GJQ Runtime MCP Server
OfficialThe GJQ Runtime MCP Server enables AI assistants to interact with the GuoJi Quantum Cloud Platform for submitting and managing quantum computing tasks.
Account Management
setup_gjq_account_tool– Configure and cache cloud API credentialsactive_account_info_tool– View active account info (API key masked)
Device/Backend Management
list_backends_tool– List all available quantum backends (devices and simulators)get_backend_configuration_tool– Get static configuration (basis gates, qubit count, etc.)get_backend_properties_tool– Get calibration properties (T1/T2 times, gate error rates)least_busy_tool– Find the least busy available backend
Quantum Circuit Execution
sample_tool– Submit a sampling task using an OpenQASM 2.0/3.0 circuit, with configurable shots, transpilation, and optimization levelestimate_tool– Submit an expectation-value estimation task with a specified observable (Pauli strings + coefficients)
Task Management
get_task_status_tool– Poll task status (INITIALIZING / QUEUED / RUNNING / DONE / ERROR / CANCELLED)get_task_result_tool– Retrieve results of a completed taskget_task_log_tool– Get the execution log of a taskget_task_detail_tool– View task details (backend used, shots, submission time)list_my_tasks_tool– List all tasks submitted by the current user
MCP Resources
Pre-built example circuits: Bell state, GHZ state, Superposition, and Random circuits (
circuits://*)Server status resource at
gjq://status
Allows interaction with the CETC-ICQ quantum cloud platform, providing tools for account management, device listing, circuit submission (sampling and estimation), and task management.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@GJQ Runtime MCP ServerList available quantum backends"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
GJQ-Runtime-MCP-Server
一个Model Context Protocol(MCP)服务器,让AI助手通过gjq-clientPython SDK与国基量子计算云平台交互。
功能
账号管理:配置并查看云平台凭据
设备管理:列出后端、查询配置/校准信息、获取最空闲后端
计算任务:从OpenQASM提交采样(sampling)与期望估计(estimation)任务
任务管理:轮询状态、获取结果/日志/详情、列出任务
示例电路:Bell/GHZ/叠加/随机,以MCP资源形式提供
功能展示
Related MCP server: mcp-qiskit
安装与启动(以Cursor为例)
克隆仓库并创建虚拟环境
git clone <this-repo>
cd gjq-runtime-mcp-server
python -m venv .venv
# Windows
.\.venv\Scripts\activate
# Linux/macOS
source .venv/bin/activate
pip install -e ..env.example重命名为.env,进入设置GJQ_API_KEY=你的_api_key。(API key 从 https://www.tiangongqs.com/cloud 获取)本地启动 MCP Server(先验证可运行)
python -m gjq_runtime_mcp_server在项目根目录创建
.cursor/mcp.json
# Windows(该行去除)
{
"mcpServers": {
"gjq-runtime": {
"command": ".venv\\Scripts\\python.exe",
"args": ["-m", "gjq_runtime_mcp_server"],
"cwd": "/path/to/gjq-runtime-mcp-server",
"env": { "GJQ_API_KEY": "你的_api_key" }
}
}
}
# Linux/macOS(该行去除)
{
"mcpServers": {
"gjq-runtime": {
"command": ".venv/bin/python",
"args": ["-m", "gjq_runtime_mcp_server"],
"cwd": "/path/to/gjq-runtime-mcp-server",
"env": { "GJQ_API_KEY": "你的_api_key" }
}
}
}在 Cursor 中验证
重启 Cursor。
打开
Cursor Settings → Tools & MCPs → Installed MCP Servers。确认有
gjq-runtime,打开开关,并检查显示小绿点。
MCP 工具
账号:
setup_gjq_account_tool、active_account_info_tool设备:
list_backends_tool、get_backend_configuration_tool、get_backend_properties_tool、least_busy_tool计算:
sample_tool、estimate_tool任务:
get_task_status_tool、get_task_result_tool、get_task_log_tool、get_task_detail_tool、list_my_tasks_tool
所有工具返回 {"status": "success" | "error", ...}。
提交电路时 OpenQASM 2.0 开箱即用;如需提交 OpenQASM 3 电路,请额外安装解析库:
pip install qiskit_qasm3_import。
MCP 资源
gjq://status、circuits://bell-state、circuits://ghz-state、circuits://superposition、circuits://random
其他 MCP 客户端配置
上面的 JSON 适用于 Cursor、Claude Desktop 等基于 JSON 配置的客户端。
客户端 | 配置文件 |
Cursor |
|
Claude Desktop | macOS: |
Codex |
|
Codex 使用 TOML 而非 JSON,在 ~/.codex/config.toml 中添加如下内容
(顶层表名必须是 mcp_servers):
[mcp_servers.gjq-runtime]
command = "/path/to/gjq-runtime-mcp-server/.venv/bin/python"
args = ["-m", "gjq_runtime_mcp_server"]
cwd = "/path/to/gjq-runtime-mcp-server"
[mcp_servers.gjq-runtime.env]
GJQ_API_KEY = "你的_api_key"Agent 技能
配套技能位于 skills/gjq-quantum-runtime/。
在 Cursor 中使用时,把该目录复制到 .cursor/skills/(项目级)或
~/.cursor/skills/(个人级)。
安全说明
API key 以明文存储在
~/.gjq_client/gjq_client_account.json以及 MCP 客户端配置的env中,请当作机密妥善保管,切勿提交.env。
开发
pip install -e ".[test]"
pytest许可证
Apache License 2.0
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseAqualityDmaintenanceThis MCP server enables Claude Desktop to create, visualize, and simulate quantum circuits using Qiskit and Qiskit Aer, with support for preset circuits, custom QASM, and noise modeling.Last updated3
- Alicense-qualityCmaintenanceMCP server exposing Qiskit quantum computing functionality through the Model Context Protocol. Enables LLMs to create, manipulate, and execute quantum circuits via standardized MCP tools and resources.Last updatedMIT
- Alicense-qualityAmaintenanceMCP server for quantum device physics laboratory instrumentation control, enabling LLMs to interact with physics instruments and measurement systems through QCodes and JupyterLab.Last updated27MIT
- Alicense-qualityBmaintenanceAn MCP server that provides real-time IBM Quantum device data including queue depths, error rates, and coherence times, enabling AI assistants to query and compare quantum hardware.Last updated6MIT
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server for Gainium — manage trading bots, deals, and balances via AI assistants
MCP server for GLM chat completions using Zhipu AI models via AceDataCloud
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/guoji-quantum/gjq-runtime-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server