mcp-scala MCP Server

Use This MCP server To

Integrate MCP server functionality in Scala-based applications Generate random numbers and sequences via MCP tools Execute numeric computations like sum through MCP tools Develop custom MCP tools using Scala 3 Test MCP client-server communication using stdio transport Extend MCP server with additional content parts and transports Contribute to open-source MCP server development in Scala

README

MCP-scala

Model Context Protocol server written in Scala 3

Development stage

This software is currently ALPHA state.

This implementation needs your attention and contribution.

Feel free to open Issue / PR to contribute this project.

Demo

First, build server into JS:

sbt example/fastLinkJS

Then, utilize server in your MCP client:

// Example for Cline
{
  "mcpServers": {
    "mcpscala": {
      "disabled": false,
      "timeout": 30,
      "command": "sh",
      "args": ["/path/to/run.sh"],
      "transportType": "stdio"
    }
  }
}

You can run some tool:

randomNumber
- generate random number between min to max.
iota
- generate a sequence of numbers from min to max.
sum
- calculate the sum of a sequence of numbers.

Implement your tool

See Main.scala for details.

//> using scala 3
//> using toolkit typelevel:default
//> using dep dev.capslock::mcpscala:0.1.0

package dev.capslock.mcpscala

import cats.effect.IO
import cats.effect.IOApp
import dev.capslock.mcpscala.transport.StdioServer
import dev.capslock.mcpscala.mcp.ContentPart
import sttp.tapir.Schema.annotations.description

case class RandomNumberInput(
    @description("Minimum value (inclusive)") min: Int,
    @description("Maximum value (exclusive)") max: Int
) derives io.circe.Decoder,
      sttp.tapir.Schema

def randomNumber(input: RandomNumberInput): IO[Seq[ContentPart]] = IO {
  val random = scala.util.Random.between(input.min, input.max)
  Seq(ContentPart.TextContentPart(random.toString))
}

/** Entry point for the Stdio server.
  */
object StdioMain extends McpIOApp(
    name = "random-number",
    header = "Generate a random number",
  ):
    
  val handlers = Handler.methodHandlers(
    Map(
      "randomNumber" -> server.Tool(randomNumber),
    )
  )

mcp-scala FAQ

How do I run the mcp-scala server?

Build the server using sbt and run it via a shell script with stdio transport as shown in the demo.

What transport protocols does mcp-scala support?

Currently, mcp-scala supports stdio transport; HTTP transport is planned for future releases.

Can I define custom tools in mcp-scala?

Yes, mcp-scala allows defining custom tools with automatic JSON Schema derivation.

Is mcp-scala production-ready?

No, it is currently in alpha stage and may lack some features like authorization and notification handling.

How can I contribute to mcp-scala?

You can contribute by opening issues or pull requests on the GitHub repository.

Does mcp-scala support authorization?

Authorization handling is not yet implemented but planned for future updates.

What programming language is mcp-scala written in?

It is written in Scala 3, leveraging its features for MCP server implementation.

Can mcp-scala be used with different LLM providers?

Yes, as an MCP server, it is provider-agnostic and can work with OpenAI, Claude, Gemini, and others.