What is MCP, and why does it matter for e-signatures?

MCP (the Model Context Protocol) is the open standard AI assistants use to call real tools instead of guessing. Because Signavos exposes an MCP server, an assistant like Claude can genuinely upload a contract, place the signature fields, send it, and tell you when it comes back signed — rather than writing instructions for you to follow by hand.

Can an AI agent spend my money?

No. There is no tool that buys credits, and there never will be. Credits are only ever purchased by you, in a browser. An agent can spend credits you already own — one per document sent — and it has to confirm that charge explicitly before anything is sent.

Can an AI agent sign a document for me or for someone else?

No. Signavos has no tool that applies a signature. Recipients always sign themselves, in their own browser, from their own email link. The agent prepares and sends; humans sign.

Which AI assistants can connect?

Any MCP-capable client. Claude Code, Claude for desktop and web, and Cursor all connect with the URL alone; custom agents on the Anthropic API can connect the same way. The connection is standard OAuth 2.1, so no API keys are created or stored anywhere.

Is it safe to give an AI agent access to my documents?

You authorize it on a consent screen and can revoke it at any time. Access is scoped to your own account only, every action is written to the same tamper-evident audit trail as your own actions and tagged with the agent that performed it, and the destructive or billable steps require explicit confirmation.

Does using an agent cost extra?

No. Agent access is included and priced identically to the web app: one credit per document sent, no subscription and no per-seat fee. You are never charged for connecting an agent or for anything it reads.

AI agent access · MCP

Let your AI agent send documents for signature.

Signavos has a built-in MCP integration, so you can add your AI agent and let it do the paperwork. Connect Claude, Claude Code, Cursor or any Model Context Protocol client to one URL, approve it once, and your assistant can upload a PDF, add recipients, place the signature fields, send the document, watch for the signature and hand you back the signed file with its audit trail. It is the same engine the web app uses — the same validation, the same tamper-evident chain, the same price of one credit per document sent, with no subscription and no per-seat fee. And the limits are the part worth reading twice: an agent can spend a credit you already own, but it can never buy credits, and it can never sign on anyone's behalf.

Create an account Download the agent skill

Endpoint

https://signavos.com/api/mcp

How it works

One conversation, start to signed.

1
Upload
Hand the agent a PDF. It validates, scans and stores it exactly as the web app does.
2
Prepare
The agent adds recipients and places signature fields — by preset, so it never has to guess coordinates.
3
Confirm
Sending spends 1 credit, so the agent must confirm the charge explicitly before anything is sent.
4
Send
Recipients get an email link and sign in their browser. No account, no password.
5
Track
The agent polls status and tells you the moment the document is signed.
6
Collect
It fetches the signed PDF and the signing certificate with the audit trail.

Connect in a minute

Add your AI agent.

No API keys to create, copy or rotate. You authorize the agent on a consent screen, the same way you would connect any app to your account.

Claude Code

claude mcp add --transport http signavos https://signavos.com/api/mcp

Then run /mcp, choose signavos, and approve the consent screen.

Claude (desktop & web)

Open Settings → Connectors → Add custom connector.
Paste https://signavos.com/api/mcp as the server URL, then Add and Connect.
Approve the consent screen that opens in your browser.

Cursor

Command Palette → Cursor Settings → Tools & MCP → New MCP Server.
Add: { "mcpServers": { "signavos": { "url": "https://signavos.com/api/mcp" } } }
Select "Needs login" and authorize.

Any MCP client

Streamable HTTP endpoint: https://signavos.com/api/mcp
Authorization is OAuth 2.1 with PKCE and dynamic client registration — discovery starts at /.well-known/oauth-protected-resource.

Prefer to hand your agent written instructions? Download the Signavos agent skill — a single Markdown file describing every tool, limit and guard rail, ready to drop into Claude Code, Cursor or your own agent's instructions.

What your agent can do

11 tools, no guesswork.

get_account
Read the account email, credit balance and every limit below.
list_documents
List documents with their status, filtered and paged.
get_document
Inspect one document: recipients, fields, artifacts and what to do next.
get_download_url
Get a time-limited link to the signed PDF or its signing certificate.
upload_document
Upload a PDF inline, up to 3 MB.
create_upload_url
Get a signed URL for a larger PDF, up to 40 MB.
complete_upload
Finish a signed-URL upload; the file is validated and scanned like any other.
add_recipient
Add a signer by name and email.
remove_recipient
Remove a signer from a draft.
place_fields
Place signature, initials, name, date, text and checkbox fields — by preset or exact position.
send_document
Send for signature. Spends 1 credit and requires explicit confirmation.

Guard rails

Built so an agent cannot cost you anything you did not approve.

You approve it, and you can revoke it

Agents connect through an OAuth consent screen you see and approve. Remove the agent from your authorized applications and access stops immediately.

An agent can never spend money

There is no purchase tool. Credits are only ever bought by you in a browser — an agent can spend the credits you already own, one per document, and nothing else.

Sending always needs explicit confirmation

The send tool refuses to run unless the agent confirms the charge on purpose, so an exploratory prompt cannot mail a contract by accident.

It only ever sees your account

Every request is scoped to your account on the server. An agent cannot name someone else's account, and it never receives an account identifier to tamper with.

The same audit trail as the web app

Agent actions are recorded in the same tamper-evident chain as your own, tagged with the agent that performed them — so the signing certificate stays legally defensible.

Signers stay human

Signavos has no tool that signs on someone's behalf. Recipients always sign the document themselves, from their own email link.

Limits

The numbers your agent works within.

Your agent reads these from the server before it does anything, so it never has to guess and never trips a limit mid-task.

Credits per document sent: 1
Recipients per document: up to 20
Inline upload (base64): 3 MB max
Upload via signed URL: 40 MB max
Drafts kept per account: 2

Questions

AI agents and e-signatures

What is MCP, and why does it matter for e-signatures?: MCP (the Model Context Protocol) is the open standard AI assistants use to call real tools instead of guessing. Because Signavos exposes an MCP server, an assistant like Claude can genuinely upload a contract, place the signature fields, send it, and tell you when it comes back signed — rather than writing instructions for you to follow by hand.
Can an AI agent spend my money?: No. There is no tool that buys credits, and there never will be. Credits are only ever purchased by you, in a browser. An agent can spend credits you already own — one per document sent — and it has to confirm that charge explicitly before anything is sent.
Can an AI agent sign a document for me or for someone else?: No. Signavos has no tool that applies a signature. Recipients always sign themselves, in their own browser, from their own email link. The agent prepares and sends; humans sign.
Which AI assistants can connect?: Any MCP-capable client. Claude Code, Claude for desktop and web, and Cursor all connect with the URL alone; custom agents on the Anthropic API can connect the same way. The connection is standard OAuth 2.1, so no API keys are created or stored anywhere.
Is it safe to give an AI agent access to my documents?: You authorize it on a consent screen and can revoke it at any time. Access is scoped to your own account only, every action is written to the same tamper-evident audit trail as your own actions and tagged with the agent that performed it, and the destructive or billable steps require explicit confirmation.
Does using an agent cost extra?: No. Agent access is included and priced identically to the web app: one credit per document sent, no subscription and no per-seat fee. You are never charged for connecting an agent or for anything it reads.

Give your agent something useful to do.

Create an account, buy credits when you need them, and connect your assistant. There is no subscription to cancel if you stop.

Get started See pricing