# group-roles

Read relay-defined role names from verified kind 39003 state. NIP-29 does not let clients define role permissions.

Agent View of the PolicyLayer registry record for `group-roles`. HTML page: https://policylayer.com/tools/dev-forgesworn-bray/group-roles

## Facts

- Tool: `group-roles`
- Server: Nostr Bray (`nostr-bray`) — https://policylayer.com/tools/dev-forgesworn-bray.md
- Install: `npx -y nostr-bray`
- Homepage: https://github.com/forgesworn/bray
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "group-roles",
    "arguments": {}
  }
}
```

## Why group-roles is rated Low

This tool retrieves and queries relay-defined role information from Nostr kind 39003 state events. It performs lookups only without creating, modifying, deleting, or executing any operations. The description confirms it does not permit clients to define or alter role permissions, reinforcing its read-only nature. The 'verified' qualifier indicates it validates data integrity but does not modify state.

From the tool's own definition: "Tool description explicitly states 'Read relay-defined role names from verified kind 39003 state' — the verb 'Read' and action of retrieving role names indicates a query operation with no side effects."

## Use case

AI agents call group-roles to retrieve information from Nostr Bray without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Nostr Bray:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "group-roles": {}
  }
}
```

## Other tools on Nostr Bray (260)

- `blossom-delete` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/blossom-delete.md
- `group-delete` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/group-delete.md
- `group-delete-event` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/group-delete-event.md
- `group-remove-user` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/group-remove-user.md
- `label-remove` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/label-remove.md
- `marketplace-credentials-clear` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/marketplace-credentials-clear.md
- `marketplace-retire` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/marketplace-retire.md
- `social-delete` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/social-delete.md
- `tombstone` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/tombstone.md
- `trust-revoke` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/trust-revoke.md
- `vault-revoke` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/vault-revoke.md
- `wallet-revoke` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/wallet-revoke.md
- `zap-wallet-clear` — Destructive — https://policylayer.com/tools/dev-forgesworn-bray/zap-wallet-clear.md
- `cast-spell` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/cast-spell.md
- `execute-action` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/execute-action.md
- `identity-restore-shamir` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/identity-restore-shamir.md
- `identity-switch` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/identity-switch.md
- `marketplace-probe` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/marketplace-probe.md
- `nip44-encrypt` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/nip44-encrypt.md
- `onboard-verified` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/onboard-verified.md
- `relay-auth` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/relay-auth.md
- `trust-attest-chain` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/trust-attest-chain.md
- `trust-ring-lsag-sign` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/trust-ring-lsag-sign.md
- `trust-ring-prove` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/trust-ring-prove.md
- `trust-spoken-verify` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/trust-spoken-verify.md
- `vault-encrypt` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/vault-encrypt.md
- `wallet-serve` — Execute — https://policylayer.com/tools/dev-forgesworn-bray/wallet-serve.md
- `marketplace-pay` — Financial — https://policylayer.com/tools/dev-forgesworn-bray/marketplace-pay.md
- `zap-make-invoice` — Financial — https://policylayer.com/tools/dev-forgesworn-bray/zap-make-invoice.md
- `zap-send` — Financial — https://policylayer.com/tools/dev-forgesworn-bray/zap-send.md
- …and 230 more: https://policylayer.com/tools/dev-forgesworn-bray.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=dev-forgesworn-bray · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dev-forgesworn-bray