Deterministic execution gating for autonomous AI agents

The Problem

AI agents write code and move money — with zero safety checks.

Result: exploits, drained wallets, "the agent did it" with no audit trail.

The Solution

TeosMCP CodeGuard sits between your agent and execution.

Before any code runs → CodeGuard scores it → returns ALLOW or BLOCK.

No LLM guessing. No randomness. Deterministic every time.

What It Detects

• Credential exposure (API keys, private keys)
• Destructive operations (drop table, rm -rf, self-delete)
• Unexpected network calls
• Infinite loops / unbound recursion
• Unvalidated financial operations
• Agent self-modification

Install

npx @elmahrosa/teos-mcp-codeguard

MCP Config

{
  "mcpServers": {
    "teos-mcp-codeguard": {
      "command": "npx",
      "args": ["@elmahrosa/teos-mcp-codeguard"]
    }
  }
}

Pricing

• Free: 1,000 decisions/month — $0
• Pro: 100,000 decisions/month — $99/month
• Enterprise: Unlimited — $2,000+/month

Part of TeosMCP Ecosystem

• CodeGuard → code risk before execution (this server)
• TeosLinker → on-chain risk monitoring
• TeosMCP Core → unified policy engine (coming soon)

GitHub: https://github.com/Elmahrosa/agent-code-risk-mcp

X: @king_teos