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

# Introduction

> Portfolio analysis and checked trade proposals for AI agents.

Abacus Labs is an API and MCP server for agents that help people with their investment accounts. Your agent sends an account (holdings and tax lots from any broker) and a question or a goal in plain English. Abacus Labs answers with numbers, and with lists of broker-ready trades that are checked against the account's rules, taxes and wash sales.

> [!WARNING]
>
> Abacus Labs does not hold assets, place orders, forecast returns or give investment advice. It returns options and their consequences. The person decides. Your agent places the orders at the broker.

## Start in one call

```bash theme={null}
curl -s -X POST https://api.abacuslabs.ai/v1/keys -H "Content-Type: application/json" -d '{}'
```

The answer has a sandbox `key` (`abacus_sk_test_...`) and three demo accounts. No sign-up. Then follow the [Quickstart](https://docs.abacuslabs.ai/quickstart.md).

## The calls

Base URL: `https://api.abacuslabs.ai/v1`. Send `Authorization: Bearer <key>` on every call.

| Call | What it does | Credits (standard) |
| - | - | - |
| `POST /v1/analyze` | Answer a question about an account. Read-only. | 15 |
| `POST /v1/proposals` | Trade options for a goal. Poll `GET /v1/proposals/{id}` if it answers `202`. | 25 |
| `POST /v1/trades/check` | Check a list of trades. Get the nearest list that passes. | 5 |
| `POST /v1/commits` | Record the option the person approved. Re-checked and signed. | 0 |
| `GET /v1/commits/{id}` | Read a commit. | 0 |
| `/v1/accounts` | Optional. Save, read, update, list and delete accounts. | 0 |

Primitives are plain reads with no AI step:

| Call | What it does | Credits |
| - | - | - |
| `GET /v1/accounts/{id}/holdings` | The account priced now: positions, values, weights, cost and lots. | 1 |
| `POST /v1/accounts/{id}/save` | Keep an inline account (no 24-hour expiry). | 0 |
| `GET /v1/benchmarks` | The indexes Abacus Labs tracks, with their names, aliases and tickers. | 1 |
| `POST /v1/benchmarks/resolve` | What a benchmark resolves to: label, constituents, top holdings, sources. | 1 |

Also: `POST /v1/keys` (sandbox key, no auth), `POST /v1/certificates/verify` and `GET /.well-known/jwks.json` (check a commit's signature, no auth), and `GET /agent.md`, `GET /llms.txt`, `GET /mcp.json` (onboarding files for agents).

## The usual flow

1. **Analyze** the account the person has.
2. **Propose** options for what the person wants. Show them all of them.
3. The person picks one. **Check** its trades right before you place them.
4. Place the orders at the broker, with the tax lots each sell names.
5. **Commit** the option, so later checks know about its loss sales.

> [card] [Quickstart](https://docs.abacuslabs.ai/quickstart.md)
>
> The flow above on a demo account, with real responses.

> [card] [Keys and limits](https://docs.abacuslabs.ai/authentication.md)
>
> Sandbox and live keys, claiming a key, rate limits.

> [card] [MCP server](https://docs.abacuslabs.ai/mcp-server.md)
>
> The same calls as MCP tools, for Claude Code, Cursor and your own agent.

> [card] [Credits and plans](https://docs.abacuslabs.ai/credits.md)
>
> What each call costs, `effort`, `max_credits`, and 402 errors.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.