MCP server · Security
Inkog MCP server
by inkog-io
Your AI can scan agent code for security risks and explain the findings in plain English.
Inkog is a helper that checks the AI agents you build for security problems while you are still working on them. You ask your AI assistant to scan your code, and Inkog looks for things like infinite loops, prompt injection, and missing human oversight. It is handy if you build agents and want a second pair of eyes without leaving your chat.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another service. This one connects your AI to Inkog, a security checking service for AI agents. Once connected, your AI can send your code to Inkog and bring back the results in the same conversation.
What this MCP server does
You ask your AI to scan a folder or file where your agent code lives. Your AI passes that request to the Inkog helper. The helper sends your code to Inkog's online service, which looks for common AI agent problems like loops that never stop, prompt injection paths, and missing guardrails. Inkog sends back a list of findings, and your AI shows them to you in the chat, often with a plain English explanation and a suggested fix. You can then ask your AI to apply the fix and scan again.
Click to zoomWhat you can do with it
- Scan your agent code for logic flaws and security risks
- Explain a finding in plain English and suggest how to fix it
- Check that your AGENTS.md governance notes match what the code actually does
- Generate a compliance report for frameworks like the EU AI Act, NIST, or OWASP
- Audit another MCP server before you install it
- Audit how multiple agents talk to each other for delegation problems
- Create a Machine Learning Bill of Materials listing your AI components
Try asking your AI
- “Scan the current directory with Inkog and show me any CRITICAL or HIGH findings.”
- “Explain the top finding in plain English. What is the risk, and how do I fix it?”
- “Verify my AGENTS.md against the code.”
- “Audit the agent-to-agent delegation in this crew.”
- “Run a compliance report and map the findings to EU AI Act Articles 12, 14, and 15.”
What it gives back to you
You get back a list of findings, each with a severity level and a short description. You can also ask for a longer explanation of a single finding, a compliance report in markdown or JSON, or a bill of materials listing your AI components. Everything shows up as text in your chat, so you can read it, copy it, or ask follow-up questions right away.
Before you start
What you need
- A free Inkog account at app.inkog.io
- An Inkog API key from your dashboard (a kind of password that starts with sk_live_)
- An MCP-compatible AI app like Claude Desktop, Cursor, or Claude Code
- Node.js installed on your computer so the npx command can run
Good to know
Your code is sent to Inkog's online service for analysis, so do not scan anything you are not allowed to share with a third party.
Install it with your AI
Add Inkog MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Inkog MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Developers and technical teams who build AI agents and want security checks and compliance reports without leaving their coding chat.
