Need a replacement for Trigify? Check out the Trigify -> Teamfluence Migration Service
Help Center Documentation

How to Connect the Teamfluence MCP Server

Use your leads and networking tools from Claude, ChatGPT and other AI assistants.


The Teamfluence MCP server lets an AI assistant read and update the leads in your workspace. MCP (Model Context Protocol) is an open standard that AI assistants use to connect to other tools.

Once connected, you can ask things like "Show me this month's qualified leads, most engaged first" and the assistant gets the answer from Teamfluence.

What you need:

  • A Teamfluence account
  • An MCP password (Step 1)
  • An AI assistant that supports remote MCP servers, for example Claude, ChatGPT, Cursor, VS Code (Copilot) or Goose

You don't need an API key. You sign in with your Teamfluence account.

MCP server URL:

https://api.teamfluence.com/mcp

Step 1: Set your MCP password

You do this once. The sign-in in Step 2 asks for it.

Step 2: Add the server to your assistant

Pick your assistant below. Every assistant follows the same three moves: add a new MCP server, paste the URL, sign in with Teamfluence.

Claude

Custom connectors work on Claude Free, Pro, Max, Team and Enterprise. Free allows one.

  • In Claude, go to Customize → Connectors.
  • Click + and choose Add custom connector.
  • Paste https://api.teamfluence.com/mcp and click Add.
  • A browser window opens. Sign in with your Teamfluence email and the MCP password from Step 1.
  • In a chat, click +, choose Connectors and switch Teamfluence on.

On a Team or Enterprise plan, an Owner adds the connector once under Organization settings → Connectors. Everyone else then clicks Connect on it from their own Customize → Connectors screen and signs in with their own account.

ChatGPT

ChatGPT needs Developer Mode. It's available on Plus, Pro, Business, Enterprise and Edu, on the web.

  • Go to Settings → Security and login and turn on Developer mode.
  • In Settings → Connectors, add a custom connector with the URL https://api.teamfluence.com/mcp.
  • When asked how to authenticate, choose OAuth.
  • Sign in with your Teamfluence email and the MCP password from Step 1.
  • In a chat, click +, then More, then Developer Mode, and pick Teamfluence.

Cursor, VS Code (Copilot), Goose and other assistants

  • In your assistant's settings, add a new MCP server connection.
  • Use the URL https://api.teamfluence.com/mcp.
  • When the assistant asks you to sign in, complete the sign-in with your Teamfluence email and the MCP password from Step 1.

Menu names differ between assistants. If you can't find where to add a server, search your assistant's help pages for "remote MCP server".

Step 3: Check that it works

Ask your assistant:

List my available Teamfluence workspaces.

You should see the names of the workspaces your account can reach. If you belong to more than one, tell the assistant which one to use, for example: "Use the Acme workspace from now on."

Things to know

  • More than one workspace. Every request runs against one workspace. If you have several, the assistant lists them first and then needs the exact workspace name.
  • Sending is real. The assistant can send connection requests and direct messages from a teammate's account when you ask it to. Most assistants show you each action before it runs. Read it before you approve.
  • Each person signs in. Teammates connect with their own Teamfluence account and their own MCP password.

Troubleshooting

The sign-in fails or asks for a password I don't have. Set your MCP password first (Step 1), then try again. The sign-in asks for that password.

The assistant says it can't find my workspace. Ask it to list your available workspaces first, then use the exact name it returns.

I don't see the option to add a custom connector in Claude or ChatGPT. Check your plan. In ChatGPT, turn on Developer mode first. On company plans, an admin may need to add or allow the connector.

Next steps