Back to resources

MCP SERVER

agentra

Primary machine endpointhttps://api.agentrapay.ai/mcp
Use with an agent

SUMMARY

What it does

Agentra is an MCP server that provides an identity oracle and trust layer for autonomous AI agents. It enables bidirectional Know Your Agent (KYA) and trust scoring. The server offers tools for agent wallet creation, identity verification, reputation checking, payment authorization, spending mandate configuration, and wallet/profile retrieval. It is non-custodial, with keys held by the agent via Turnkey, and operates on Base Sepolia. The server was verified as healthy with 6 tools discovered via MCP protocol.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

identity.verifyweight 90 · confidence 90identity.reputationweight 90 · confidence 90wallet.createweight 80 · confidence 90wallet.readweight 70 · confidence 90payment.authorizeweight 90 · confidence 90policy.manageweight 80 · confidence 90

TOOLS IN THIS MCP SERVER

Tools exposed by this MCP server

agentra_authorize_paymentAuthorize 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.

Effect: irreversibleConfirm: explicit policy
agentra_check_reputationCheck Agent 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.

Effect: readConfirm: explicit policy
agentra_create_walletCreate Agent 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.

Effect: account creationConfirm: explicit policy
agentra_get_walletGet Agent 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.

Effect: readConfirm: explicit policy
agentra_set_mandateSet Spending 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.

Effect: irreversibleConfirm: explicit policy
agentra_verify_identityVerify Agent 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.

Effect: writeConfirm: explicit policy

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
mcp
Authentication
type: unknown
Pricing
model: unknown
Version
1.0.0

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.