# AgentGuard MCP server

> Provides a spending firewall for AI agents on NEAR using on-chain limits, human approval, and a TEE-based risk oracle to prevent unauthorized payments.

- Repository: https://github.com/CodeMasterLabs/agentguard
- Page: https://hostedmcp.org/servers/codemasterlabs/agentguard
- Transport: —
- Stars: 0
- License: MIT

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `AGENTGUARD_CONTRACT` | no | no |  |
| `AGENTGUARD_ORACLE_URL` | no | no |  |
| `AGENTGUARD_VAULT_ID` | no | no |  |
| `AGENT_ACCOUNT_ID` | no | no |  |
| `AGENT_PRIVATE_KEY` | no | no |  |
| `ONECLICK_JWT` | no | no |  |

## Tools (4)

- `agentguard_budget`
- `agentguard_pay`
- `agentguard_pending`
- `agentguard_swap_status`

## FAQ

### What does AgentGuard protect against?

It protects against prompt injections, runaway loops, and look-alike addresses that could drain an AI agent's wallet.

### How does the risk oracle work?

The risk oracle runs in a Trusted Execution Environment (TEE) using Intel TDX to check requests for prompt injection and sign a verdict.

### What are the possible outcomes of a spending request?

Requests result in one of three outcomes: Paid (within limits), Held (waits for owner approval), or Refused (denied by policy or oracle).
