Claude
- Open Add custom connector ↗
- Name it iPlugin Junqi and paste the URL
- Click Add, then ask away
https://iplugin.dev/junqi/mcp
1v1 face-up Luzhanqi
IPlugin Junqi is a fullscreen face-up Luzhanqi (军棋) match on the classic 12 × 5 field. You command 25 red pieces from the bottom; your AI commands 25 blue pieces from the top. Every deployment is legal: the flag sits in a headquarters, mines guard the back two rows, bombs avoid the front line, and three engineers start on the railways. Move one step along a road or travel any distance straight along a railway; engineers can turn corners. Camps are safe, headquarters freeze a piece in place, bombs trade with any enemy, engineers defuse mines, and higher ranks win. Capture the enemy flag — or leave the opponent with no legal move — to win. The plugin includes legal-destination hints, road and railway highlighting, battle reports, complete-turn undo, army ledgers, three difficulty levels, an AI First option and confirmed resignation. There is no Junqi engine, opening book or hidden move selector: the model chooses every blue move from the server's legal move list.
Start a fullscreen face-up Junqi game and let me move first.
Follows the skill
https://iplugin.dev/junqi/mcphttps://iplugin.dev/junqi/mcpiplugin.devThe AI reads these server instructions before using this connector, every time.
Junqi (Luzhanqi) is a public, face-up two-player game on a 12-row by 5-column field. The human plays red from the bottom; the current ChatGPT model plays blue from the top. Each side has 25 pieces: one flag, three landmines, two bombs, three engineers and sixteen ranked pieces. The model chooses every blue move from the legalMoves list; the server validates roads, railways, camps, headquarters, combat, undo, resignation and win conditions. There is no engine, opening book, hidden information or hidden move selector. Call only once per conversation to open the board; never call it again after the board is open, even for a new game. Then use the game tools sequentially for one gameId. Goal: capture the enemy flag, or leave the opponent with no legal move. Coordinates are rows A–L from top to bottom and columns 1–5. Camps are safe; a piece in a headquarters cannot move; engineers may turn corners on railways. Ask the human to confirm before resigning.
1v1 face-up Luzhanqi. IPlugin Junqi is a fullscreen face-up Luzhanqi (军棋) match on the classic 12 × 5 field. You command 25 red pieces from the bottom; your AI commands 25 blue pieces from the top.
Open its listing in the app's connector directory and connect. No sign-in is needed. Step-by-step setup for each app is on this page.
The iPlugin Junqi MCP server URL is https://iplugin.dev/junqi/mcp. Paste it as a custom connector in Claude, ChatGPT, Gemini or Grok, or add it to Claude Code, Cursor or any MCP client. Setup steps.
Yes. iPlugin Junqi is published or run by Trustflow, so it is the official MCP server. See other official connectors.
It is listed in 1 store: ChatGPT. Apps where it is not listed can usually still add it as a custom connector.
It is ranked 13,994 of 15,293 in the ChatGPT directory. A rank is the store's own order, not a usage count. How we track ranks.
It has 7 tools: 2 read data, 3 change data and 2 can delete or overwrite data. See every tool and its inputs.
Yes. 3 tools can change data and 2 tools can delete or overwrite it. Most AI apps ask before they run these. The store marks these as destructive:
It comes with 1 skill. A skill tells the AI how to do one job well with these tools. Read each SKILL.md.
Here are examples from its store listing. Type one into your AI after you connect.
Yes. Some of its tools show an interactive widget in the chat, not only text. See more connectors with interactive UI.
This page updates every day. To ask about iPlugin Junqi from Claude, ChatGPT or a coding agent, connect the Agent Ready MCP server: it tracks ranks, tools and new listings across the AI plugin stores.