# Agent Identity MCP Server

MCP Server for AI agent identity and authorization. Create, verify, and manage agent identities with trust scores and scoped authorization tokens.

## Features

- **Agent Identities** — Create and manage unique agent identities with capabilities
- **Trust Scores** — Automatic trust scoring based on agent behavior history
- **Authorization Tokens** — Scoped, time-limited authorization for specific actions
- **Auto-Approval** — High-trust agents get automatic authorization for known capabilities
- **Identity Revocation** — Revoke compromised or misbehaving agent identities

## Installation

```bash
pip install agent-identity-mcp-server
```

## Usage with Claude Code

Add to your `.mcp.json`:

```json
{
  "mcpServers": {
    "agent-identity": {
      "command": "uvx",
      "args": ["agent-identity-mcp-server"]
    }
  }
}
```

## Tools

| Tool | Description |
|------|-------------|
| `create_agent_identity` | Create a new agent identity with name, owner, capabilities |
| `get_identity` | Look up an agent's identity and trust score |
| `authorize_action` | Request authorization for a specific action |
| `verify_authorization` | Verify if an authorization token is valid |
| `list_identities` | List all registered agent identities |
| `revoke_identity` | Revoke an agent's identity |

## Trust Score System

Trust scores range from 0.0 to 1.0 and are calculated from the agent's last 50 actions:

| Score | Level | Auto-Approve |
|-------|-------|--------------|
| 0.9+ | High | Yes |
| 0.7+ | Good | No |
| 0.5+ | Neutral | No |
| 0.3+ | Low | No |
| <0.3 | Critical | No |

## Authorization Flow

1. `create_agent_identity` — Register the agent
2. `authorize_action` — Request permission for an action
3. `verify_authorization` — Verify the token before executing
4. Trust score updates automatically based on activity

## Data Storage

All identity data is stored locally in SQLite at `~/.agent-identity/identities.db`.


---

## More MCP Servers by AiAgentKarl

| Category | Servers |
|----------|---------|
| 🔗 Blockchain | [Solana](https://github.com/AiAgentKarl/solana-mcp-server) |
| 🌍 Data | [Weather](https://github.com/AiAgentKarl/weather-mcp-server) · [Germany](https://github.com/AiAgentKarl/germany-mcp-server) · [Agriculture](https://github.com/AiAgentKarl/agriculture-mcp-server) · [Space](https://github.com/AiAgentKarl/space-mcp-server) · [Aviation](https://github.com/AiAgentKarl/aviation-mcp-server) · [EU Companies](https://github.com/AiAgentKarl/eu-company-mcp-server) |
| 🔒 Security | [Cybersecurity](https://github.com/AiAgentKarl/cybersecurity-mcp-server) · [Policy Gateway](https://github.com/AiAgentKarl/agent-policy-gateway-mcp) · [Audit Trail](https://github.com/AiAgentKarl/agent-audit-trail-mcp) |
| 🤖 Agent Infra | [Memory](https://github.com/AiAgentKarl/agent-memory-mcp-server) · [Directory](https://github.com/AiAgentKarl/agent-directory-mcp-server) · [Hub](https://github.com/AiAgentKarl/mcp-appstore-server) · [Reputation](https://github.com/AiAgentKarl/agent-reputation-mcp-server) |
| 🔬 Research | [Academic](https://github.com/AiAgentKarl/crossref-academic-mcp-server) · [LLM Benchmark](https://github.com/AiAgentKarl/llm-benchmark-mcp-server) · [Legal](https://github.com/AiAgentKarl/legal-court-mcp-server) |

[→ Full catalog (40+ servers)](https://github.com/AiAgentKarl)

## License

MIT