# NOMOS

> NOMOS is an MCP server for security. Check an AI agent's action against signed rules before it commits, with auditable proof. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free trial
- **Platforms:** API, Web
- **Website:** https://www.nomosprotocol.com
- **MCP Registry name:** com.nomosprotocol/nomos
- **Categories:** security, AI models and LLM tooling
- **Listing updated:** 2026-11-14

## About

Most agent security asks who the agent is. NOMOS asks whether this exact action is allowed. Policy is reconciled with how teams actually decide, then sealed as signed, versioned rules (conditions, outcomes, priorities, a default, escalations and a data contract). The system that would be changed verifies an Act against those rules offline, using the issuer's public key, so no call to NOMOS is needed at decision time.

The verdict is AUTHORIZED, DENIED, ESCALATED or INCOMPLETE. Facts must come from certified witnesses or the system's own records, never from the agent, and a missing fact is undecided rather than false. Approvals are signed over the exact act so they cannot be reused. Verdicts are computed deterministically, not by a model, and each carries a hash for auditors.

The nomos.can() call queries any published authority with no key or signup. Signing uses Ed25519 or ES256, and a Regulated plan allows your own keys in a cloud KMS or HSM. The MCP server also exposes an act tool.

## Features

- **Action-level authorization:** Checks the act itself, not the identity of the agent.
- **Offline verification:** Counterparties verify authority against a public key.
- **Four verdicts:** Authorized, denied, escalated or incomplete.
- **Bound approvals:** Signed over the exact act so they cannot be reused.
- **Drift tracking:** Flags when behaviour departs from the sealed artifact.
- **Own-key signing:** Regulated plan supports AWS, Google, Azure KMS or HSM keys.

## Good for

- Gate a payment or refund an agent proposes
- Prove to an auditor why an action was allowed
- Let an agent act toward a supplier's system with verifiable authority
- Turn a policy PDF into executable rules

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http nomos https://www.nomosprotocol.com/api/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://www.nomosprotocol.com/api/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "nomos": {
      "url": "https://www.nomosprotocol.com/api/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "nomos": {
      "type": "http",
      "url": "https://www.nomosprotocol.com/api/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "nomos": {
      "serverUrl": "https://www.nomosprotocol.com/api/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "nomos": {
      "type": "http",
      "url": "https://www.nomosprotocol.com/api/mcp"
    }
  }
}
```

## Tools

- `verify_decision`: Check whether an AI decision is allowed, denied, or needs escalation according to a sealed NOMOS governance artifact. Always returns `allowed` (boolean) — that field is safe to read regardless of which artifact type answered. The rest of the shape genuinely differs by artifact type, because it proxies two different underlying endpoints: pub_ demo artifacts return a flat shape (`outcome`: auto_appr
- `generate_governance`: Convert one or more policy documents into a sealed NOMOS governance artifact (.nomos). Extracts executable rules using Claude, detects contradictions between rules, computes an Autonomy Readiness Index (ARI) score (0–1), and cryptographically seals the result. Returns an artifact_id you can use with verify_decision immediately. Optionally accepts historical behavioral decision logs to add a behavi
- `detect_contradictions`: Analyze policy documents (and optional behavioral decision logs) to detect contradictions, hidden rules, and gaps between declared policy and observed behavior. Stateless — no artifact is created and nothing is persisted. Returns contradictions of three types: rule_collision (two rules that apply to the same case with different decisions where the policy does not settle it soundly, each with that 
- `ask_authority`: Query a published authority on the NOMOS Exchange marketplace — a different system from verify_decision's own sealed policies. Every public authority (e.g. eu-ai-act.nomos) is queryable with no key. Returns the authority's own verdict (AUTHORIZED/DENIED/ESCALATED), the exact rule and reason, and a permanent, cryptographically-bound transcript (query_id + url) — replayable evidence, not just a repl
- `ask_by_context`: Ask whether an action is allowed WITHOUT choosing the law yourself (NOMOS-SPEC-014). Describe where the act happens and who it involves; NOMOS works out from its signed registrar log which laws govern it, asks every one, and combines strictly: any deny denies, a yes needs every law. Prefer this over ask_authority whenever you do not already know which law applies: naming one law leaves out the oth
- `find_authority`: Find which published authorities on the NOMOS Exchange govern something you are about to do, from a plain description (e.g. "deploy a recruitment model in the EU"). No name needed. Returns the matching authorities ranked, and for each the facts it reads that match your description (what to pass to ask_authority as inputs) and its most relevant rules with where they come from in the source. Also re
- `request_authority`: Ask for an authority (a law, regulation, standard or policy) to be added to the NOMOS Exchange when find_authority finds nothing. Requests are public and ranked by how many asked; they decide what is compiled next. Repeated requests from one caller count once. This never creates an authority: only its issuer, or NOMOS compiling the public text, can.

## FAQ

### Is a model involved in the decision?

No. Models help extract rules, but the verdict is deterministic.

### Do I need an API key to try it?

No key or signup is needed for nomos.can() on published authorities.

### What if a fact is missing?

The verdict is INCOMPLETE and the missing fact is named.

### What policy files are accepted?

PDF, Word or plain text, optionally with a CSV of past decisions.

### Is NOMOS free?

NOMOS is a paid product with a free trial.

### How do I add NOMOS to Claude Code?

Run this command in your terminal: claude mcp add --transport http nomos https://www.nomosprotocol.com/api/mcp

### What are the best alternatives to NOMOS?

The closest alternatives to NOMOS are REA, Claude Code Ultimate Guide, Agent Roast, Midplane and Leash.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Agent Roast](https://ai-powered.com/mcp/agent-roast): Agent Roast is an open-source MCP server for developer tools.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.
- [Leash](https://ai-powered.com/mcp/leash): Leash is a free MCP server for security.
- [Tinplate Edge AI Safety, Security & EU Compliance](https://ai-powered.com/mcp/tinplate-edge-ai-safety-security-and-eu-compliance): Tinplate Edge AI Safety, Security & EU Compliance is a freemium MCP server for security.
- [SecureCloud](https://ai-powered.com/mcp/securecloud): SecureCloud is a free MCP server for security.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.

---
Source: https://ai-powered.com/mcp/nomos
