Vorim AI — Agent Identity & Trust
Vorim AI — MCP Server
MCP (Model Context Protocol) server for Vorim AI — the identity and trust layer for AI agents. Exposes 13 tools for agent registration, permission checks, audit logging, and trust verification.
Works with Claude Desktop, Cursor, VS Code, and any MCP-compatible AI client.
Quick Start
npm install -g @vorim/mcp-serverOr run directly with npx:
VORIM_API_KEY=agid_sk_live_... npx @vorim/mcp-serverConfiguration
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.
Get an API Key
Sign up at vorim.ai (free)
Go to Settings > API Keys
Create a key with
agents:*,audit:*,trust:*scopes
Available Tools (13)
Health
Tool | Description |
| Check API health and connectivity |
Agent Identity
Tool | Description |
| Register a new agent with Ed25519 cryptographic identity |
| Get agent details by ID |
| List all agents with pagination and filtering |
| Update agent metadata (name, description, status) |
| Permanently revoke an agent |
Permissions
Tool | Description |
| Check if agent has a permission scope (sub-5ms) |
| Grant a permission with optional expiry and rate limits |
| List all active permissions for an agent |
| Revoke a specific permission scope |
Audit
Tool | Description |
| Log an audit event for an agent action |
| Export signed audit bundle with SHA-256 manifest |
Trust
Tool | Description |
| Verify agent trust score (public, no auth required) |
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"
"Revoke agent agid_acme_a1b2"
Environment Variables
Variable | Required | Default | Description |
| Yes | — | Your Vorim API key ( |
| No |
| API base URL (override for self-hosted) |
What is Vorim AI?
Vorim AI provides the identity and trust layer for autonomous AI agents:
Cryptographic Identity — Ed25519 keypairs for every agent
Fine-Grained Permissions — 7 scopes with time bounds and rate limits
Immutable Audit Trails — SHA-256 signed export bundles for compliance
Trust Scoring — 0-100 scores based on behavioural history
Compliance Ready — EU AI Act, US Executive Order 14110, SOC 2, GDPR
Links
Platform: vorim.ai
API Docs: vorim.ai/docs
Protocol Spec: github.com/Kzino/vorim-protocol
TypeScript SDK: @vorim/sdk on npm
Python SDK: vorim on PyPI
Agent Discovery: vorim.ai/.well-known/agent.json
License
MIT — see LICENSE for details.
Built by Vorim AI
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Kzino/vorim-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server