Ignisign for AI agents

Ignisign is an electronic signature platform that lets businesses send, sign, and securely manage contracts and other documents online, tracking every signer's status along the way. 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.

DocumentsAPI keyMCP + RESTignisign.io
AUDIT LOG · IGNISIGNPOLICY: acme-support
09:41:07 · claude · u_8f2read
ignisign.list_documents
List Documents✓ allowed · 212ms
09:41:08 · claude · u_8f2read
ignisign.get_webhooks
Get Webhooks✓ allowed · 164ms
09:41:09 · claude · u_8f2write
ignisign.create_signer
Create Signer✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
ignisign.delete_signer
Delete Signer✕ blocked · policy: deny
EVERY IGNISIGN CALL, ON THE RECORD
01 · USE CASES

What agents do in Ignisign.

01

Check a signature request's status

Check whether all signers have completed a document before following up.

02

Initialize a new signature request

Start a signature request for a contract, adding the required signers.

03

Cancel a request with confirmation

Cancel a pending signature request only after the sender confirms the document is being replaced.

02 · ACTIONS

32 Ignisign actions, graded by risk.

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

read

14

Look things up. Allowed by default.

  • ignisign.get_webhooks
    Get Webhooks
  • ignisign.list_documents
    List Documents
  • ignisign.search_signers
    Search Signers
  • ignisign.get_signer_inputs
    Get Signer Inputs
  • ignisign.get_signer_profile
    Get Signer Profile
  • ignisign.get_signed_document
    Get Signed Document
  • ignisign.get_signer_profiles
    Get Signer Profiles
  • ignisign.get_signature_requests
    Get Signature Requests
  • ignisign.get_application_context
    Get application context
  • ignisign.get_document_information
    Get Document Information
  • ignisign.get_missing_signer_inputs
    Get Missing Signer Inputs
  • ignisign.get_signer_input_constraints
    Get Signer Input Constraints
  • ignisign.get_signature_request_details
    Get Signature Request Details
  • ignisign.get_signature_request_document
    Get Signature Request Document

write

13

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

  • ignisign.create_signer
    Create Signer
  • ignisign.update_signer
    Update Signer
  • ignisign.create_document
    Initialize Document
  • ignisign.create_webhook_endpoint
    Create Webhook Endpoint
  • ignisign.update_webhook_endpoint
    Update Webhook Endpoint
  • ignisign.update_signature_request
    Update Signature Request
  • ignisign.update_document_information
    Update Document Information
  • ignisign.api_authentication
    Ignisign API Authentication
  • ignisign.init_signature_request
    Initialize Ignisign Signature Request
  • ignisign.publish_signature_request
    Publish Signature Request
  • ignisign.provide_document_content_file
    Provide Document Content File
  • ignisign.provide_document_content_data_json
    Provide Document Content Data JSON
  • ignisign.provide_document_content_private_file
    Provide Document Content Private File

destructive

5

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

  • ignisign.delete_signer
    Delete Signer
  • ignisign.delete_document
    Delete Document
  • ignisign.delete_webhook_endpoint
    Delete Webhook Endpoint
  • ignisign.cancel_signature_request
    Cancel Signature Request
  • ignisign.delete_signature_request
    Delete Ignisign Signature Request
03 · HOW IT WORKS

Ignisign in three steps.

  1. 01Your users connect IgnisignThey add their Ignisign api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Signer” can wait for the user, and “delete Signer” can be denied outright.
  3. 03Any agent can actYour agent calls Ignisign 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('ignisign', {
  read: 'allow',
  write: 'ask',        // create_signer
  destructive: 'deny',  // delete_signer
})

# 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 Ignisign connects.

Users add their Ignisign 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 Ignisign 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 Ignisign from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Ignisign and Arc0, answered.

Q01

Can I use Ignisign with Claude, ChatGPT or Cursor?

Yes. Connect Ignisign 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 Ignisign actions you allow.

Q02

How do users connect Ignisign?

Users add their Ignisign 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 Ignisign actions can my agent take?

32 in total: 14 read, 13 write and 5 destructive, such as “create Signer”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Ignisign?

Yes. Actions like “delete Signer” 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 Ignisign too?

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

Get started

Plug Ignisign into your agent.

Your users connect Ignisign once, under your brand. Your agent gets 32 actions behind your policies, with every call on the record.

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