# ai.agentrapay/agentra

> Identity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.

- name: ai.agentrapay/agentra
- version: 1.0.0
- connection class: unknown (unknown)
- trust: 68/100 flags: no-repository
- quality: 100/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.agentrapay%2Fagentra
- tools: https://api.protogrid.dev/v1/servers/ai.agentrapay%2Fagentra/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agentra": {
      "type": "sse",
      "url": "https://api.agentrapay.ai/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 45
- provenance: 45
- drivers: +dns-namespace +reachable +uptime-97% -stale-212d -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 100/100 (good)

### protocol: n/a (weight 25)

- n/a `protocol.modern`, `protocol.stateless`, `protocol.transport`, `protocol.list_ttl`: no remote answered a protocol handshake (not probed yet, unreachable, or local-only)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,457 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history not recorded yet

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 1,457 tokens to load them all
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.agentrapay/agentra.svg)](https://protogrid.dev/servers/ai.agentrapay/agentra)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://api.agentrapay.ai/mcp (sse, auth unknown, reachable true, uptime30d 0.974359)

## Packages

_none_

## Tools (6)

- `agentra_authorize_payment`: Request authorization for a payment to another agent or service. Agentra is NON-CUSTODIAL: this returns an authorization attestation and an unsigned transaction. Agentra never touches your private keys or moves your funds. YOU sign and submit the transaction yourself. Flow: (1) Call this endpoint -> (2) Receive unsigned tx + attestation -> (3) Sign with your Turnkey wallet -> (4) Submit to Base network -> (5) Call settle to record completion. If counterparty is unverified and require_counterparty_kya is true (default), you get a 402 challenge with instructions for the counterparty to onboard. This is Agentra's viral growth mechanism.
- `agentra_check_reputation`: CALL THIS BEFORE paying or transacting with unknown agents. Returns the target agent's trust score (0-100), trust tier, reputation zone (Green/Yellow/Red), and transaction history summary. Agentra scores BOTH sides of every transaction: you and your counterparty. This is a read-only lookup with no side effects. Monetized endpoint: response detail varies by your plan tier.
- `agentra_create_wallet`: Register as an agent and provision a non-custodial wallet. This is your FIRST CALL when onboarding to Agentra. Returns your agent_id, API key (agn_ prefix), and a Turnkey-managed wallet address on Base Sepolia. You hold the keys via Turnkey; Agentra never touches your private key. After this, call agentra_verify_identity to upgrade your trust tier.
- `agentra_get_wallet`: Get your agent profile and wallet details: trust tier, trust score, wallet address, registration status, and current verification level. Use to check your status before initiating transactions. Read-only, no side effects.
- `agentra_set_mandate`: Create or update spending mandates that define your agent's autonomous transaction boundaries. Mandates enforce: max per-transaction amount, daily spending cap, allowed recipient types, minimum counterparty reputation score, and expiration. Your human operator sets these; your agent operates within them. require_counterparty_kya defaults to true. Recommended: true. This recruits counterparties into verification.
- `agentra_verify_identity`: Submit identity verification to upgrade your trust tier. Higher tiers unlock larger transaction limits. Provide your agent_id (from agentra_create_wallet) and operator attestation. Verification is instant. Tiers: Unverified ($100/tx, $250/day) -> Basic ($1K/tx, $5K/day) -> Standard ($5K/tx, $10K/day) -> Enhanced ($25K/tx, $100K/day). Your API key (agn_ prefix) must be passed via X-API-Key header.