Home

MCPShield

AI Agent Security Platform — Discover, monitor, and risk-score MCP servers across your organization.

What is MCPShield?

As AI tools (Claude, Cursor, Windsurf, ChatGPT) increasingly rely on MCP (Model Context Protocol) servers to access filesystems, databases, shells, and APIs, the attack surface they expose grows silently. MCPShield gives you visibility: a lightweight Python agent scans MCP configurations on developer machines, scores each server for risk, and reports into a centralized multi-tenant dashboard.

Features

Feature	Description
Automatic Discovery	Scans Claude Desktop, Cursor, Windsurf, and custom MCP configs on Windows, macOS, and Linux
Risk Scoring Engine	Weighted 0–100 score across shell access, filesystem writes, credential exposure, network calls
Real-time Alerts	Fires on new high-risk servers and on score increases > 10 points
Centralized Dashboard	Org-wide risk distribution, top-risk servers, per-agent heartbeat, and alert history
Multi-tenant	Full data isolation — users, agents, servers, and alerts are scoped per organization
Privacy-first	Environment variable names only — credential values are never captured

Architecture

flowchart LR
    subgraph dev["Developer Endpoints"]
        direction TB
        W[Windows]
        M[macOS]
        L[Linux]
    end

    subgraph agent["mcpshield-agent"]
        direction TB
        S1[Discover MCP configs]
        S2[Score risk 0–100]
        S3[Report via API key]
        S1 --> S2 --> S3
    end

    subgraph backend["MCPShield Backend  •  FastAPI"]
        direction TB
        B1[Risk engine]
        B2[Alert generator]
        B3[(PostgreSQL)]
        B1 --> B2 --> B3
    end

    subgraph ui["Security Dashboard  •  Next.js"]
        direction TB
        U1[Risk overview]
        U2[Alerts]
        U3[Agent status]
    end

    dev -->|pip install + scan| agent
    agent -->|X-API-Key| backend
    backend -->|JWT| ui

Loading

Quick Links

• Installation — Get MCPShield running
• Quick-Start — 5-minute walkthrough
• Agent-Usage — All CLI commands
• Risk-Scoring — How scores are calculated
• API-Reference — REST API reference
• Architecture — System design and data flow

Tech Stack

Component	Technology
Backend	FastAPI, SQLAlchemy 2.0, Alembic, PostgreSQL
Frontend	Next.js 14 App Router, React 18, Tailwind CSS
Agent	Python 3.11+, Click CLI, psutil
Auth	HS256 JWT (30 min access / 7 day refresh), bcrypt, SHA-256 API key hashing