> For the complete documentation index, see [llms.txt](https://docs.moderncollections.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.moderncollections.io/getting-started/overview.md).

# Overview

This section walks you from zero to "first integration commit" in under an hour. Pick the path that matches what you're building.

## Choose your path

There are four common integration shapes. Each has a different start sequence.

### Path A: classic REST integration (most common)

You have an accounts-receivable system. You want to forward overdue invoices to us, watch them progress, and reconcile payments back. This is the path the majority of our creditor partners take.

1. [Authentication](/getting-started/authentication.md) — get an API key, understand the auth model.
2. [Environments](/getting-started/environments.md) — production and demo base URLs.
3. [First API call](/getting-started/first-api-call.md) — `POST /v1/placements` with a test invoice.
4. [Webhooks overview](/webhooks/overview.md) — register your callback URL.
5. [Signature verification](/webhooks/signature-verification.md) — verify what we send you.
6. [Guide: ingest overdue invoices](/integration-guides/ingest-overdue-invoices.md) — the end-to-end recipe.

### Path B: MCP / AI agent integration

You're building an AI agent (in Claude Desktop, Cursor, your own product, etc.) and want it to be able to file or query collections placements. This is a 2026-onward pattern.

1. [Authentication](/getting-started/authentication.md) — same creditor API key.
2. [MCP overview](/mcp-servers/overview.md) — what MCP is and how our server fits.
3. [MCP installation](/mcp-servers/installation.md) — add our server to your client.
4. [Guide: MCP agent quickstart](/integration-guides/mcp-agent-quickstart.md) — end-to-end with an example workflow.

### Path C: read-only transcript / audit integration

You want to listen to what our agents are doing without driving any action.

1. [Authentication](/getting-started/authentication.md).
2. Call transcripts and summaries — `GET /v1/placements/{id}/calls` (see [Placements](/rest-api/placements.md)).
3. [Audit log query](/mcp-servers/tools/audit-log-query.md) or the [REST audit endpoint](/rest-api/placements.md) — historical events.

## What every integrator should read

Regardless of path, two pages are non-negotiable before you go live:

* [Error handling](/getting-started/error-handling.md) — how to be a good API citizen with retries, idempotency, and rate limits.
* [Compliance for integrators overview](/compliance-for-integrators/overview.md) — what your side has to do to stay legal.

## Tools you'll need

* A modern HTTP client. We test against `curl`, Python `httpx`, and JavaScript `fetch`.
* An API key — issued either through the self-serve onboarding wizard (`POST /v1/creditors` → verification → `POST /v1/creditors/me/issue-api-key`) or by an admin on approval. See [Authentication](/getting-started/authentication.md).
* (Optional) The first-party [`mc_api` Python client](/sdks/python.md) (which also ships the `mc-api` CLI). A [JavaScript SDK](/sdks/javascript.md) is planned but not yet available.
* (Optional, for MCP) Claude Desktop, Cursor, Continue, or any MCP-compatible client.

## Estimated time-to-first-call

| Path               | Time-to-first-call                                 |
| ------------------ | -------------------------------------------------- |
| Path A (REST)      | 15-30 minutes                                      |
| Path B (MCP)       | 5-15 minutes (most of it is client install)        |
| Path C (A2A)       | Several weeks (involves engineering on both sides) |
| Path D (read-only) | 10 minutes                                         |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.moderncollections.io/getting-started/overview.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.