Plango for ChatGPT and Claude

Ask ChatGPT or Claude whether an MCP server, agent skill, agent plugin, GitHub repo or npm package is safe to install, and look up CVEs. It needs no Plango account.

Server address

https://installplango.com/mcp

Add it to Claude

• Open Settings, then Connectors.
• Choose “Add custom connector.”
• Name it Plango and paste the server address.

Add it to ChatGPT

• Open chatgpt.com/plugins.
• Select the plus button, then “Add custom MCP server.”
• Name it Plango, paste the server address and choose “No authentication.”

What it does

• Get safety report: returns Plango’s report on a project. A grade from A+ to F, what the code can reach on your computer, and each finding with its file and line.
• Scan a project: downloads the public source of a project Plango has not reviewed yet, reviews it and stores the report. The assistant asks you first. Plango never runs the code.
• Look up a CVE: returns the severity, score, affected product and summary of one CVE.
• Search CVEs: lists the known vulnerabilities of a product, such as an AI coding agent or an MCP server.

Things to ask

• Is this MCP server safe to install? https://github.com/modelcontextprotocol/servers/tree/main/src/time
• Which known vulnerabilities affect Cursor?
• What is CVE-2025-49596?

Limits

• Plango reads public GitHub repos and public npm packages only. It cannot see your computer, your private repos or your accounts.
• A grade is an automated review of the source at one revision. It is evidence, not a guarantee.
• CVE data comes from the US National Vulnerability Database: every CVE that affects AI agents and their tools, and every CVE published this year.

Privacy and support

What the plugin receives is in our Privacy Policy. For help, use our support page or email support@acrebase.com.