Sandbox
Sign in
@Puliczek/awesome-mcp-security
Collections#Any agent#Security#Research

Awesome list of MCP security resources

This repository collects links about Model Context Protocol security, including official guidance, research papers, videos, writeups, and tooling. It is organized as a curated reference list rather than a runnable project, so you use it to find resources and examples quickly.

734 stars•233 forks•Updated 6mo ago
MCP Auth: The Future of AI Agent Security
Arcade • 3.1k views • 1 year ago

Videos about this repo

Who it's for

Builders who want to understand MCP security risks, defenses, and tools.

What it delivers

You can quickly find MCP security references and tools without searching across the web.

What it does

Security considerations

Summarizes official MCP security guidance, including input validation, access control, rate limiting, output sanitization, and human confirmation.

Curated research links

Lists papers, videos, and articles about MCP threats, authorization, prompt injection, and server abuse.

Tools and code

Points to scanners, gateways, monitoring tools, and vulnerable test servers for MCP security work.

MCP security servers

Collects MCP servers that connect to security tools like Semgrep, Burp Suite, VirusTotal, Shodan, and Nuclei.

README

🤝 Show your support - give a ⭐️ if you liked the content

Awesome MCP Security Awesome

Everything you need to know about Model Context Protocol (MCP) security.

Table of Contents

📔 Security Considerations

Official Security Considerations from the Official MCP Specification Rev: 2025-03-26

[!NOTE] 15.04.2025: The current MCP auth specification is in progress of being replaced by a more robust specification. Please join the conversation if you have concerns around the current auth specification.

  • Servers MUST:

    • Validate all tool inputs
    • Implement proper access controls
    • Rate limit tool invocations
    • Sanitize tool outputs

  • Clients SHOULD:

    • Prompt for user confirmation on sensitive operations
    • Show tool inputs to the user before calling the server, to avoid malicious or accidental data exfiltration
    • Validate tool results before passing to LLM
    • Implement timeouts for tool calls
    • Log tool usage for audit purposes

[!WARNING]
For trust & safety and security, clients MUST consider tool annotations to be untrusted unless they come from trusted servers.

[!WARNING]
For trust & safety and security, there SHOULD always be a human in the loop* with the ability to deny tool invocations.

Applications SHOULD:

  • Provide UI that makes clear which tools are being exposed to the AI model.
  • Insert clear visual indicators when tools are invoked.
  • Present confirmation prompts to the user for operations, to ensure a human is in the loop.

[!NOTE]
*Human-in-the-Loop (HITL) means that user help monitor and guide automated tasks, like deciding whether to accept tool requests in Cursor.

📃 Papers

📺 Videos

📕 Articles, X threads and Blog Posts

🧑‍🚀 Tools and code

💾 MCP Security Servers

💻 Other Useful Resources

😎 Contributing

👍🎉 First off, thanks for taking the time to contribute! 🎉👍

Please read and follow our contributing guide

Thanks! 🦄

🤝 Show your support

🤝 Show your support - give a ⭐️ if you liked the content

✔️ Disclaimer

This project can only be used for educational purposes. Using this resource against target systems without prior permission is illegal, and any damages from misuse of this software will not be the responsibility of the author.

Files in the repo

Repository payload•2 top-level entries
  • CONTRIBUTING.md
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More collections

VoltAgent/awesome-openclaw-skillsCollections

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

52k
phuryn/
pm-skills
phuryn/pm-skillsCollections

PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.

26k
asgeirtj/system_prompts_leaksCollections

Extracted system prompts from Anthropic - Claude Fable 5.1, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly.

65k
1 add