$ loading_
Score trust and safety before installing MCP servers, AI skills, or npm packages.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "MCPskills" yet — see the docs or source repo.
Run a pre-install security review for this MCP server. Return a trust score, triggered risk signals, related vulnerability intelligence such as OSV/KEV/EPSS, and a go/no-go recommendation: <repo URL or package name>
An assessment with a trust score, detailed risk signals, vulnerability intel summary, and an install recommendation.
Compare the installation risk and trustworthiness of these three npm packages, rank them by safety, and explain the key risks and recommended choice: <Package A>, <Package B>, <Package C>
A ranked comparison showing each package’s risk signals, score differences, and final recommendation.
Design automatic approval rules for our MCP/AI skill intake process using trust score, vulnerability severity, and risk signals. Define conditions for auto-approve, manual review, and mandatory rejection.
A clear gating policy with threshold rules, tiered actions, and practical implementation guidance.
Statically scan MCP servers, skills, and plugins for security risks.
Publish, author, and reuse AI tools and skills via MCP and REST.
Equip AI agents with persistent skills and secure executable scripting.
Compile and serve skill definitions to AI agents via MCP.
Search, load, and manage AI agent skills from SkillDB directly.
Search, audit, and install open-source AI skills and MCP servers.