MCP App Store
by KeenEthics
Plango icon

Plango MCP Server for Claude

By Acrebase, Inc.

Overview

Plango reads the source code of MCP servers, agent skills, agent plugins, GitHub repos and npm packages, and tells you how safe they are to install. Ask "is this safe?" with a GitHub link, an npm package name or an install command. If Plango has already reviewed the project, you get its report: a grade from A+ (best) to F, what the code can reach on your computer, and each finding with its file and line. If the project is new, Plango can download the public source, review it, and return the report. Small projects take about a minute. Plango never runs the code. Plango also looks up CVEs: one CVE by its id, or the known vulnerabilities of a product such as an AI coding agent or an MCP server. The data comes from the US National Vulnerability Database and covers every CVE that affects AI agents and their tools, and every CVE published this year. 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.

How to connect

  1. Claude: Open the Plango listing in the Claude connectors directory and choose Connect. Claude listing Plango exposes 4 tools here.

Tools

get_cve

Claude
Use this when the user names a CVE id (CVE-2026-12345). Returns severity, score, the affected product and a summary from Plango's copy of the US National Vulnerability Database: every CVE that affects AI agents and their tools, and every CVE published this year.

get_safety_report

Claude
Use this when the user asks whether an MCP server, agent skill, agent plugin, GitHub repo or npm package is safe to install or run. Returns Plango's stored report: a grade from A+ (best) to F, what the project can reach on the computer, and each finding with its file and line. Reads Plango's database only; when the project has not been scanned yet it says so, and start_safety_scan scans it.

search_cves

Claude
Use this when the user asks which known vulnerabilities affect a product, such as an AI coding agent, an MCP server or a library. Searches product names and summaries in Plango's copy of the US National Vulnerability Database (AI agent CVEs of any year, and every CVE published this year). CVEs of a product with that name come first, AI agent CVEs before others, then newest first.

start_safety_scan

Claude
Use this when get_safety_report says a project has not been scanned yet, or its report is out of date. Plango downloads the public source from GitHub or npm (it never runs it), reviews it, and stores the report. Small projects finish within a minute and the report is returned; for larger ones call get_safety_report a few minutes later.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/plango"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/plango)