Skip to main content
Glama
Vorim AI — Agent Identity & Trust

Vorim AI — Agent Identity & Trust

Vorim AI — MCP Server

npm version MIT 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.

Related MCP server: aip-identity

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

Tool

Description

vorim_ping

Check API health and connectivity

Agent Identity

Tool

Description

vorim_register_agent

Register a new agent with Ed25519 cryptographic identity

vorim_register_ephemeral

Register a did:key ephemeral agent with TTL

vorim_get_agent

Get agent details by ID

vorim_list_agents

List all agents with pagination and filtering

vorim_update_agent

Update agent metadata (name, description, status)

vorim_revoke_agent

Permanently revoke an agent

Permissions

Tool

Description

vorim_check_permission

Check if agent has a permission scope (sub-5ms)

vorim_grant_permission

Grant a permission with optional expiry and rate limits

vorim_list_permissions

List all active permissions for an agent

vorim_revoke_permission

Revoke a specific permission scope

Credential Delegation

Tool

Description

vorim_delegate_credential

Delegate OAuth credentials to an agent

vorim_request_token

Agent requests a short-lived access token

vorim_list_delegations

List active credential delegations

Audit

Tool

Description

vorim_emit_event

Log an audit event for an agent action

vorim_export_audit

Export signed audit bundle with SHA-256 manifest

Trust

Tool

Description

vorim_verify_trust

Verify agent trust score (public, no auth required)

Onboarding

Tool

Description

vorim_onboard_start

Start device-authorization onboarding for a user with no API key; returns a user code and activation URL

vorim_onboard_check

Check whether the user approved onboarding and retrieve the issued API key

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

Variable

Required

Default

Description

VORIM_API_KEY

Yes

—

Your Vorim API key (agid_sk_live_...)

VORIM_BASE_URL

No

https://api.vorim.ai

API base URL (override for self-hosted)

License

MIT — see LICENSE for details.


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

Available Tools

17 tools
vorim_check_permissionA

Check if an agent has a specific permission scope. Returns allowed (boolean), reason if denied, and remaining quota. Sub-5ms via Redis cache.

Inputs: agent_id (required), scope (required).

vorim_delegate_credentialC

Delegate a credential to an agent. Creates a scoped delegation with optional rate limits and expiry.

Inputs: connection_id (required), agent_id (required), scopes_delegated (required), max_requests_per_hr, +1 more.

vorim_emit_eventB

Log an audit event for an agent action. Every agent action should be logged for compliance and traceability.

Inputs: agent_id (required), event_type (required), action (required), result (required), +4 more.

vorim_export_auditA

Export a signed audit bundle for a date range. Returns events with a SHA-256 manifest for tamper-proof verification.

Inputs: from (required), to (required).

vorim_get_agentA

Get details of a specific agent by agent_id. Returns name, status, trust score, capabilities, permissions, and metadata.

Inputs: agent_id (required).

vorim_grant_permissionC

Grant a permission scope to an agent. Optionally set expiry and rate limits.

Inputs: agent_id (required), scope (required), valid_until, rate_limit_max, +1 more.

vorim_list_agentsA

List all agents in the organisation. Supports pagination and filtering by status.

Inputs: page, per_page, status.

vorim_list_delegationsB

List credential delegations. Optionally filter by agent_id to see delegations for a specific agent.

Inputs: agent_id.

vorim_list_permissionsC

List all active permissions for an agent.

Inputs: agent_id (required).

vorim_pingA

Check Vorim AI API health and connectivity. Returns status, version, and service health.

Inputs: no named parameters.

vorim_register_agentA

Register a new AI agent with Vorim. Returns the agent identity (Ed25519 keypair, agent_id, trust score). The private key is shown once — store it securely.

Inputs: name (required), capabilities (required), scopes (required), description.

vorim_register_ephemeralC

Register an ephemeral agent with a did:key identity. Short-lived agents that auto-expire. Returns agent_id, did:key, and keypair.

Inputs: capabilities (required), scopes (required), ttl_seconds.

vorim_request_tokenC

Request a short-lived access token for an agent. Returns a scoped token for the specified provider.

Inputs: agent_id (required), scope (required), provider_id.

vorim_revoke_agentA

Permanently revoke an agent. This cannot be undone. The agent's identity will be deactivated and its trust score set to 0.

Inputs: agent_id (required).

vorim_revoke_permissionC

Revoke a specific permission scope from an agent.

Inputs: agent_id (required), scope (required).

vorim_update_agentC

Update an agent's metadata (name, description, status, capabilities).

Inputs: agent_id (required), name, description, status, +1 more.

vorim_verify_trustA

Verify an agent's identity and trust score. Public endpoint — no authentication required. Returns trust score (0-100), status, active scopes, and key fingerprint.

Inputs: agent_id (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 17 tools

    Disambiguation5/5

    Every tool has a clearly distinct purpose targeting specific operations in the agent identity and trust domain, such as checking permissions, delegating credentials, registering agents, or revoking access. There is no overlap in functionality, making it easy for an agent to select the correct tool without confusion.

    Naming Consistency5/5

    All tool names follow a consistent 'vorim_verb_noun' pattern with snake_case, such as vorim_check_permission, vorim_register_agent, and vorim_revoke_permission. This uniformity enhances readability and predictability across the entire toolset.

    Tool Count5/5

    With 17 tools, the server is well-scoped for managing agent identity and trust, covering essential operations like registration, permission management, auditing, and verification. Each tool serves a specific and necessary function, avoiding bloat or gaps.

    Completeness5/5

    The toolset provides complete CRUD and lifecycle coverage for the domain, including agent registration, updates, revocation, permission management, delegation, auditing, and trust verification. There are no obvious gaps, ensuring agents can handle all core workflows effectively.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      C
      quality
      B
      maintenance
      Cryptographic identity and trust protocol for AI agents. 38 MCP tools across 8 protocol layers: Ed25519 identity, delegation chains, values compliance, signed communication, policy engine, task coordination, cross-layer integration, and agentic commerce. 264 tests passing.
      154
      262 npm
      4
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      MCP server for AI agent identity — verify agents with Ed25519 signatures, check trust scores, sign and verify content, exchange encrypted messages. Built on the Agent Identity Protocol (AIP).
      8
      1
      MIT