SchemaPin 🧷

Created By
ThirdKeyAIa year ago
A reference implementation of the SchemaPin protocol for cryptographically signing and verifying AI agent tool schemas to prevent supply-chain attacks.
Overview

What is SchemaPin?

SchemaPin is a cryptographic protocol designed to ensure the integrity and authenticity of tool schemas used by AI agents, preventing supply-chain attacks by allowing developers to cryptographically sign their schemas and enabling clients to verify their authenticity.

How to use SchemaPin?

Tool developers can sign their schemas using the provided Python or JavaScript libraries, while AI clients can verify these schemas by fetching the signature and public key, ensuring that the schemas have not been altered since publication.

Key features of SchemaPin?

  • Strong security with ECDSA P-256 signatures and SHA-256 hashing.
  • Cross-language support with implementations in Python and JavaScript.
  • Simple integration with high-level APIs for developers and clients.
  • Trust-On-First-Use (TOFU) key pinning to prevent key substitution attacks.
  • Compliance with RFC 8615 for public key discovery.

Use cases of SchemaPin?

  1. Signing and verifying AI tool schemas to prevent unauthorized modifications.
  2. Ensuring the integrity of schemas in AI applications to mitigate supply-chain risks.
  3. Facilitating secure communication between AI agents and their tools.

FAQ from SchemaPin?

  • Can SchemaPin be used with any AI tool?

Yes! SchemaPin is designed to work with any AI tool that requires schema verification.

  • Is SchemaPin open-source?

Yes! SchemaPin is available on GitHub under the MIT License.

  • How does SchemaPin enhance security?

By using cryptographic signatures and key pinning, SchemaPin ensures that only verified schemas are used, reducing the risk of supply-chain attacks.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
ThirdKeyAI
Star
1
Language
JavaScript
License
MIT license
Category
security

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago