Vorim AISAFE
MCP server for Vorim AI — AI agent identity, permissions, and audit trails. 19 tools for Claude, OpenAI, Cursor, VS Code, and any MCP-compatible client.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/@vorim/mcp-server) [](https://smithery.ai/servers/vorimai/vorim) [](LICENSE)
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
0bb7db3e87a3OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server --env VORIM_API_KEY=${VORIM_API_KEY} -- npx -y @vorim/[email protected]Exposed tools (19)
15 read · 2 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
vorim_check_permission | read | |
vorim_delegate_credential | read | |
vorim_emit_event | read | |
vorim_export_audit | read | |
vorim_get_agent | read | |
vorim_grant_permission | read | |
vorim_list_agents | read | |
vorim_list_delegations | read | |
vorim_list_permissions | read | |
vorim_onboard_check | read | |
vorim_onboard_start | write | |
vorim_ping | read | |
vorim_register_agent | read | |
vorim_register_ephemeral | read | |
vorim_request_token | read | |
vorim_revoke_agent | destructive | |
vorim_revoke_permission | destructive | |
vorim_update_agent | write | |
vorim_verify_trust | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
vorim_revoke_agent, vorim_revoke_permission
@modelcontextprotocol/sdk, zod, @types/node, tsx, typescript
Gates applied: no_behavioural_pass.
0bb7db3e87a3full audit observations/trust-audit/mcp-server/vorim-ai-labs__vorim-ai-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 0bb7db3e87a3 | SAFE | B | 89 | first audit |
Questions
What is the Vorim AI MCP server?
MCP server for Vorim AI — AI agent identity, permissions, and audit trails. 19 tools for Claude, OpenAI, Cursor, VS Code, and any MCP-compatible client.
What tools does Vorim AI expose?
19 in total: 15 read-only, 2 that write, and 2 that can delete or overwrite (vorim_revoke_agent, vorim_revoke_permission). Every one is listed on this page with its risk.
Is Vorim AI safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Vorim AI need?
It reads VORIM_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Vorim AI run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @vorim/mcp-server at 1.1.15.
How current is this page?
The grade is for one exact copy of the source (0bb7db3e87a3), read on 2026-10-08. The repository is watched and re-audited when it changes.