M8ven Verification
Transparency is what makes a trust score credible. Here is exactly what we check, how we score, and what we cannot detect.
We parse the MCP server's tool manifest — what tools it declares, what input fields each tool asks for, and what permission hints it sets.
We inspect the MCP's published source and compare what the code does against what the tool descriptions claim. The goal is to catch the gap between declared capability and actual behavior.
Beyond security, we check whether the repo follows basic engineering practices.
npm test actually passesWhen you embed our badge, every load checks the latest commit on the linked repo against the verified version. If the code has changed, the badge automatically updates to show a stale state.
Every check contributes to a 0-100 trust score. Failures subtract more than warnings. Annotation dishonesty (tools claiming read-only but containing write operations) and hardcoded secrets are weighted heaviest.
A high score does not guarantee security. Verification narrows the unknowns — it doesn't eliminate them. Here's what stays beyond reach, and why we list it anyway: naming the limits is what makes the score mean anything.
Code that behaves normally for N days before activating malicious behavior.
Malicious code that only activates on specific operating systems, credential patterns, or data inputs.
If the agent calls a backend API, we can see the call but not what the server does with the data once it arrives.
We flag obfuscated code as a red flag in itself, but cannot always deobfuscate.
Without source code we can only verify what is observable from outside (publisher identity, tool list, metadata).
An agent that uses its declared permissions in ways the user did not intend.
Verification isn't a one-time label. We're working toward keeping every entry current as code, behavior, and publisher claims evolve over time — so a Verified badge reflects the MCP as it stands today, not the day it was first checked.