菜单
Patsnap TRIZ Concept Solution Engine MCP for AI agents. Generates innovation or product cost-reduction concepts through asynchronous TRIZ and TRIZ/DFMA workflows. Use for engineering problem solving, concept alternatives, cost-reduction analysis, task-progress retrieval, and selected-solution details.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/patsnap/mcp --skill patsnap-solution-engine命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Patsnap Patent Research MCP for AI agents. Performs novelty searches, invention freedom-to-operate reviews, and design-patent FTO reviews from technical text, claims, disclosures, or product images. Use for defined novelty and infringement-risk research workflows, including asynchronous task retrieval; do not use it as a substitute for legal advice.
Create or update Patsnap MCP catalog documentation in this repository. Use when adding a Marketplace MCP server, refreshing its README or service SKILL, classifying it under ip-intelligence, life-sciences, or rd-innovation, or updating the repository README and Glama indexes.
Patsnap Patent Analysis MCP for AI agents. Aggregates and mines a patent search result into trends, distributions, rankings, cross-tabs, keyword clouds, and innovation sunbursts. Use after a patent-search tool has returned a reusable search expression; this service analyzes rather than discovers patents.
正在显示 SKILL.md
| name | patsnap-solution-engine |
| description | Patsnap TRIZ Concept Solution Engine MCP for AI agents. Generates innovation or product cost-reduction concepts through asynchronous TRIZ and TRIZ/DFMA workflows. Use for engineering problem solving, concept alternatives, cost-reduction analysis, task-progress retrieval, and selected-solution details. |
| homepage | https://open.zhihuiya.com/marketplace/mcp-servers/patsnap-solution-engine |
| metadata | {"author":"Patsnap","category":"RD Innovation","version":"1.0.0","requires":{"mcp_endpoint":"https://connect.zhihuiya.com/c18800/mcp?apikey=YOUR_API_KEY"}} |
Get your API key at https://open.zhihuiya.com
This skill connects your AI agent to Patsnap's TRIZ Concept Solution Engine MCP server.
{
"mcpServers": {
"patsnap_solution_engine": {
"url": "https://connect.zhihuiya.com/c18800/mcp?apikey=YOUR_API_KEY",
"type": "streamableHttp"
}
}
}
For the full tool schema, refer to: https://open.zhihuiya.com/marketplace/mcp-servers/patsnap-solution-engine
run_triz_innovation_task → fetch_triz_innovation_task_stream → fetch_triz_innovation_solution_detail.run_triz_reduction_task → fetch_triz_reduction_task_stream → fetch_triz_reduction_solution_detail.Do not mix innovation and reduction tool families for one task. Preserve the returned job_id; after candidates arrive, preserve the selected idea_id.
The start tools require user_input. Include the current design, desired outcome, constraints, unacceptable trade-offs, and known function or cost information. The CN endpoint accepts at most 1,000 characters; non-CN environments may allow only 500.
Poll only the stream tool matching the start tool until candidates or a terminal failure are returned. A complete task normally takes 5–10 minutes and may take longer with complex or incomplete input. Intermediate selection points run automatically using the highest-priority option; do not represent them as user-approved choices.
Compare candidate concepts using feasibility, expected impact, implementation complexity, risk, and the user's constraints. Retrieve details only after an idea_id is selected. Separate service output from your own assessment and state unresolved engineering assumptions.
For reduction tasks, retain returned cost analysis, trimming analysis, DFMA findings, and benefit estimates. Treat estimates as hypotheses until checked against BOM, process, quality, and supplier data.