joLink MCP server

joLink Runtime

<!-- mcp-name: io.github.L1ch404/jolink-runtime -->

English | 简体中文

A lightweight, headless Java IDE for AI coding agents.

Closing the loop for autonomous Java development.

Design principle: Everything exists to reduce uncertainty for the LLM.

joLink does not provide an editor UI. Instead, it exposes incremental compilation, testing, application startup and breakpoint debugging through MCP to the coding agent you already use—so it can run the code, inspect real state, and verify its own changes.

Persistent compilation state and HotSwap reduce repeated full rebuilds and JVM restarts. When tests, logs and endpoint responses are not enough, the agent can use breakpoints and inspect exception events, stack frames and variables.

Free and local. It does not require a joLink account, model API key, inference provider, or separate agent application.

Install

1. Open a new chat in your coding agent.
2. Click the copy button in the code block below, paste the entire prompt into that chat, and send it.

Follow this guide:
https://github.com/L1ch404/jolink-runtime/blob/main/INSTALL.md
Install joLink MCP and its English Skill for my current agent.
Use user-level installation by default and preserve existing configuration.
Check the saved configuration and Skill file. If this chat cannot load the new MCP or Skill,
stop and tell me how to reload the client; leave connection verification to a chat after reloading.

as instructed, then open a new chat. Configuration complete but not yet loaded is not an installation failure. In the loaded chat, you can send:

1. If the agent reports that a reload is needed, reconnect MCP or restart the client

Verify the existing joLink MCP and jolink-java Skill in this client without reinstalling them.
Call the joLink status tool exposed by this client once, and check its Skill list or loading facility.
If either is still unavailable, report what is missing and stop; do not write a standalone verification script.
Do not start applications or run tests.

The guide provides official client-specific locations and examples for Codex, Claude Code, Cursor, VS Code/Copilot, CodeBuddy, Gemini CLI, OpenCode, Cline, Roo Code and Windsurf. All start MCP with uvx jolink-runtime@latest and use the same English Skill; no plugin bundle or universal installer is required. MCP performs the work; the Skill helps the agent discover and use it. The guide also covers uv setup, preserving configuration, reconnection and verification.

For Chinese instructions, use the Chinese installation guide.

Why joLink

Coding agents are good at reading and changing code, but they can become stuck in a loop of static assumptions:

analyze
-> patch
-> assume the patch works
-> patch again

joLink adds the missing runtime feedback loop:

analyze
-> change
-> run
-> observe
-> update the hypothesis
-> change again if necessary

This is useful when:

code;

• the Java application is not running yet;
• a code change needs to be verified against real behavior;
• repeated patches have not solved the problem;
• endpoint results do not match the source-code interpretation;
• logs or tests are insufficient to explain the executed path;
• business naming is inconsistent and static search cannot find the relevant

• deeper runtime evidence such as breakpoints, stacks, or variables is needed.

The goal is not to use a debugger for every problem.

Start with the cheapest useful evidence:

application status
-> logs and actual outputs
-> exception events
-> executed path
-> breakpoints, stack frames, and variables

Debug deeper only when necessary.

What it can do

joLink exposes four focused MCP tools:

Shortened. The full README is on GitHub.