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. 🧵
New @polygraphso feature
you check your npm deps for known CVEs. but the MCP servers you wire into an agent - tools that can read files, move money, reach the network - usually get zero behavioral review. so we shipped a github action that fails the build when one grades D or F.
New: @polygraphso is on PulseMCP.
Grade any MCP server A–F on how it behaves — tool-output injection, egress, data-leak — before your agent trusts it. Open and reproducible.
Just ran @polygraphso on its own MCP server: grade A.
All four behavioural checks pass — no tool-output injection, no egress overreach, no leaked canaries, stable under adversarial input. litmus-v5, Docker sandbox active.
It's the open engine, so re-run it and check us.
To reinforce our long-term commitment to building Polygraph and to Polygraphers, our team bought $15K of $POLYGRAPH and locked it for 6 months.
This is not a fix for everything, but it’s a clear step: more skin in the game, locked publicly.
Here's the sablier vesting lock tx: basescan.org/tx/0x476e33bcf…
Following very useful advice from the Bankr team, I've locked up all 2.73B $POLYGRAPH tokens for 6 months.
Used Sablier to do this, there's the vesting creation tx.
basescan.org/tx/0x7d80266e8…
$POLYGRAPH is building an open source AI security grader that tests tools & agents for:
• Prompt hijacking
• Permission abuse
• Data leaks
Current progress:
✅ Polygraph live with the litmus v2 testing harness
✅ CLI live
✅ Public grades already published for select MCP servers
✅ Onchain funding mechanism active
Next
→ More public grades for GitHub, Slack & filesystem tools
→ Onchain verifiable grades using TEEs
→ BankrBot skill integration
→ Expansion beyond MCP into broader AI tooling
As AI agents gain access to real permissions, security verification becomes infrastructure
$POLYGRAPH is positioning itself as the trust layer
@pcbo
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 @bankrbot community.
Thank you to everyone making this possible.
The @bankrbot community launched $POLYGRAPH.
Today, its trading fees started funding @polygraphso – an open-source grading framework for AI tools.
The Bankr funding loop is simple:
1. Community launches token
2. Project earns fees
3. Fees fund open-source AI infra
CA:
295 Followers 6K Following"Empty your mind. Be formless, shapeless like water. Pour into cup, it becomes cup; bottle, bottle; teapot, teapot. Water can flow or crash. Be water, my friend
587 Followers 2K FollowingCrypto recharger. Meme trader. Video editor. I read the culture, ride the wave & cut the content. Early in. Always learning. Never stopping.
2K Followers 6K FollowingSeed Altar Coin is more than a token — it is a spiritual flame, a digital offering, and a gift of connection. Each coin carries the essence of planting.
179 Followers 2K FollowingCrafting the sub agent routing infrastructure for OSIRIS.
Maximizing autonomous execution speed and decentralized swarm coordination.
Gamers 4 Life !
7K Followers 6K FollowingCrypto enthusiast || Trader || $eth maxi || Memecoin Degen || Big supporter of @Otonomos || DM always open for collabs || Head of markets !
3K Followers 7K FollowingActive crypto enthusiast primarily focused on promoting and participating in various blockchain projects, particularly those related to Aptos, Monad, and NFTs.
109K Followers 28 FollowingBuilding financial infra for agents to fund themselves. Launch a token, trading fees pay for API costs. Wallets, tools, treasury automation.