{
  "markdown": "# Vorim AI — MCP Server\n\n[![npm version](https://img.shields.io/npm/v/@vorim/mcp-server.svg)](https://www.npmjs.com/package/@vorim/mcp-server)\n[![smithery badge](https://smithery.ai/badge/vorimai/vorim)](https://smithery.ai/servers/vorimai/vorim)\n[![MIT License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n\n> 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.\n\n## What is Vorim AI?\n\nVorim 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.\n\nThe protocol underneath (VAIP) is open, MIT-licensed, and submitted to IETF as `draft-nyantakyi-vaip-agent-identity-01`.\n\nThis package is the **MCP (Model Context Protocol) server** that exposes 19 Vorim tools to any MCP-compatible AI client.\n\nWorks with **Claude Desktop**, **Cursor**, **VS Code**, **Google Antigravity**, and any other MCP client.\n\n## Quick Start\n\n```bash\nnpm install -g @vorim/mcp-server\n```\n\nOr run directly with npx:\n\n```bash\nVORIM_API_KEY=agid_sk_live_... npx @vorim/mcp-server\n```\n\n## Configuration\n\n### Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"vorim\": {\n      \"command\": \"npx\",\n      \"args\": [\"@vorim/mcp-server\"],\n      \"env\": {\n        \"VORIM_API_KEY\": \"agid_sk_live_...\"\n      }\n    }\n  }\n}\n```\n\n### Cursor\n\nAdd to `.cursor/mcp.json` in your project root:\n\n```json\n{\n  \"mcpServers\": {\n    \"vorim\": {\n      \"command\": \"npx\",\n      \"args\": [\"@vorim/mcp-server\"],\n      \"env\": {\n        \"VORIM_API_KEY\": \"agid_sk_live_...\"\n      }\n    }\n  }\n}\n```\n\n### VS Code\n\nAdd to your VS Code MCP settings with the same format.\n\n### Google Antigravity\n\nAdd to the workspace config at `.agents/mcp_config.json`, or the global config at `~/.gemini/config/mcp_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"vorim\": {\n      \"command\": \"npx\",\n      \"args\": [\"@vorim/mcp-server\"],\n      \"env\": {\n        \"VORIM_API_KEY\": \"agid_sk_live_...\"\n      }\n    }\n  }\n}\n```\n\nYou can also add it from the UI: Settings → Customizations → Installed MCP Servers → Add MCP.\n\n## Get an API Key\n\n1. Sign up at [vorim.ai](https://vorim.ai) (free, no credit card)\n2. Go to **Settings > API Keys**\n3. Create a key with `agents:*`, `audit:*`, `trust:*` scopes\n\n## Available Tools (19)\n\n### Health\n| Tool | Description |\n|------|-------------|\n| `vorim_ping` | Check API health and connectivity |\n\n### Agent Identity\n| Tool | Description |\n|------|-------------|\n| `vorim_register_agent` | Register a new agent with Ed25519 cryptographic identity |\n| `vorim_register_ephemeral` | Register a `did:key` ephemeral agent with TTL |\n| `vorim_get_agent` | Get agent details by ID |\n| `vorim_list_agents` | List all agents with pagination and filtering |\n| `vorim_update_agent` | Update agent metadata (name, description, status) |\n| `vorim_revoke_agent` | Permanently revoke an agent |\n\n### Permissions\n| Tool | Description |\n|------|-------------|\n| `vorim_check_permission` | Check if agent has a permission scope (sub-5ms) |\n| `vorim_grant_permission` | Grant a permission with optional expiry and rate limits |\n| `vorim_list_permissions` | List all active permissions for an agent |\n| `vorim_revoke_permission` | Revoke a specific permission scope |\n\n### Credential Delegation\n| Tool | Description |\n|------|-------------|\n| `vorim_delegate_credential` | Delegate OAuth credentials to an agent |\n| `vorim_request_token` | Agent requests a short-lived access token |\n| `vorim_list_delegations` | List active credential delegations |\n\n### Audit\n| Tool | Description |\n|------|-------------|\n| `vorim_emit_event` | Log an audit event for an agent action |\n| `vorim_export_audit` | Export signed audit bundle with SHA-256 manifest |\n\n### Trust\n| Tool | Description |\n|------|-------------|\n| `vorim_verify_trust` | Verify agent trust score (public, no auth required) |\n\n### Onboarding\n| Tool | Description |\n|------|-------------|\n| `vorim_onboard_start` | Start device-authorization onboarding for a user with no API key; returns a user code and activation URL |\n| `vorim_onboard_check` | Check whether the user approved onboarding and retrieve the issued API key |\n\n## Example Usage\n\nOnce configured, use natural language in Claude, Cursor, or any MCP client:\n\n- *\"Register an agent called invoice-processor with read and execute permissions\"*\n- *\"Check if agent agid_acme_a1b2 has permission to execute\"*\n- *\"Log a tool_call event for the agent: action=process_invoice, result=success\"*\n- *\"What's the trust score for agent agid_acme_a1b2?\"*\n- *\"Export the audit trail for the last 30 days\"*\n- *\"Delegate my GitHub OAuth token to this agent for 24 hours\"*\n- *\"Revoke agent agid_acme_a1b2\"*\n\n## Why Use Vorim AI\n\n- **Cryptographic identity** — Ed25519 keypairs for every agent. Not a shared service account.\n- **Fine-grained permissions** — 7 scopes with time bounds and rate limits, sub-5ms checks.\n- **Tamper-evident audit trails** — SHA-256 hash-linked events, signed export bundles for compliance.\n- **Public trust scoring** — anyone can verify any agent without auth (no shared secrets).\n- **Open protocol** — VAIP submitted to IETF, MIT-licensed, freely implementable.\n- **Compliance-ready** — EU AI Act, US Executive Order 14110, SOC 2, GDPR.\n\n## Environment Variables\n\n| Variable | Required | Default | Description |\n|----------|----------|---------|-------------|\n| `VORIM_API_KEY` | Yes | — | Your Vorim API key (`agid_sk_live_...`) |\n| `VORIM_BASE_URL` | No | `https://api.vorim.ai` | API base URL (override for self-hosted) |\n\n## Links\n\n- **Platform:** [vorim.ai](https://vorim.ai)\n- **API Docs:** [vorim.ai/docs](https://vorim.ai/docs)\n- **Protocol Spec (VAIP):** [github.com/Vorim-AI-Labs/vorim-protocol](https://github.com/Vorim-AI-Labs/vorim-protocol)\n- **TypeScript SDK:** [@vorim/sdk on npm](https://www.npmjs.com/package/@vorim/sdk)\n- **Python SDK:** [vorim on PyPI](https://pypi.org/project/vorim/)\n- **OpenClaw Skill:** [Vorim-AI-Labs/vorim-openclaw-skill](https://github.com/Vorim-AI-Labs/vorim-openclaw-skill)\n- **Agent Discovery:** [vorim.ai/.well-known/agent.json](https://vorim.ai/.well-known/agent.json)\n\n## License\n\nMIT — see [LICENSE](LICENSE) for details.\n\n---\n\nBuilt by [Vorim AI](https://vorim.ai). Questions or feedback: [kwame@vorim.ai](mailto:kwame@vorim.ai).\n",
  "bytes": 6604,
  "sha": "c75b6a8aec768eeec734a806d00ae0901167ec6832203215d92ace38db6e4306",
  "repo_slug": "kzino/vorim-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_kzino_vorim_mcp_server_54046cda/readme"
}