What does yotta-verify-mcp do?
YuanXinMCP (元信MCP) - a pre-installation security scanner for Agent skills via stdio MCP. Tools: scan_skill / generate_badge / gate_check / get_report. Zero-dependency Python 3.8+.
YuanXinMCP - A pre-installation security scanner for AI agent skills using stdio MCP. Provides tools: scan_skill, generate_badge, gate_check, get_report. Requires zero dependencies and runs on Python 3.8+.
YottaMeta/yotta-verify-mcp (YuanXinMCP) is a security scanning tool designed to run before installing AI agent skills. It helps developers and agent users identify potential security risks by scanning skill packages for malicious code, sensitive data leaks, or unsafe dependencies. The tool operates via stdio MCP (Model Context Protocol), offering four main tools: scan_skill for scanning, generate_badge for creating security status badges, gate_check for pass/fail gating, and get_report for detailed reports. It is built as a zero-dependency Python 3.8+ script, making it lightweight and easy to integrate into agent workflows or CI/CD pipelines. Platforms supported include any MCP-compatible agent environment, such as Claude Code or similar tools. By providing a simple, automated security check, it helps maintain a safer ecosystem for agent skill sharing and installation.
npx skills add YottaMeta/yotta-verify-mcpInstalled? Explore more Research & Data Analysis skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →
YuanXinMCP (元信MCP) - a pre-installation security scanner for Agent skills via stdio MCP. Tools: scan_skill / generate_badge / gate_check / get_report. Zero-dependency Python 3.8+.
USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.
Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.
Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Agent skill repository discovered by 10x-chat research.
Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `api/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.