$ loading_
Audit MCP servers and plugins for risk before installation with graded findings.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "MCPVet" yet — see the docs or source repo.
Please review this MCP server's config and documentation. Check for shell execution, secret access, data exfiltration, prompt injection, or remote code download, then provide a risk rating, evidence, and installation recommendation.
A graded security review listing findings, risk explanations, and whether installation is recommended.
I have three candidate plugins. Review each for dangerous permissions, external network access, sensitive data reads, and execution capabilities, then rank them from highest to lowest risk and explain the main concerns.
A comparison table or ranked list that helps the user choose the safer plugin option.
Based on this review, prepare an audit summary for the team including high-risk items, impact scope, mitigation advice, and a pre-deployment checklist.
A concise team-facing audit summary with an actionable checklist.
Review fleet-wide vulnerability and PII scan findings with natural language.
Query vulnerability intelligence, risk scores, and attack-surface data for security decisions.
Score trust and safety before installing MCP servers, AI skills, or npm packages.
Analyze MCP tool security risks, detect malicious behavior, and provide risk scores.
Search vetted MCP servers by task and review advisory guidance.
Delegate coding tasks to Codex via MCP with security and result checks.