Register a new agent
Request
- Base URL: https://api.1claw.co
- URL: https://api.1claw.co/v1/agents
- Auth: HTTP bearer
Request body
Default LLM provider for automations and Shroud.
Default LLM model for automations and Shroud.
List this agent in the cross-org agent directory.
Description shown on the public directory listing.
Tags shown on the public directory listing.
Skip creating the default access policy for this agent.
Address screening policy applied to transaction recipients.
Enable durable key-value and semantic memory for this agent. Required before PUT /v1/agents/{agent_id}/memory/{namespace}/{key} will accept a write; without it that endpoint returns 403.
Namespaces this agent may use. Empty or omitted means unrestricted.
Maximum size of a single memory entry value. Null uses the platform default (64 KiB).
Authentication method. api_key generates a one-time key; mtls requires client_cert_fingerprint; oidc_client_credentials requires oidc_issuer and oidc_client_id.
Maximum value per transaction in native major units for the transacting chain family (ETH on EVM, BTC on Bitcoin, SOL on Solana, XRP, ADA, TRX).
Rolling daily spend cap in native major units, enforced per chain family at signing time.
Deprecated alias for tx_max_value. Same unit semantics (native major units, not ETH-only).
Deprecated alias for tx_daily_limit.
Per-agent token TTL in seconds (overrides global default)
Restrict agent to specific vault UUIDs (empty = all vaults in org)
SHA-256 fingerprint of the client certificate (required for mTLS auth)
OIDC issuer URL (required for oidc_client_credentials auth)
OIDC client ID (required for oidc_client_credentials auth)
Enable Shroud LLM Proxy for this agent
Default system prompt for agent chat when requests do not override it.
Enable Execution Intents (bindings and execute endpoint) for this agent
Guardrails applied to all execution intents for this agent
When true, transaction/sign requests must arrive via a TEE host (Pro+ only)
When true, execute requests must arrive via TEE and all direct secret reads are blocked (Pro+ only)
Token contract/mint addresses this agent may interact with. Empty = unrestricted.
When true, only tokens in the known_tokens registry may be used.
Allowed XRP Ledger transaction types (Payment, TrustSet, etc.). Empty = all allowed.
Per-chain guardrail overrides. Keys are signing chains (ethereum, bitcoin, solana, xrp, cardano, tron). Each value may include max_value, daily_limit, to_allowlist, token_allowlist, max_per_day, overhead_budget, max_ata_creates_per_day, max_fee_per_gas_gwei, max_gas_limit, gas_daily_budget_native (UTC-day cumulative EVM gas estimate in native units). Strictest of global and per-chain limits wins. Daily limits apply per chain family spend, not cross-chain totals.
Max transactions per UTC calendar day. Null = unlimited.
Per-chain daily overhead budget in native units (e.g. {"solana":"0.5","xrp":"100"}).
Solana wallet addresses whose ATAs may be created. Empty = unrestricted.
Whether this agent may order payment cards (x402 card ordering). Pro+ tier.
Maximum USD amount for a single card order.
Maximum cumulative USD spent ordering cards per rolling 24h window.
One cap across ALL of this agent's x402 stablecoin spend — POST /v1/pay and card orders together. Calendar day, UTC. Omit for no cap. Applied in addition to the per-route caps, never instead of them: tx_* bounds signing and submitting, pay_* bounds POST /v1/pay, and card_* bounds card orders. None of those three bounds the others, so this is the only field that caps an agent's total stablecoin spend.
Allowed x402 payTo recipients for card orders (empty = built-in Laso recipients).
Whether agents may reveal card details subject to per-card reveal policy.
When true, card orders route through the human approval queue before x402 payment.
Graduated transaction approval policy (HITL thresholds). Separate from hard guardrails.
Which business actions this agent must ask a human about, and above what amount. {} means no per-action rules.
Shape: { "default_mode": "deny|approve|allow", "rules": [ { "action_type": "refund.create", "mode": "approve", "require_for_amount_above_usd": "50", "summary_template": "Refund {{amount_usd}} to {{customer_email}}" } ] }.
A rule can only raise the bar. Editing this is classified as a guardrail widening, so it routes through the same approval flow as loosening a transaction limit. Malformed rules are rejected on write rather than ignored at request time.
EIP-712 escalation when typed_data matches no allowlist — deny (403) or route to HITL (approve).
Simulation failure escalation — deny (422) or route to HITL (approve).
Block unlimited ERC-20 approvals (max uint256 / setApprovalForAll).
Max transactions to the same recipient address per UTC day.
Max native-unit spend to the same recipient per UTC day.
Cap on first-time recipient spend in native units.
Per-transaction USD cap (requires price oracle).
Rolling 24h USD spend cap (requires price oracle).
Raw digest signing policy — allow, deny, or route to HITL (approve).
personal_sign guardrails (message allowlist, max bytes, etc.).
Allow ERC-4337 gasless UserOperations.
Allow EIP-7702 (tx type 4) set-code transactions.
Optional expiration time for the agent's API key.
Named environment for this agent (production, preview, development, or custom).
When true, the environment tag cannot be changed after creation.
When true, env var resolve endpoints auto-fill environment from this agent's tag.
Optional completed approval ID for control-plane consensus bypass when creating an agent under a control-plane governance policy.
Response
Agent created with one-time API key
One-time API key (only present for api_key auth method)
Changes
No recorded changes to this operation across all 1 revision of this API.