Integration

Papersign integration

Papersign is Paperform's e-signature product. With its API an agent can list, search and read signature documents with their signers, variables and status, prepare a draft with updated signers and variables, send a document for signature (Papersign emails each signer), generate a signing link to share with a signer yourself, cancel, copy or move documents, get a download link for a completed signed PDF, list spaces, list and create folders, and register folder webhooks for document and signer events. The API has no route to upload a new document: work starts from a document that already exists in Papersign. The direct PDF download route (a redirect) is not exposed; use get_completed_document_url. Authentication is a Paperform API key (Account, Developer page) sent as a Bearer token; API access needs a Papersign plan that includes the Papersign API.

Connect Papersign How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Papersign.Built from the 16 Papersign tools below, on the connection you add once.

What you can do with Papersign

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Webhook, 4 operations

create_folder_webhookCreate folder webhookPOSTRegisters a webhook on a folder: Papersign calls target_url when the chosen document or signer events (document.completed, signer.signed...) happen on documents directly in the folder or in all its subfolders, per scope.
delete_webhookDelete webhookDELETEDeletes a Papersign folder webhook by its id. Returns status ok.
list_folder_webhooksList folder webhooksGETReturns the webhooks registered on a Papersign folder: id, target URL, scope (the folder's direct documents or all its descendants), the folder, and the document and signer events they fire on.
update_webhookUpdate webhookPUTUpdates a Papersign folder webhook: its name, target URL, scope or the events it fires on. Returns the updated webhook.

Document, 2 operations

get_documentGet documentGETReturns one Papersign document: name, status, folder and space, signers (key, name, email, phone, job title, company), variables (key, name, value), creation, sent and completion dates, and where it came from.
list_documentsList documentsGETLists Papersign documents, newest first by default, with their status, folder, space, signers, variables, dates and origin. Filter by name, status, folder, space or originating Paperform submission; page with limit and skip.

Folder, 2 operations

create_folderCreate folderPOSTCreates a Papersign folder inside a parent folder, or at a path inside a space (missing folders on the path are created too), and returns it.
list_foldersList foldersGETLists Papersign folders with their id, name, parent folder and space. Filter by space, by parent folder (its descendants) or by name.

Cancel, 1 operation

cancel_documentCancel documentPUTCancels a document that is out for signature (only a document in progress can be cancelled) and returns it with its updated status.

Completed document url, 1 operation

get_completed_document_urlGet completed document urlGETReturns a fresh link to the fully signed PDF of a completed document. Anyone holding the link can download the PDF until expires_at_utc (one week, or less if your team set a shorter expiry). A draft answers 400; a sent but unfinished document, 422.

Copy, 1 operation

copy_documentCopy documentPOSTCopies a document, optionally under a new name and into another folder or space, and returns the new copy.

Create draft, 1 operation

create_draft_documentCreate draft documentPOSTSaves a document as a draft with updated signers and variables, optionally on a copy, without sending it: no completeness check, no sign request, no notification. Use send_document when it is ready.

Link, 1 operation

generate_signer_linkGenerate signer linkPOSTGenerates a signing link, valid one week, for one pending signer of a sent document, to share yourself instead of the Papersign email. Anyone holding it can sign as that signer; a new link invalidates the previous one.

Move, 1 operation

move_documentMove documentPOSTMoves a document to another folder or space, optionally renaming it, and returns the updated document.

Send, 1 operation

send_documentSend documentPOSTSends a document out for signature: Papersign emails an invitation to each signer. Can also update signers and variables, set an expiry, reminders and a sender, or send a copy instead of the original. Returns the sent document.

Space, 1 operation

list_spacesList spacesGETLists Papersign spaces with their id, name, root folder id and whether the whole team can access them. Filter by name.

Use Papersign from Claude Code, Cursor or Codex

Connect Papersign in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Papersign operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Papersign

Create your workspace
Sign up free. Nothing to install.
Connect Papersign once
Add your Papersign connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.