Step-by-Step Guide to Setting Up a Mirai QQ Bot with Python Using mirai-console-loader and mirai-api-http

This article provides a comprehensive tutorial for developing a QQ bot using the Mirai framework, focusing on Python developers while also covering the necessary Java/Kotlin components.

Mirai ecosystem : The core consists of mirai-core and mirai-core-api ; mirai-console wraps these for easier plugin development, and mirai-api-http exposes HTTP/WebSocket interfaces for other languages.

Starting with mirai-console-loader : Download the mirai-console-loader (mcl) from GitHub, unzip, open a command prompt, navigate to the folder, and run mcl . If configuration errors appear, edit the config file as shown in the screenshots.

Handling slide captcha with mirai-login-solver-selenium : After launching mcl , add the captcha‑solver plugin using the command mcl --update-package net.mamoe:mirai-login-solver-selenium --channel nightly --type plugin . Download the matching chromedriver manually, rename it (e.g., chromedriver-86.0.4240.198.exe ), and replace the file in the indicated directory before rerunning mcl and logging in.

Adding mirai-api-http for language extensibility : Place the downloaded mirai-api-http.jar into the plugins folder, then restart mcl . If a signature verification error occurs, replace Oracle JDK with OpenJDK and update the system environment variables accordingly.

Configuring OpenJDK : Download an OpenJDK build, extract it, place it in a convenient location, and add its bin directory to the system PATH variable.

mirai-api-http settings (setting.yml) :

authKey: graia-mirai-api-http-authkey
cacheSize: 4096
enableWebsocket: true
host: '0.0.0.0'
port: 8080

Installing the Python library : Run pip install graia-application-mirai to install the Graia framework.

Python bot script (bot.py) :

from graia.broadcast import Broadcast
from graia.application import GraiaMiraiApplication, Session
from graia.application.message.chain import MessageChain
import asyncio

from graia.application.message.elements.internal import Plain
from graia.application.friend import Friend

loop = asyncio.get_event_loop()

bcc = Broadcast(loop=loop)
app = GraiaMiraiApplication(
    broadcast=bcc,
    connect_info=Session(
        host="http://localhost:8080",
        authKey="graia-mirai-api-http-authkey",
        account=5234120587,
        websocket=True
    )
)

@bcc.receiver("FriendMessage")
async def friend_message_listener(app: GraiaMiraiApplication, friend: Friend):
    await app.sendFriendMessage(friend, MessageChain.create([
        Plain("Hello, World!")
    ]))

app.launch_blocking()

Run the script; if the bot replies "Hello, World!" to a friend message, the setup is successful.

Conclusion : The steps above constitute a starter guide for building a Mirai‑based QQ bot. For more advanced features and API details, refer to the official Mirai documentation.