Get started

Boldsign for AI agents

BoldSign is an e-signature platform that businesses use to send documents for signing, track signer status, and manage signing templates and brand settings. 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 BoldsignSee the 14 actions ↓
DocumentsOAuth 2.0MCP + RESTboldsign.com
AUDIT LOG · BOLDSIGNPOLICY: acme-support
09:41:09 · claude · u_8f2write
boldsign.brand_get
Get Brand Details✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
boldsign.document_remove_authentication
Remove Document Authentication✕ blocked · policy: deny
EVERY BOLDSIGN CALL, ON THE RECORD
01 · USE CASES

What agents do in Boldsign.

01

Send a document for signature

Send a document to its recipients for signing after the user approves the final draft.

02

Check remaining API credits

Read-only lookup of the account's API credit balance before sending another document out for signature.

03

Require approval before extending expiry

Treat extending a document's expiry date as a change needing confirmation since it affects a signer's deadline.

02 · ACTIONS

14 Boldsign actions, graded by risk.

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

read

0

Look things up. Allowed by default.

  • No read actions.

write

13

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

  • boldsign.brand_get
    Get Brand Details
  • boldsign.brand_list
    List Brands
  • boldsign.file_upload
    Upload File (Helper)
  • boldsign.document_list
    List Documents
  • boldsign.document_send
    Send Document
  • boldsign.custom_field_edit
    Edit Custom Field
  • boldsign.document_edit_beta
    Edit Document (Beta)
  • boldsign.document_team_list
    List Team Documents
  • boldsign.custom_field_create
    Create Custom Field
  • boldsign.document_behalf_list
    List Behalf Documents
  • boldsign.document_extend_expiry
    Extend Document Expiry
  • boldsign.plan_get_api_credits_count
    Get API Credits Count
  • boldsign.embedded_request_create_link
    Create Embedded Request Link

destructive

1

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

  • boldsign.document_remove_authentication
    Remove Document Authentication
03 · HOW IT WORKS

Boldsign in three steps.

  1. 01Your users connect BoldsignThey sign in to Boldsign on Arc0 Connect, under your brand, and approve the access you ask for.
  2. 02You set the rulesReads run, writes like “get Brand Details” can wait for the user, and “remove Document Authentication” can be denied outright.
  3. 03Any agent can actYour agent calls Boldsign 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('boldsign', {
  read: 'allow',
  write: 'ask',        // brand_get
  destructive: 'deny',  // document_remove_authentication
})

# 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 Boldsign connects.

Users sign in to Boldsign on Arc0 Connect and approve the scopes you request. Build with Arc0’s Boldsign OAuth app, or bring your own so the Boldsign consent screen names you. Tokens refresh automatically, and you can export them whenever you want.

The same Boldsign 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
OAuth 2.0
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Boldsign from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More documents apps.

Google Docs43 actionsActiveMerge13 actionsAirparser10 actionsAlgodocs3 actionsDocuSign338 actionsSharePoint Graph162 actionsSharePoint105 actionsDocumenso77 actions
ALL DOCUMENTS APPS →
07 · FAQ

Boldsign and Arc0, answered.

Q01

Can I use Boldsign with Claude, ChatGPT or Cursor?

Yes. Connect Boldsign 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 Boldsign actions you allow.

Q02

How do users connect Boldsign?

Users sign in to Boldsign on Arc0 Connect and approve the scopes you request. Build with Arc0’s Boldsign OAuth app, or bring your own so the Boldsign consent screen names you. Tokens refresh automatically, and you can export them whenever you want.

Q03

Which Boldsign actions can my agent take?

14 in total: 0 read, 13 write and 1 destructive, such as “get Brand Details”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Boldsign?

Yes. Actions like “remove Document Authentication” 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 Boldsign too?

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

Get started

Plug Boldsign into your agent.

Your users connect Boldsign once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.

Connect BoldsignBrowse all apps →

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