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

# Sendforsign for AI agents

> The contracts layer for products that build AI agents: templates with per-recipient field roles, embedded white-label signing, and an audit trail of what each agent did and on whose behalf.

Your agent can already write a contract. What it cannot do on its own is turn that text into a signed,
legally attributable agreement inside **your** product: the right template for **your customer**, the fields
**the agent** may fill and the ones only the counterparty may fill, a signing link shown in **your** UI, an
event when it is signed, and a record of what the agent did and on whose behalf.

Sendforsign is that layer. It exposes the same API two ways:

* a **remote MCP server** at `https://api.sendforsign.com/mcp` that any MCP client (Claude, ChatGPT, Cursor,
  the OpenAI Agents SDK, your own agent) can connect to, and
* the **REST API** at `https://api.sendforsign.com/api` that the MCP server itself calls, for when you want
  deterministic code around the agent.

> [card] [MCP quickstart](https://about.sendforsign.com/ai-agents/mcp-quickstart.md)
>
> Connect Claude Code, Claude Desktop, Cursor or an OpenAI agent in two minutes.

> [card] [Tools reference](https://about.sendforsign.com/ai-agents/tools.md)
>
> Every MCP tool, what it writes, and which one emails people.

> [card] [Agent modes and accountability](https://about.sendforsign.com/ai-agents/accountability.md)
>
> Read-only, draft and send modes, confirmations, domain allowlists and the audit log.

> [card] [Recipes](https://about.sendforsign.com/ai-agents/recipes.md)
>
> Template → fill → send, embedded signing without email, multi-tenant, webhooks.

## Why Sendforsign, if other e-signature tools also ship MCP

An MCP server is table stakes; most e-signature vendors have one. What matters for a product that builds agents is
what happens around the signature:

### 1. Templates with field roles

Each field (placeholder) in a template has a **filled by** role: the owner (your agent), any recipient, or one
specific recipient. The agent reads the template, fills only its own fields and leaves the counterparty's fields to
the counterparty. It does not have to guess, and it cannot overwrite what a signer is supposed to enter.
See [placeholder `fillingType`](https://about.sendforsign.com/usecase/placeholder-filler).

### 2. Embedded, white-label, multi-tenant

* Every customer of your product gets its own space (a `clientKey`, and/or a `userKey` per end user) with its own
  templates and contracts. The agent works in the right tenant because **you** set it in a header, not the model.
* Recipients get a signing link (`https://app.sendforsign.com/sharing/{recipientKey}`) that you can show in your
  own UI, chat or app, with no Sendforsign email at all.
* Emails, when you do send them, carry your [branding](https://about.sendforsign.com/api-reference/settings/branding.md), and
  [webhooks](https://about.sendforsign.com/api-reference/webhook/concept.md) tell your backend when a contract is fully signed.
* The [React components](https://about.sendforsign.com/sdk/introsdk.md) let a human review and edit what the agent drafted, inside your product.

### 3. Agent accountability

The integrator, not the agent, decides what an agent may do:

* **Modes**: `read_only`, `draft` (prepare everything, email nobody) or `send`.
* **Explicit confirmation**: tools that email people or archive contracts refuse to run without `confirm: true`,
  which the agent is told to set only after a human approves.
* **Recipient domain allowlist**: an agent cannot send a contract outside the domains you list.
* **Audit log**: every write by an agent is recorded with the agent's name, the person or company it acted for, the
  mode, the arguments and the outcome, in a hash-chained log.

[Read how this maps to attribution rules for electronic signatures.](https://about.sendforsign.com/ai-agents/accountability.md#legal-context)

## Who this is for

* **Vertical SaaS with an agent** (creative and event businesses, staffing, real estate, logistics, agencies, HR,
  insurance): your agent drafts your customer's contract from your customer's template, sends it or hands the link
  to your UI, and your backend reacts to the signature.
* **Legal-AI startups** that draft or negotiate but don't want to build execution: upload the final text, add
  signers, send, get the signed PDF.
* **People using Claude, ChatGPT or Cursor directly**: "make an NDA from our template and send it to Anna".

## For LLMs and coding agents

* [`/llms.txt`](https://about.sendforsign.com/llms.txt) — an index of these docs for language models.
* [`/llms-full.txt`](https://about.sendforsign.com/llms-full.txt) — the API and MCP reference in one file.
* Every page is also available as Markdown: add `.md` to its URL.
* [Agent skill](https://about.sendforsign.com/ai-agents/skills.md) — a `SKILL.md` that teaches Claude Code, Codex and other agents the recipes and
  the pitfalls.


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