01Ai 01Protocol Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited 01Ai 01Protocol Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Portable, cryptographically verifiable AI agent identity.
This repository contains the canonical public distribution packages for 01 Protocol.
@01protocol/sdk (packages/sdk): TypeScript/JavaScript SDK for creating, verifying, and evolving .01ai identities.@01protocol/mcp-server (packages/mcp-server): MCP server exposing agent identity tools to Claude Desktop and other MCP clients.protocol-01 (python-sdk): Python SDK.# SDK
npm install @01protocol/sdk
# MCP server (Claude Desktop / any MCP client)
npx @01protocol/mcp-serverAdd to your claude_desktop_config.json:
{
"mcpServers": {
"01protocol": {
"command": "npx",
"args": ["-y", "@01protocol/mcp-server"],
"env": {
"AGENT_VAULT_DIR": "/Users/you/.01protocol/agents"
}
}
}
}Config file locations:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsongithub-docs/spec/Contribution docs will be added at root (CONTRIBUTING.md). For now, open issues or PRs with reproducible examples.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.