← Discover MCPs and Agents
l
MCPAI & MLGitHub

llm-client

User-friendly Java HTTP client that provides access to large language model APIs and services

Links

README

From the repo.

CodeGPT - LLM Client

A user-friendly Java HTTP client, providing access to the large language model (LLM) APIs and services.

Contributions welcome Maven

Installation

To use the package, you need to use following Maven dependency:

<dependency>
    <groupId>ee.carlrobert</groupId>
    <artifactId>llm-client</artifactId>
    <version>0.8.58</version>
</dependency>

Gradle dependency:

dependencies {
  implementation("ee.carlrobert:llm-client:0.8.58")
}

Usage

Chat Completion SSE

OpenAIClient client = new OpenAIClient.Builder(System.getenv("OPENAI_API_KEY"))
    .setOrganization("MY_ORGANIZATION")
    .build();

EventSource call = client.getChatCompletionAsync(
    new OpenAIChatCompletionRequest.Builder(List.of(new OpenAIChatCompletionStandardMessage("user", prompt)))
        .setModel(OpenAIChatCompletionModel.GPT_4)
        .setTemperature(0.1)
        .build(),
    new CompletionEventListener<String>(){
      @Override
      public void onMessage(String message, EventSource eventSource) {
        System.out.println(message);
      }
    });

call.cancel();

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement".

  1. Fork the Project
  2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
  3. Commit your Changes (git commit -m 'Add some AmazingFeature')
  4. Push to the Branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

License

This is an unofficial OpenAI library and is not associated with or endorsed by OpenAI.

MIT © Carl-Robert Linnupuu

Collected info

  • 28 stars
  • 32 forks
  • Language: Java
  • Source updated: 8/30/2026

Config for your environment

Replace {MCP_ENDPOINT_URL} with this MCP’s endpoint URL (from its repo or docs above). No API key — you connect directly.

Tool

OS

Config file: ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server": {
      "url": "{MCP_ENDPOINT_URL}"
    }
  }
}

Paste into mcpServers in the config file. Restart Cursor after saving.

If this MCP is also published on mcpchannel.ai, you can subscribe from Browse and use the gateway config there instead.