Vorim AI — MCP Server

smithery badge

Give every AI agent its own cryptographic identity, scoped permissions, and a tamper-evident audit trail — directly from Claude Desktop, Cursor, or any MCP-compatible client.

What is Vorim AI?

Vorim AI is the identity and trust layer for autonomous AI agents. It gives each agent its own Ed25519 keypair, time-bounded scoped permissions, hash-linked audit events, and a publicly verifiable trust score — so when an agent does something, you can prove who acted, what they were allowed to do, and what happened.

The protocol underneath (VAIP) is open, MIT-licensed, and submitted to IETF as draft-nyantakyi-vaip-agent-identity-01.

This package is the MCP (Model Context Protocol) server that exposes 19 Vorim tools to any MCP-compatible AI client.

Works with Claude Desktop, Cursor, VS Code, Google Antigravity, and any other MCP client.

Quick Start

npm install -g @vorim/mcp-server

Or run directly with npx:

VORIM_API_KEY=agid_sk_live_... npx @vorim/mcp-server

Configuration

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "vorim": {
      "command": "npx",
      "args": ["@vorim/mcp-server"],
      "env": {
        "VORIM_API_KEY": "agid_sk_live_..."
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "vorim": {
      "command": "npx",
      "args": ["@vorim/mcp-server"],
      "env": {
        "VORIM_API_KEY": "agid_sk_live_..."
      }
    }
  }
}

VS Code

Add to your VS Code MCP settings with the same format.

Google Antigravity

Add to the workspace config at .agents/mcp_config.json, or the global config at ~/.gemini/config/mcp_config.json:

{
  "mcpServers": {
    "vorim": {
      "command": "npx",
      "args": ["@vorim/mcp-server"],
      "env": {
        "VORIM_API_KEY": "agid_sk_live_..."
      }
    }
  }
}

You can also add it from the UI: Settings → Customizations → Installed MCP Servers → Add MCP.

Get an API Key

1. Sign up at vorim.ai (free, no credit card)
2. Go to Settings > API Keys
3. Create a key with agents:*, audit:*, trust:* scopes

Available Tools (19)

Health

Agent Identity

Permissions

Credential Delegation

Audit

Trust

Onboarding

Example Usage

Once configured, use natural language in Claude, Cursor, or any MCP client:

• "Register an agent called invoice-processor with read and execute permissions"
• "Check if agent agid_acme_a1b2 has permission to execute"
• "Log a tool_call event for the agent: action=process_invoice, result=success"
• "What's the trust score for agent agid_acme_a1b2?"
• "Export the audit trail for the last 30 days"
• "Delegate my GitHub OAuth token to this agent for 24 hours"
• "Revoke agent agid_acme_a1b2"

Why Use Vorim AI

• Cryptographic identity — Ed25519 keypairs for every agent. Not a shared service account.
• Fine-grained permissions — 7 scopes with time bounds and rate limits, sub-5ms checks.
• Tamper-evident audit trails — SHA-256 hash-linked events, signed export bundles for compliance.
• Public trust scoring — anyone can verify any agent without auth (no shared secrets).
• Open protocol — VAIP submitted to IETF, MIT-licensed, freely implementable.
• Compliance-ready — EU AI Act, US Executive Order 14110, SOC 2, GDPR.

Environment Variables

Links

• Platform: vorim.ai
• API Docs: vorim.ai/docs
• Protocol Spec (VAIP): github.com/Vorim-AI-Labs/vorim-protocol
• TypeScript SDK: @vorim/sdk on npm
• Python SDK: vorim on PyPI
• OpenClaw Skill: Vorim-AI-Labs/vorim-openclaw-skill
• Agent Discovery: vorim.ai/.well-known/agent.json

License

MIT — see LICENSE for details.

Built by Vorim AI. Questions or feedback: kwame@vorim.ai.