signplume

Use signplume from your AI assistant

Get help with setup and signature design from your favourite AI. Connect signplume to Claude, ChatGPT, Microsoft Copilot, Gemini, Cursor or VS Code and ask it to set signplume up with you: it brings your team in, designs a signature with your logo and colours, then asks which other features you want and sets them up. Afterwards, manage everything by asking: add and invite people, change designs and rules, run banner campaigns and read their clicks, check billing and who is signing — with your own role.

A few things stay on the signplume screens, because they handle a credential or your own account security: connecting Google Workspace or Microsoft Entra ID, the Outlook add-in key, the server-side signing credentials, IP ranges, header secret and route, your two-step login, and the billing portal.

No signplume account yet? Connect anyway: the sign-in page has Create an account, and you come straight back to approve your assistant.

signplume's MCP address

https://signplume.com/mcp

Paste it where your assistant adds connectors. The first time, it sends you to signplume to sign in and approve.

How to connect

Claude — web, desktop and mobile
  1. Open Settings → Connectors and choose Add custom connector.
  2. Name it signplume and paste https://signplume.com/mcp.
  3. Choose Add, then Connect. Sign in to signplume and approve.
  4. In a chat, switch signplume on from the tools menu.

On Team or Enterprise an Owner adds it once under Admin settings → Connectors; members then choose Connect.

ChatGPT
  1. Open Settings → Apps & Connectors → Advanced settings and switch on Developer mode.
  2. In Apps & Connectors choose Create, name it signplume, paste https://signplume.com/mcp and pick OAuth.
  3. Sign in to signplume and approve, then add signplume to a chat from the + menu.

Needs a paid plan on the web; on Business and Enterprise an admin may have to allow developer mode.

Microsoft Copilot (Copilot Studio)
  1. Open your agent: Tools → Add a tool → New tool → Model Context Protocol.
  2. Paste https://signplume.com/mcp, choose OAuth 2.0, then Dynamic discovery.
  3. Create a new connection, sign in to signplume and approve, then add the tool to the agent.
Gemini

Gemini CLI:

gemini mcp add --transport http signplume https://signplume.com/mcp

Then run /mcp auth signplume in Gemini CLI to sign in.

Gemini Enterprise's custom MCP connectors need a client ID and secret made by hand rather than signing in on their own; until signplume offers those, use Gemini CLI.

Claude Code
claude mcp add --transport http signplume https://signplume.com/mcp

Then run /mcp, pick signplume and choose Authenticate.

Cursor, VS Code and other MCP clients

Cursor — ~/.cursor/mcp.json:

{ "mcpServers": { "signplume": { "url": "https://signplume.com/mcp" } } }

VS Code — .vscode/mcp.json:

{ "servers": { "signplume": { "type": "http", "url": "https://signplume.com/mcp" } } }

Any assistant that supports remote MCP servers with OAuth works: give it the address and it finds the sign-in itself.

What to ask

Your assistant also offers ready-made conversations — in Claude and others, look for set_up_signplume, onboard_new_hire and banner_campaign among the connector's prompts.

Sign in to see the assistants you have connected.

Your assistant acts as you: it can do what your role allows and nothing more, every change is recorded as yours, and it never sees your password or two-step codes. You can disconnect it at any time.