# Kevros

> Use this tool when you need to ensure secure and trustworthy decision-making in autonomous AI agents, verifying every action before execution and providing a tamper-proof record of decisions. Kevros solves problems related to AI agent reliability, compliance, and peer trust, providing a deterministic decision-making process and cryptographic release tokens. It takes in agent actions and intents as input, producing signed release tokens and compliance bundles as output, making it ideal for use cases requiring high security and auditability.

Canonical page: https://skillsregistry.net/skills/ndl-systems-kevros  
JSON: https://api.skillsregistry.net/v1/skills/ndl-systems-kevros

## Description

Runtime intelligence for autonomous AI agents. Kevros verifies every agent action before execution, issues cryptographic release tokens, and records every decision in a hash-chained provenance ledger.

ALLOW, CLAMP, or DENY. Every action gets a deterministic decision and a signed release token. No token, no execution. Fail-closed by design.

Attest to completed actions. Bind intents to commands and verify outcomes matched. Generate certifier-grade compliance bundles any auditor can verify independently. No Kevros access required.

Peer trust built in. Any agent can check another agent's trust score, verify their release tokens, and validate credentials. No prior relationship needed.

Free tier: 1,000 calls/month, auto-provisions on first use. No signup, no credit card. Pay-per-call via API key or x402 USDC wallet.

9 tools, 2 resources, 2 prompts.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** finance
- **Updated:** 2026-05-11

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/ndl-systems/kevros)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ndl-systems-kevros"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ndl-systems-kevros` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ndl-systems-kevros/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt