← Back to Blog
·5 min read·MindFizz

Introducing MCPScan: The First Local-First Security Scanner for MCP Servers

The Model Context Protocol (MCP) is everywhere. In the last year, over 8,500 MCP servers have appeared across registries, GitHub, and npm — giving AI agents the ability to read files, query databases, execute code, manage infrastructure, and interact with dozens of third-party APIs.

Here's what hasn't kept pace: security tooling.

Most MCP servers ship with no security review. No input validation on tool parameters. No authentication on transport layers. No sandboxing of execution environments. Developers install them with npx or uvx, wire them into their agent framework of choice, and move on.

Today, we're changing that.

What MCPScan Does

MCPScan is an open-source, local-first security scanner for MCP servers. It analyses MCP server configurations and tool definitions to identify vulnerabilities before they reach production.

It runs entirely on your machine. No data leaves your environment. No cloud accounts, no API keys, no telemetry.

Core Capabilities

  • Configuration Analysis — Inspects MCP server configurations and flags insecure defaults, overly permissive tool definitions, and missing authentication.
  • Tool Definition Scanning — Analyses tool schemas for injection vectors, unsafe parameter types, and patterns that could allow prompt injection or data exfiltration.
  • Transport Security Review — Checks for unencrypted transports, missing auth headers, and CORS misconfigurations.
  • OWASP LLM Top 10 Mapping — Every finding maps to the OWASP Top 10 for LLM Applications.
  • CI/CD Integration — Structured JSON output for GitHub Actions, GitLab CI, or any pipeline.

Why Local-First Matters

Most security scanners phone home. They upload your configurations to a cloud service for analysis. For MCP servers — which often contain database connection strings, API keys, and internal service URLs — that's a non-starter.

MCPScan runs entirely locally. Your configurations never leave your machine. A scanner that exfiltrates your MCP configs to analyse them is, ironically, demonstrating the exact class of vulnerability it should be detecting.

Getting Started

pip install mcpscan

# Scan a configuration
mcpscan scan --config ~/.config/claude/claude_desktop_config.json

# JSON output for CI/CD
mcpscan scan --config mcp.json --format json --output results.json

What's Next

MCPScan is just the beginning. On the roadmap: dynamic analysis with runtime monitoring, MCP registry scanning, a policy engine for organisational rules, VS Code integration, and community detection rules.

MCPScan is open source and MIT licensed. Star the repo on GitHub, try it on your configs, and open issues for anything we've missed.

The MCP ecosystem is moving fast. Security tooling needs to move faster. MCPScan is our contribution to making that happen.

Want to secure your MCP infrastructure?