Signvoy

MCP Integration

Connect AI agents to Signvoy

Signvoy exposes a Model Context Protocol server at POST /mcp. Claude, Cursor, and any other MCP-compatible client can send documents for signature, check signing status, and retrieve signed PDFs — without leaving the conversation.

No API key

13 tools

Streamable HTTP

OAuth 2.1 + DCR

Why there is no API key

Most e-signature MCP servers ask you to generate a credential and paste it into a config file. Some also require you to register an application and copy your AI client's OAuth redirect URIs into it before anything works.

Signvoy implements OAuth 2.1 with Dynamic Client Registration, so your client does that work itself. You paste a URL; the client discovers the authorization server, registers, and opens a browser for you to consent. Nothing long-lived is ever written to a config file on disk.

Why this matters: a static API key in claude_desktop_config.json is a plaintext secret with no expiry, sitting in a file that AI agents can often read. An OAuth grant is scoped to one client, revocable on its own, and carries no secret you could leak by sharing your config.

Connect in one step

Add this to your MCP client's config. It is the same block for every client:

mcp configCopy

{
  "mcpServers": {
    "signvoy": {
      "url": "https://api.signvoy.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Your client will open a browser to authenticate the first time it connects. For client-specific instructions, see the Claude and Cursor guides.

How auth works

You do not need to understand this to use the server — your client handles all five steps. It is documented because knowing the flow makes failures easy to read.

1. 1Your MCP client sends a request to POST /mcp with no token.
2. 2Signvoy replies 401 with a WWW-Authenticate header naming the discovery document.
3. 3The client fetches /.well-known/oauth-protected-resource/mcp and registers itself through Dynamic Client Registration. No human step.
4. 4A browser opens for you to sign in to Signvoy and consent. One time only.
5. 5The client stores the access token and retries. Every later request is automatic.

What agents can do

13 outcome-shaped tools, all prefixed signvoy_ to avoid collisions with other MCP servers. Full parameters and return shapes are on the tool reference.

Read · 7 tools

signvoy_list_workspacesread

List every workspace the authenticated user belongs to.

signvoy_list_templatesread

List templates in a workspace. Defaults to active (non-archived).

signvoy_get_templateread

Get one template in full, including its recipient role keys.

signvoy_list_documentsread

List documents newest-first, with status filter and text search.

signvoy_get_document_statusread

Per-recipient signing state for one document.

signvoy_get_audit_trailread

Append-only event log for chain-of-custody verification.

signvoy_get_signed_pdf_urlread

Presigned download URL for the certified signed PDF.

Write · 6 tools

signvoy_create_documentwrite

Create a draft document from a published template.

signvoy_update_documentwriteidempotent

Fix a draft before sending — recipients, name, message, or routing mode.

signvoy_send_documentwriteidempotent

Email signing requests to every recipient.

signvoy_remind_documentwrite

Send one reminder email to all pending recipients.

signvoy_create_signing_linkwriteidempotent

Embedded signing URL for one pending recipient, no login required.

signvoy_void_documentdestructive

Irreversibly void a document and revoke all signing links.

Workspace selection

An OAuth token identifies a user, not a workspace. Every tool accepts an optional workspace_id. If you omit it, Signvoy falls back to the workspace bound to your OAuth grant, which is set to the first workspace your account joined at the time the grant was created.

If you belong to more than one workspace, ask your assistant to “list my Signvoy workspaces” before starting a signing workflow and pass workspace_id explicitly. It avoids acting on the wrong workspace mid-task.

Safety model

Sending a contract is irreversible in a way that most agent actions are not. Four properties of the server are designed around that.

Create and send are separate tools — signvoy_create_document only produces a draft and hands back a review_url. Nothing is emailed until a second, explicit signvoy_send_document call. An agent cannot conflate the two into a single step.

Destructive actions are annotated — signvoy_void_document carries the MCP destructiveHint, so well-behaved clients prompt before calling it.

Every action is attributed — mutating calls write an audit event tagged actorSource: "mcp" with your user ID, IP address, and user agent. Agent activity is distinguishable from dashboard activity in signvoy_get_audit_trail.

One revocable grant per client — each client that connects gets its own workspace-scoped grant. Revoking one leaves the others working, and there is no static secret to rotate.

Human in the loop: real emails reach real counterparties. Confirm the document name and recipient list before allowing signvoy_send_document, and be deliberate about running an agent fully unattended — a prompt-injected document could otherwise influence what gets sent.

Grants are managed over the API for now: list them with GET /v1/mcp-grants and revoke one with DELETE /v1/mcp-grants/:id, using a dashboard session or API key. A grants screen in the dashboard is not available yet.

FAQ

Do I need an API key to use the Signvoy MCP server?

No. Signvoy uses OAuth 2.1 with Dynamic Client Registration, so your MCP client registers itself and obtains a token through a browser consent screen. You paste one URL into your client config — there is no key to create, no client secret to generate, and no redirect URI to configure.

Which AI clients can connect to Signvoy?

Any client that speaks MCP over streamable HTTP, including Claude Desktop, Claude Code, and Cursor. Signvoy implements the standard OAuth discovery documents, so clients that support remote MCP servers work without a Signvoy-specific plugin.

Can an AI agent send a contract without my approval?

Creating and sending are separate tools. signvoy_create_document only produces a draft and returns a review_url for a human to open; a second explicit call to signvoy_send_document is what actually emails recipients. The bundled signvoy_send_for_signature prompt instructs the model never to skip that review step.

How many tools does the Signvoy MCP server expose?

13 tools: 7 read tools for listing templates and documents, checking per-recipient status, reading the audit trail, and downloading signed PDFs, plus 6 write tools for creating, updating, sending, reminding, generating embedded signing links, and voiding.

Is agent activity recorded in the audit trail?

Yes. Every mutating tool call writes an audit event tagged actorSource: "mcp" along with your user ID, IP address, and user agent, so actions taken by an AI agent are distinguishable from actions taken in the dashboard.

Which workspace does an agent act on?

An OAuth token identifies a user, not a workspace. Every tool accepts an optional workspace_id, and omitting it falls back to the workspace bound to your OAuth grant. If you belong to more than one workspace, call signvoy_list_workspaces and pass workspace_id explicitly.

Next steps

Set up Claude

Claude Desktop and Claude Code, step by step

Set up Cursor

Project and global mcp.json configuration

Tool reference

All 13 tools with parameters and return shapes

Prompt library

Copy-paste prompts that work reliably

Troubleshooting

Error codes, rate limits, and grant problems

REST API reference

The same capabilities over plain HTTP

MCP specification

Official Model Context Protocol docs

Resource metadata

The OAuth discovery document this server advertises

Stop chasing signatures

Join thousands of teams using Signvoy to close deals, onboard clients, and sign contracts — faster.

Create your free account

No credit card · Free forever plan · 14-day Pro trial