MCP-Lattice - Security scanner for Model Context Protocol (MCP)

项目说明

MCP-Lattice

Open-source MCP security scanner with capability graph analysis.

![Go Report Card]()
![Release]()

The Problem

The Model Context Protocol (MCP) ecosystem has grown to over 10,000 servers, yet there is no comprehensi tool to audit them. At least 25 CVEs and disclosure reports ha across tool poisoning, prompt injection, SSRF, and auth bypass classes. Existing scanners cover only a fraction of the attack surface and none analyze cross-ser chains. MCP-Lattice fills that gap.

What MCP-Lattice Does

Quick Start

Install

Or download a prebuilt binary from the releases page.

Run

What It Finds

Capability Graph Analysis

MCP-Lattice builds a capability graph across all configured MCP servers, modeling what each tool can read, write, execute, and transmit. It then searches for cross-ser chains -- for example, a filesystem-read tool on one ser with an HTTP-send tool on another creates an exfiltration path. This is the key differentiator: no other scanner detects multi-ser combinations.

Results

We attempted to scan 100 MCP servers from the npm registry (75 scanned successfully, 25 timed out):

| Metric | Value |
| --- | --- |
| Total findings | 1,275 (759 Critical, 505 High, 11 Medium) |
| Cross-ser chains | 1,082 (84.9% of findings) |
| Servers with findings | 34 of 75 scanned |
| Most affected servers | browser-de (150), Heroku (116), Notion (94), CircleCI (89) |

Full methodology and reproduction scripts are in the research/ directory.

Contributing

We welcome contributions -- especially new detection templates, which are the easiest way to get started.

Documentation

License

Apache License 2.0. See LICENSE for the full text.

项目信息

开发语言：Go

Star 数：9

技术要点

该项目属于安全软件方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕 Security scanner for Model Context Protocol (MCP) with capability graph analysis. Detects emergent attack chains across multi-server AI agent deployments that no individual tool scan can find.展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。