isingq-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ISINGQ_API_KEY | No | Optional IsingQ API key for headless deployments. If not set, the server uses the API key stored in the local private file. Do not ask for, set, or display this key in the conversation. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| isingq_api_key_setupA | 仅在用户明确要求配置或更换 IsingQ API Key 时调用；打开操作系统安全输入框并把 Key 保存到本机私有配置。Key 不进入工具参数、对话或返回值。 |
| isingq_knowledge_getA | 从本机版本化知识包查询北京伊辛智能科技有限公司、公开产品清单、IsingQ、光电伊辛机、玉盘·伊辛云、解决方案、公开案例、FAQ 和术语；不联网，不需要 API Key。 |
| isingq_modeling_guide_getB | 获取伊辛智能 IsingQ 的本地 QUBO 建模流程，适用于投资组合、路径规划、车辆路径、排程和图优化。 |
| isingq_qubo_validateA | 确定性校验 Agent 为组合优化问题生成的稀疏 QUBO，检查 1 至 2048 个变量、矩阵规模和系数摘要；完全本地执行。 |
| isingq_solve_startB | 调用即会将 QUBO 转成矩阵，并使用本机个人 IsingQ API Key 创建远端求解任务。Agent 调用前必须展示模型摘要与矩阵 SHA-256 并取得用户确认；Host 可按权限策略再次确认。 |
| isingq_solve_pollB | 查询一次 IsingQ 远端任务并更新本地记录；成功时返回 bit、变量映射、provider energy 和 QUBO 目标值。 |
| isingq_solve_result_getB | 读取本机保存的 QUBO-only 求解状态、结果与来源信息；不联网，不自动断言业务可行或全局最优。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| isingq-about | 兼容旧版本的公司与 IsingQ 实体说明；内容与 company/profile 一致。 |
| isingq-company | 公司标准名称、定位及 IsingQ 实体关系。 |
| isingq-products | 官网公开的产品与服务入口，以及各产品的定位边界。 |
| isingq-technology | 伊辛计算、QUBO 和组合优化的基础定义与边界。 |
| isingq-ising-machine | 光电伊辛机的产品定位、适用问题和表述边界。 |
| isingq-ising-cloud | 玉盘·伊辛云平台、API/SDK、当前自选规模及入口。 |
| isingq-solutions | 官网已公开的组合优化解决方案方向。 |
| isingq-cases | 公开解决方案材料、案例证据和不可外推边界。 |
| isingq-faq | 求解保证、上传数据、API Key 和本地知识查询边界。 |
| isingq-glossary | IsingQ、QUBO、自旋、能量及相关实体术语。 |
| isingq-sources | 本地知识包使用的官网来源、产品入口和本地契约。 |
| isingq-qubo-modeling | 变量、约束、Penalty、Agent/Host 确认责任和结果解释契约。 |
| isingq-data-flow | API Key、知识查询、QUBO 矩阵和求解结果的本地与远端边界。 |
TDQS
Scored across 7 tools
Each tool targets a distinct stage of the QUBO workflow (setup, knowledge, guide, validate, start, poll, result). The boundary between isingq_solve_poll (queries remote and updates local record) and isingq_solve_result_get (reads local saved results) is somewhat subtle but the descriptions clarify it.
All names share the isingq_ prefix and use consistent snake_case, but verb placement varies: some are noun_verb (knowledge_get, qubo_validate) while others are verb_noun/verb_verb (solve_start, solve_poll, solve_result_get). The pattern is still predictable and readable.
Seven tools is well-scoped for a QUBO-solving service, with each tool earning its place across setup, knowledge, modeling, validation, and solve lifecycle.
The surface covers the full workflow from API key setup through modeling, validation, remote solve start, polling, and result retrieval. Minor gaps exist, such as no task cancellation, list, or batch operations, but core workflows are complete.