MCP server · Security

HVTracker MCP server

Check if an AI agent, framework, or MCP server is trustworthy before you connect to it.

Security For it and development Security

HVTracker MCP is a helper that lets your AI look up trust information about AI agents, frameworks, and MCP servers before you connect to them. It pulls together public signals like package history, signed commits, and security advisories into a simple score and verdict. It is handy for anyone who is about to install or connect to an AI tool and wants a quick sanity check first.

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 an outside service. This one connects your AI to HVTracker, a public registry that keeps trust information about AI agents and MCP servers. Once connected, your AI can ask HVTracker questions for you and bring back the answers in the chat.

What this MCP server does

You ask your AI something like whether a certain MCP server is safe to connect to. Your AI passes that question to the HVTracker helper. The helper looks up public trust data about that server, package, or agent on hvtracker.net. It sends back a trust score, a verdict, and the evidence behind them. You see the result right in your chat, without leaving your conversation.

What you can do with it

Check the trust verdict for an MCP server before you connect to it
Look up the trust profile of an AI agent or framework
Compare two agents side by side with an evidence-based verdict
Search the HVTracker registry by name, repo, description, or category
Scan a whole requirements.txt, package.json, or MCP client config at once
See the top-ranked AI agents and MCP servers by trust score
Check whether an agent's trust score is improving or declining over 90 days

Try asking your AI

“Is the MCP server called filesystem safe to connect to?”
“Compare LangChain and CrewAI for me on trust.”
“Scan this requirements.txt and tell me which packages look risky.”
“Show me the top AI agents in the security category.”

What it gives back to you

You get back a trust score, a grade, and a short verdict for whatever you asked about. For a stack scan, you get one verdict per item plus a summary of the whole set. For comparisons, you get both agents side by side with the evidence behind the call. It can also give you a link to the full compare page or the agent's trust history.

Before you start

What you need

An MCP client that supports remote servers, like Claude Desktop or another MCP-compatible app
Nothing else: no API key and no account are required for the hosted server

Good to know

It only reads public trust data and does not change anything on your system, but the scores are based on public signals and are not a guarantee that a tool is safe.

Install it with your AI

Add HVTracker 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 HVTracker 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 4,609 MCP servers here for you.