The first behavioral grade for an MCP server is now onchain.
@polygraphso grades how a server actually behaves — does it try to hijack the caller, phone home, or leak planted data? — and writes the result as an EAS attestation on Base. 🧵
GoodBuilders Season 4 applications are LIVE 🎉
$50,000 + in G$ streaming funding via @flowstatecoop for builders creating real G$ utility on @Celo
⚒️ Build products
👥 Reach real users
💙 Grow the G$ ecosystem
👉 Apply now: ubi.gd/applyS4
While @TalentProtocol tracks GitHub commits and onchain activity, we evaluate your app idea, functionality, UX, and MiniPay fit.
If you built, shipped, and reached real users in the past weeks, Proof of Ship is for you!
Proof of Ship submissions close on Monday, June 22nd at 23h59 GMT.
Before the Leaderboard locks on @TalentProtocol, here's your final checklist to make sure your project is in its best shape ↓
We're co-hosting with @posthog an evening of honest, practical conversation about what it actually means to be a Product Engineer.
This has been a recurring discussion topic between CTOs and we're going to explore it further in person, over food and drinks in Lisbon!
A selected
Top @base Projects to Watch This Week
1. @legionagent by @trynullsec - agent swarm that plans, builds, scans, and ships software with signature-gated execution.
2. @cybercentry - co-author of ERC-8126 and ERC-8196, building verification rails for agent identity, risk, and
I gave @polygraphso a try and tested my own @productclank agent skill.
It basically grades my skill so other devs can have confidence when using it. And it did find some critical gaps I had (and resolved) in a quick session with CC
Your agent runs skills you've never vetted. You asked us to grade them — now you can.
An open, deterministic scan: injection, exfil, dangerous bundled commands → A–F. Don't trust the grade — re-run it and get the same letter.
We have spent years building reputation systems for builders: turning projects, contributions, and verified signals into something people can trust. Polygraph.so applies that same instinct to the agentic web.
The product is still early, and the grading system has a
AI agents need to know which tools they can trust before installing them.
We test third-party AI tools for hijacking, permission overreach, and data leaks.
Then we publish a public A to F grade with evidence attached.
Open-source work, supported by $POLYGRAPH fees from the
Reputation for builders was the first chapter.
Reputation for agents is next.
@polygraphso is our first step: test agent behavior and calculate a polygraph score.
Shipping next: verifiable polygraph score with TEEs + onchain attestations on @base.
Know more on:
We built this Polygraph litmus test for AI agents during the @base and @privy_io hackathon today at NYC.
The idea is simple: don’t trust an MCP server just because it looks useful. Test how it first.
Reputation for AI agents starts with verifiable behavior.
Here's your monthly housekeeping moment with @0x_leal and @pcbo.
[NEW] Opportunities – New way to get builder attention
[SOON] Agentic reputation – launching on @base x @privy_io NYC hackathon
[NEXT MONTH] Built-in USDC Rewards for Talent+ members
🏆 May's Proof of Ship Leaderboard is out on @TalentProtocol!
Are you among the Top 50 projects that will get a share of the 5K USD₮ prize pool? Discover now ↓
