MCP server · Security
HallucC MCP server
by fredyee
Let your AI fact-check claims, check its own answers, and screen risky computer actions before they happen.
HallucC is a helper that gives your AI a fact-checker and a safety checker. When you ask it to look over a piece of writing, an AI answer, or a list of computer actions, it checks them claim by claim and tells you what looks solid and what does not. It is handy for anyone who uses AI for research, writing, or letting an AI agent click around on a computer.
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 HallucC, a checking service, so the AI can send text or actions there and get back a verdict. You just ask in normal words, and the AI quietly uses this helper behind the scenes.
What this MCP server does
You ask your AI to check something, like a paragraph, an AI-written answer, or a list of steps an automated agent wants to take. Your AI passes that to the HallucC helper, which sends it to the HallucC service. The service looks at each claim or action one by one and decides how risky or shaky it is. Then it sends back a colour-coded summary, reasons, and links to sources, and your AI shows you the result in the chat.
Click to zoomWhat you can do with it
- Fact-check a piece of text claim by claim and see which parts are shaky
- Check an AI agent's final answer and how it got there
- Rate computer-use actions from low to high risk before they run
- Scan an AI agent's source code for dangerous patterns
- Screen a prompt for injection or jailbreak attempts
- Spot personal information or fraud wording in text
- See which sources back up each claim
Try asking your AI
- “Check this paragraph for claims that might be wrong and show me the sources”
- “Look at my AI agent's final report and tell me if it stayed on task”
- “Rate these browser actions for risk before my agent runs them”
- “Scan this prompt for injection or jailbreak attempts”
What it gives back to you
You get a short summary with red, yellow, and green marks, plus a line for each claim or action showing its status, a confidence level, a short reason, and often a link to a source. For agent actions you also get a risk level from L0 to L3 and a note when something looks like it should wait for you. It all appears right in your chat as text you can read and copy.
Before you start
What you need
- A HallucC account and API key (a kind of password for apps, free to create at aihcc.cloud)
- An AI app that supports MCP servers, like Claude Code, Cursor, or Claude Desktop
- For the npx option: Node.js installed on your computer
Good to know
The checking tools use your free daily quota, so heavy use can run it out, and the risk ratings are guidance rather than a guarantee, so still review anything important yourself.
Install it with your AI
Add HallucC 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 HallucC 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
People who use AI for research, writing, or running AI agents and want a quick sanity check on facts and risky actions.
