Skip to main content
MCP servers let your AI assistant pull live data and trigger actions in external systems — like HubSpot, your internal APIs, or knowledge tools — right in the middle of a conversation. Connect a server once, assign it to any assistant, and its tools become available to the AI automatically.

​
What is an MCP server?

The Model Context Protocol (MCP) is an open standard for exposing tools to AI models. An MCP server is simply a remote HTTP endpoint that speaks this protocol. You don’t install anything — you paste the server’s URL (and optional authentication headers), and the assistant can call its tools while talking to your customer.

Why use MCP servers?

  • Add whole toolsets (e.g. a HubSpot or Notion integration) in one step instead of building tools one by one
  • Tools, descriptions and parameters are discovered automatically from the server
  • Works across voice calls, the web widget, and chat
  • Reuse one server across many assistants

​
Mid-call tools vs. MCP servers

Both live under the Tools page. Use whichever fits:

Mid-call tools

A single custom HTTP endpoint you define by hand (URL, method, parameters). Best for one-off calls to your own API. See Custom Mid-Call Tools.

MCP servers

A remote server that exposes many tools at once, discovered automatically. Best for connecting to a platform or a shared integration.

​
Connecting a server

MCP server configuration form
1

Open the Tools page

Go to Tools in the sidebar and switch to the MCP servers tab, then click New MCP server.
2

Fill in the details

  • Display name: a friendly name shown when assigning the server (e.g. HubSpot CRM)
  • Identifier: an internal id, lowercase letters and underscores only (e.g. hubspot)
  • Description: optional, for your own reference
  • Server URL: the remote MCP endpoint
  • Timeout: how long to wait when connecting to the server
3

Choose the transport

Leave this on Auto-detect unless you know otherwise. Auto-detect picks the right transport from the URL:
URL ends with /mcp  →  Streamable HTTP
URL ends with /sse  →  SSE (Server-Sent Events)
4

Add authentication headers (optional)

If the server requires a token, add it as a header. Headers are stored encrypted.
Authorization: Bearer your_token_here
When you save, the server is tested automatically and a notification lists the tools it exposes.

​
Try it for free

Want to test MCP without any setup? Connect the public DeepWiki server (no authentication required):
  • Display name: DeepWiki
  • Identifier: deepwiki
  • Server URL: https://mcp.deepwiki.com/mcp
Then ask your assistant something like “Use DeepWiki to summarize the facebook/react repository.”

​
Connection status & discovered tools

Each server is shown as a card with a live connection status.
MCP servers list with connection status and discovered tools

Connected

The server is reachable. Its available tools are listed on the card.

Disconnected

The server couldn’t be reached. The error is shown so you can fix the URL or headers.

Not tested

The server hasn’t been checked yet.
Use Test connection at any time to re-check a server and refresh its tool list.

​
Choosing which tools are exposed

By default, all of a server’s tools are available to your assistants. Open Manage tools (on the server’s edit page) to view each tool’s description and parameters, and enable or disable individual tools.
Manage tools panel showing tool descriptions, parameters and enable/disable toggles
Disabled tools are hidden from the AI. To expose no tools at all, simply remove the server from the assistant instead.

​
Assigning a server to an assistant

1

Open your assistant

Edit an assistant and go to the Prompt & Tools step.
2

Assign MCP servers

In the MCP servers section, select one or more servers. The list shows each server’s connection status and tool count.
3

Save

The assistant can now use the server’s enabled tools during voice calls, the web widget, and chat.

​
Authentication

The integration sends static headers with each request. It does not perform an interactive OAuth login.
Server authenticationSupportedHow
No authentication✅Nothing to configure
API key / token✅Add an Authorization (or custom) header
Token embedded in the URL (e.g. Zapier, Composio)✅Paste the full URL
Interactive OAuth login❌Use a personal access token in a header instead

​
Real-world examples

Display name: DeepWiki
Identifier: deepwiki
Server URL: https://mcp.deepwiki.com/mcp
Headers: (none)
Tools: read_wiki_structure, read_wiki_contents, ask_question
The assistant can answer questions about any public GitHub repository.
Display name: HubSpot CRM
Identifier: hubspot
Server URL: https://your-mcp-host.example.com/mcp
Headers:
  Authorization: Bearer pat-xxxxxxxx
The assistant can look up contacts, create deals, or update records during a call.

​
Best practices & security

Only connect MCP servers you trust. The tools and the data they return are provided by the remote server and are passed to the AI during live conversations.
  • Keep tokens scoped to the minimum permissions the assistant needs.
  • Use Manage tools to expose only the tools an assistant actually requires.
  • Give each tool a clear name and description on the server so the AI knows when to use it.
  • Mention the available capabilities in your assistant’s system prompt so it uses them at the right moments.
Test with simple conversations first and confirm the assistant calls the right tool with the right parameters before going live.