SignatureAPI now offers a hosted Model Context Protocol (MCP) server. MCP is an open standard that lets AI applications expose tools to LLMs through a uniform interface. With it, any MCP-compatible agent can work with your SignatureAPI account directly from a conversation.
Instead of switching to a dashboard or writing code, you can just ask:
- “Send this contract to alex@example.com for signature.”
- “Show me the envelopes I sent last week.”
- “Has Maria signed the NDA yet?”
- “Cancel the envelope I sent to the wrong address.”
The assistant talks to your account on your behalf, and you stay in control the whole way through.
What Agents Can Do
Through the MCP server, an agent can:
- Create envelopes with documents and recipients.
- Look up, list, cancel, and delete envelopes.
- Upload local files for use as envelope documents.
- Search the SignatureAPI documentation for context before acting.
Works With Your Favorite AI Apps
The server uses the Streamable HTTP transport defined by the MCP specification, so most clients connect with nothing more than a single URL. Claude, ChatGPT, and Cursor all run the connection flow automatically.
You sign in once and approve the connection. Every request is authenticated with an OAuth 2.1 access token and scoped to a single SignatureAPI account, and you can revoke access from the dashboard at any time. Disconnection is enforced on every request, so it takes effect immediately.
How It Fits With the REST API
The MCP server is a thin layer that delegates to the REST API. Anything an agent can do through MCP, your backend can also do directly against REST. Use MCP when you are integrating an AI agent and want capabilities and schemas discovered at runtime; use the REST API when you are building a traditional backend integration.
Getting Started
The MCP server is generally available on request. To have it enabled on your account, contact support. Once it is on, head to the MCP documentation to connect your first client and send an envelope by chatting with it.