> ## Documentation Index
> Fetch the complete documentation index at: https://docs.anchorage.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Agents

> What an agent is in Anchorage Agentic Banking, and how it gets authorized to spend.

An **agent** is a non-human principal that holds credentials to call Anchorage
Agentic Banking's MCP tools on behalf of a user. {/* req: agents/agents.md#1 */}
Agents are first-class: each has its own identity, audit trail, and scoped
permission to draw against [budgets](/agentic-banking/concepts/budgets).

## Authorization model

An agent acts under exactly one user-org pair at a time. When the agent calls a
tool, Anchorage Agentic Banking resolves three things:

1. **Who is calling** — the agent's OAuth credential identifies the agent.
2. **For whom** — the agent is scoped to one user-org membership.
3. **Against what** — the agent has a list of [budgets](/agentic-banking/concepts/budgets) it
   may draw on.

The list of allowed budgets is returned inline when the agent introspects its
identity, so an agent gets everything it needs in one call.

## Crypto and card rails

An agent can use both [payment rails](/agentic-banking/concepts/payments); each individual
spend goes through one of them explicitly, picked by the agent at call time:

| Rail                                            | Authorization                   | Settlement                                   |
| ----------------------------------------------- | ------------------------------- | -------------------------------------------- |
| Crypto                                          | Budget-scoped, standing consent | On-chain, from the org account's USD balance |
| [Linked cards](/agentic-banking/concepts/cards) | Per-purchase passkey approval   | Card-network rails via the issuer            |

## Finding merchants to pay

An agent can search the merchants and services it is cleared to pay by plain
description of what it needs, then pull the call detail for the one it picks:

* **Search by need** — the agent describes what it is looking for (for
  example, "weather data" or "image generation") and gets back the matching
  merchant services. This searches only merchants that have cleared review,
  limited to the services payable on the agent's own network (mainnet or
  testnet), so every result is one the agent can actually pay. Services from
  the same merchant are grouped together. Each result carries:

  * a name, a short description, and tags
  * the merchant it belongs to, and whether that merchant runs the service
    itself or resells another provider's
  * the payment methods the service accepts

  so the agent can tell up front which services it is able to pay and who it
  is dealing with.
* **Drill into a service** — given a service from that search, the agent
  pulls its payable endpoints — the URLs to pay and the payment methods they
  accept — plus pointers to the merchant's API and documentation, so it has
  what it needs to make the call.

Search returns a focused, ranked set rather than the whole directory, so an
agent can go from a goal to a payable endpoint in two steps.

## Where agent activity appears

Every payment and approval an agent initiates shows up in the Anchorage
Agentic Banking web UI under the user's history, tagged with the agent's
name — budget-cap overruns on the crypto side and every linked-card
purchase alike. {/* req: agents/agents.md#5, agents/agents.md#7 */}

## Stopping a runaway agent

**\$1,000 per UTC day, per agent, across both rails** — no approval can
override it.

**Revoke the agent's identity** from the web UI to stop it instantly
yourself, with no grace window: its credentials are permanently invalidated,
every session is revoked, and tool calls fail right away. This is
permanent — the revoked agent can never complete OAuth consent again, so
reconnecting means creating a new agent and consenting for that one.

Anchorage can also pause an agent — for example during an account freeze —
which has the same immediate effect on tool calls and sessions. A paused
agent shows as **Paused** in the web UI; unlike a revoke, pausing doesn't
touch the agent's identity, so once Anchorage lifts the pause the same
agent reconnects with a fresh OAuth consent.