spring-projects / spring-projects/spring-ai

@McpTool annotated suspending functions are ignored in ASYNC server mode

Open
#4,485 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

status: waiting-for-triage
Dominant language
Java
Stars
9.5k
Forks
2.9k
Avg merge
1d 7h
Merged PRs (30d)
6

Description

Bug description

Similar to https://github.com/spring-projects/spring-ai/issues/4392. Only @McpTool functions that return Mono, etc, are used in ASYNC mode. This should also include Kotlin suspend functions (as well as ideally Flow returning functions).

I've categorized it as a bug, but if Kotlin isn't officially supported (i.e. https://github.com/spring-projects/spring-ai/issues/3718) it may fit better as a feature request.

Environment
Java 24, Kotlin 2.2.10, Spring AI 1.1.0-M2

Steps to reproduce
Have a @McpTool method that returns Mono that works with an async server.
Change it to not return Mono but be suspend.

Expected behavior
The function is still detected.

Minimal Complete Reproducible example

@SpringBootApplication
class Application {
    companion object {
        @JvmStatic
        fun main(args: Array<String>) {
            runApplication<Application>(*args)
        }
    }

    @McpTool
    fun testTool(): Mono<String> {
        return Mono.just("test")
    }

    @McpTool
    suspend fun testTool2(): String {
        return "test"
    }
}

testTool is registered, testTool2 is not. Config:

spring:
  ai:
    mcp:
      server:
        type: ASYNC
        annotation-scanner:
          enabled: true
        capabilities:
          tool: true
          resource: true
          prompt: true
          completion: true
        stdio: false

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the @McpTool annotation scanner in ASYNC server mode and reproduce the difference between the Mono-returning testTool and suspend testTool2 from the issue. Trace why suspend functions are omitted, then verify that the suspend tool is detected and registered while the existing Mono case remains working.

Written by the indexing model from the issue text.

Assessment

Tech stack
java, kotlin
Domain
api, backend
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.