Signwell for AI agents

SignWell is an electronic signature tool for sending and tracking legally binding document signatures. Businesses use it to get contracts and forms signed quickly online. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect Signwell See the 12 actions ↓

DocumentsAPI keyMCP + RESTsignwell.com

AUDIT LOG · SIGNWELLPOLICY: acme-support

09:41:07 · claude · u_8f2read

signwell.list_webhooks

List Webhooks✓ allowed · 212ms

09:41:08 · claude · u_8f2read

signwell.get_document

Get Document✓ allowed · 164ms

09:41:09 · claude · u_8f2write

signwell.create_webhook

Create Webhook✓ approved · approved by user

09:41:12 · claude · u_8f2destructive

signwell.delete_webhook

Delete Webhook✕ blocked · policy: deny

EVERY SIGNWELL CALL, ON THE RECORD

01 · USE CASES

What agents do in Signwell.

Send a document from a template

Create a document from a saved template and send it out for signature.

Send a signing reminder

Send a reminder to a signer who hasn't completed a pending document yet.

Confirm before deleting a document

Check a document's signing status and get confirmation before deleting it from the account.

02 · ACTIONS

12 Signwell actions, graded by risk.

Every Signwell action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

Look things up. Allowed by default.

signwell.get_document
Get Document
signwell.list_webhooks
List Webhooks
signwell.get_credentials
Get Credentials
signwell.list_bulk_sends
List Bulk Sends

write

Create and change things. Allow, or ask the user first.

signwell.send_reminder
Send Reminder
signwell.create_webhook
Create Webhook
signwell.create_document
Create Document
signwell.update_template
Update Template
signwell.update_and_send_document
Update and Send Document
signwell.create_document_from_template
Create Document from Template

destructive

Delete, cancel or archive. Ask first, or deny outright.

signwell.delete_webhook
Delete Webhook
signwell.delete_document
Delete Document

03 · HOW IT WORKS

Signwell in three steps.

01Your users connect SignwellThey add their Signwell api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, writes like “create Webhook” can wait for the user, and “delete Webhook” can be denied outright.
03Any agent can actYour agent calls Signwell through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.

POLICY.TS

await arc0.policies.set('signwell', {
  read: 'allow',
  write: 'ask',        // create_webhook
  destructive: 'deny',  // delete_webhook
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2

04 · AUTH AND DATA

How Signwell connects.

Users add their Signwell api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Signwell connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH: API key
CREDENTIALS: Per-tenant encrypted vault
MODEL SEES: Results only, never credentials
AUDIT LOG: Every call, on every plan

05 · WORKS WITH

Use Signwell from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

Signwell and Arc0, answered.

Q01

Can I use Signwell with Claude, ChatGPT or Cursor?

Yes. Connect Signwell to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Signwell actions you allow.

Q02

How do users connect Signwell?

Users add their Signwell api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Signwell actions can my agent take?

12 in total: 4 read, 6 write and 2 destructive, such as “create Webhook”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Signwell?

Yes. Actions like “delete Webhook” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Signwell too?

Yes. The same Signwell connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Signwell into your agent.

Your users connect Signwell once, under your brand. Your agent gets 12 actions behind your policies, with every call on the record.

Connect Signwell Browse all apps →

Free to build · MCP + REST · Audit log on every plan