextprotocol.kotlin.sdk.Implementation
val client = Client(
clientInfo = Implementation(
name = "example-client",
version = "1.0.0"
)
)
val transport = StdioClientTransport(
inputStream = processInputStream,
outputStream = processOutputStream
)
// Connect to server
client.connect(transport)
// List available resources
val resources = client.listResources()
// Read a specific resource
val resourceContent = client.readResource(
ReadResourceRequest(uri = "file:///example.txt")
)
Creating a Server
import io.modelcontextprotocol.kotlin.sdk.server.Server
import io.modelcontextprotocol.kotlin.sdk.server.ServerOptions
import io.modelcontextprotocol.kotlin.sdk.server.StdioServerTransport
import io.modelcontextprotocol.kotlin.sdk.ServerCapabilities
val server = Server(
serverInfo = Implementation(
name = "example-server",
version = "1.0.0"
),
options = ServerOptions(
capabilities = ServerCapabilities(
resources = ServerCapabilities.Resources(
subscribe = true,
listChanged = true
)
)
)
){
"This server provides example resources and demonstrates MCP capabilities."
}
// Add a resource
server.addResource(
uri = "file:///example.txt",
name = "Example Resource",
description = "An example text file",
mimeType = "text/plain"
) { request ->
ReadResourceResult(
contents = listOf(
TextResourceContents(
text = "This is the content of the example resource.",
uri = request.uri,
mimeType = "text/plain"
)
)
)
}
// Start server with stdio transport
val transport = StdioServerTransport()
server.connect(transport)
Using SSE Transport
Directly in Ktor's Application:
import io.ktor.server.application.*
import io.modelcontextprotocol.kotlin.sdk.server.mcp
fun Application.module() {
mcp {
Server(
serverInfo = Implementation(
name = "example-sse-server",
version = "1.0.0"
),
options = ServerOptions(
capabilities = ServerCapabilities(
prompts = ServerCapabilities.Prompts(listChanged = null),
resources = ServerCapabilities.Resources(subscribe = null, listChanged = null)
)
),
) {
"This SSE server provides prompts and resources via Server-Sent Events."
}
}
}
Inside a custom Ktor's Route:
import io.ktor.server.application.*
import io.ktor.server.sse.SSE
import io.modelcontextprotocol.kotlin.sdk.server.mcp
fun Application.module() {
install(SSE)
routing {
route("myRoute") {
mcp {
Server(
serverInfo = Implementation(
name = "example-sse-server",
version = "1.0.0"
),
options = ServerOptions(
capabilities = ServerCapabilities(
prompts = ServerCapabilities.Prompts(listChanged = null),
resources = ServerCapabilities.Resources(subscribe = null, listChanged = null)
)
),
) {
"Connect via SSE to interact with this MCP server."
}
}
}
}
}
Contributing
Please see the contribution guide and the Code of conduct before contributing.
License
This project is licensed under the MIT License—see the LICENSE file for details.