Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
Give your AI agent access to 41+ JetBrains IDE tools — code analysis, search, refactoring, database queries, and more.
jbctl is an Agent Skill that bridges AI agents (Claude Code, etc.) to the built-in in WebStorm, IntelliJ IDEA, GoLand, PyCharm, and other JetBrains IDEs (2025.2+). The agent learns a workflow and can autonomously use any IDE tool.
CLI bridge for JetBrains IDE MCP Server
discover → doctor → inspect → callTool availability varies by IDE product and version.
Paste this into Claude Code to install both the CLI and the skill:
Install jbctl globally (
bun i -g jbctl) and add the skill (bunx skills add https://github.com/OrdinarySF/jbctl.git).
bun i -g jbctl
Or use npm: npm i -g jbctl. You can also run without installing via bunx jbctl.
bunx skills add https://github.com/OrdinarySF/jbctl.git
This adds the skill to .claude/skills/jbctl in your project.
# macOS Apple Silicon
curl -fSL https://github.com/OrdinarySF/jbctl/releases/latest/download/jbctl-darwin-arm64 -o /usr/local/bin/jbctl
chmod +x /usr/local/bin/jbctl
# macOS Intel
curl -fSL https://github.com/OrdinarySF/jbctl/releases/latest/download/jbctl-darwin-x64 -o /usr/local/bin/jbctl
chmod +x /usr/local/bin/jbctl
# Linux x64
curl -fSL https://github.com/OrdinarySF/jbctl/releases/latest/download/jbctl-linux-x64 -o /usr/local/bin/jbctl
chmod +x /usr/local/bin/jbctl
git clone https://github.com/OrdinarySF/jbctl.git
cd jbctl && bun install && bun scripts/build.ts
cp dist/jbctl-* /usr/local/bin/jbctl
For Claude Code:
mkdir -p .claude/skills
ln -s /path/to/jbctl/skills/jbctl .claude/skills/jbctl
For other agents that support Agent Skills, point them at skills/jbctl/SKILL.md.
The skill teaches your agent the full workflow — connection check, tool discovery, schema inspection, and tool invocation — with guardrails for destructive operations and error handling.
Your Agent (Claude Code, etc.)
|
jbctl CLI ← skill teaches the agent how to call this
|
MCP Protocol ← auto-detects transport (Streamable HTTP / SSE)
|
JetBrains IDE ← code analysis, indexing, type resolution, DB access
The IDE does the heavy lifting (indexing, inspections, type resolution). jbctl gives your agent a clean CLI interface to call it. The agent doesn't need to know about MCP transports, endpoint ports, or projectPath injection — jbctl handles all of that.
JetBrains IDEs expose an MCP Server that agents can connect to directly. But direct MCP has friction in real-world setups:
In short: direct MCP works when you have one IDE, one project, no worktrees, and the port doesn't change. jbctl works everywhere else.
jbctl discover scans for running IDEs. Matches your project path against each IDE's opened projects to find the right instance — even with multiple IDEs running simultaneously.inspect before call, so the agent never guesses parameter shapes."Look up the last 10 orders for user 42"
The agent discovers the database connection already configured in your IDE — no DSN, no credentials, no .env:
jbctl doctor -p /your/project
jbctl call list_database_connections -p /your/project --output json
# → [{"name":"prod-readonly", ...}, {"name":"local-dev", ...}]
jbctl call execute_sql_query -p /your/project \
--json '{"connectionName":"local-dev","query":"SELECT * FROM orders WHERE user_id = 42 ORDER BY created_at DESC LIMIT 10"}' \
--output json
No driver install, no connection string — the IDE already has it.
"Rename
processOrdertohandleOrderacross the whole project"
The agent uses the IDE's refactoring engine, which understands types, imports, and string references — not just text replacement:
jbctl call search_symbol -p /your/project \
--json '{"symbol":"processOrder"}' --output json
# → finds the definition and all usages
jbctl call rename_refactoring -p /your/project \
--json '{"path":"src/services/order.ts","offset":142,"newName":"handleOrder"}' --output json
# → IDE renames the symbol everywhere: definitions, imports, type references, JSDoc
One command, zero missed references.
jbctl discover handles this automatically.-p pointing to the IDE's original project directory.MIT
CLI bridge for JetBrains IDE MCP Server
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Jbctl ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-10-28 CLI bridge for JetBrains IDE MCP Server
