Diga MCP server for AI assistants

Use Diga’s hosted Model Context Protocol (MCP) server to build and manage voice agents from compatible AI assistants and development tools.

This page explains how to connect an assistant to Diga. To give a Diga voice agent access to an external MCP server during a call, see MCP integrations.

Prerequisites

Before you begin, you need:

A Diga account that belongs to at least one project
An MCP client that supports remote servers over Streamable HTTP
Only if you use an API key instead of signing in: a Diga API key from the project you want to manage. Follow Create an API key and create a restricted key with only the permissions your assistant needs.

What you can do

The Diga MCP server turns Diga API operations into tools your assistant can discover and call. Depending on your permissions, you can use natural language to:

Create, update, publish, list, and inspect voice agents and their versions
Create calls and retrieve call details, messages, recordings, logs, and traces
Create and maintain knowledge bases from text, URLs, and files
Manage phone numbers, voices, integrations, webhooks, and workflows
Review project members, usage, billing, and other project resources

Your MCP client shows the exact tools available to it, including each tool’s description and required parameters.

Choose how to authenticate

Your MCP client connects to Diga over Streamable HTTP. Choose one of two ways to authenticate:

	Sign in with Diga (OAuth)	API key
Setup	Add the server URL only. Your client opens a browser window where you sign in to Diga.	Add the server URL plus an `x-api-key` header.
Permissions	Your role in the project	The key’s restrictions
Project	Any project you belong to. Pick one after connecting and switch at any time.	Fixed to the project where the key was created
Best for	People using an assistant interactively	Scripts, shared environments, and clients without OAuth support

Setting	Value
Server name	`diga`
Server URL	`https://mcp.diga.io/mcp`
API key header (API key only)	`x-api-key: <DIGA_API_KEY>`

Signing in with Diga: your account can belong to several projects, so the server needs to know which one to work on. The first time you ask for something, the assistant lists your projects and asks you to choose one. It can also call the diga_select_project tool directly. The choice is remembered for 24 hours, and you can switch projects at any time by asking the assistant.Using an API key: the key belongs to the project where you created it, so no selection is needed. To manage another project, replace the key with one from that project.

Connect your MCP client

Choose your client. For the API key option, replace <DIGA_API_KEY> with your complete Diga API key.

Claude (web and desktop)
Claude Code
Cursor
Codex
Other clients

Open Settings → Connectors → Add custom connector, name it Diga, and enter https://mcp.diga.io/mcp as the URL. When you enable the connector, Claude opens a browser window to sign in to Diga.To use an API key instead, open Request headers in the connector settings and add x-api-key with your key as the value. If your version of Claude does not show that option, use the mcp-remote bridge in Claude Desktop (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "diga": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.diga.io/mcp", "--header", "x-api-key:<DIGA_API_KEY>"]
    }
  }
}

claude mcp add --transport http diga https://mcp.diga.io/mcp

Then run /mcp inside Claude Code and choose diga to complete the sign-in in your browser.Use an API key instead:

claude mcp add --transport http diga \
  --header "x-api-key: <DIGA_API_KEY>" \
  https://mcp.diga.io/mcp

Open Cursor Settings → MCP → Add new global MCP server. To sign in with Diga, add only the URL and complete the sign-in when Cursor opens your browser:

{
  "mcpServers": {
    "diga": {
      "url": "https://mcp.diga.io/mcp"
    }
  }
}

To use an API key instead, add the header:

{
  "mcpServers": {
    "diga": {
      "url": "https://mcp.diga.io/mcp",
      "headers": {
        "x-api-key": "<DIGA_API_KEY>"
      }
    }
  }
}

Add the server to ~/.codex/config.toml:

[mcp_servers.diga]
url = "https://mcp.diga.io/mcp"

To sign in with Diga, run codex mcp login diga and complete the sign-in in your browser.To use an API key instead, add bearer_token_env_var = "DIGA_API_KEY" to the block above and set the variable before starting Codex:

export DIGA_API_KEY="<DIGA_API_KEY>"

Codex sends this value as Authorization: Bearer <DIGA_API_KEY>, which the Diga MCP server also accepts.

Configure a remote Streamable HTTP server with the URL https://mcp.diga.io/mcp. Clients that support OAuth discover Diga’s sign-in automatically and open a browser window. For API key access, add the header:

{
  "name": "diga",
  "url": "https://mcp.diga.io/mcp",
  "headers": {
    "x-api-key": "<DIGA_API_KEY>"
  }
}

Never put an API key in the server URL or commit it to source control. URLs can appear in browser history, proxy logs, and analytics. Prefer environment-variable support when your MCP client provides it.

Verify the connection

After saving the configuration, restart or reload your MCP client. Check that a server named diga appears and that its tools are available. Start with a read-only request such as:

List my Diga agents.

If you signed in with Diga and belong to more than one project, the assistant first asks which project to use. Your client should ask for approval before running a tool if its permission settings require confirmation.

Troubleshooting

The assistant asks me to select a project

You signed in with Diga and have not chosen a project yet, or the choice expired after 24 hours. Tell the assistant which project to use, or ask it to list your projects first.

The connection fails because two-factor authentication is required

Your Diga account has two-factor authentication enabled. The authorization screen asks for your code during sign-in. If the connection was approved without it, disconnect and reconnect the Diga server in your MCP client and enter the code when asked. Alternatively, connect with an API key.

The server returns 401 Unauthorized

If you signed in with Diga, your session may have expired. Disconnect and reconnect the server to sign in again. If you use an API key, confirm that you copied the complete key and that the client sends it as x-api-key without the Bearer prefix. If you use the Authorization header instead, its value must be Bearer <DIGA_API_KEY>.

A tool returns 403 Forbidden

You are authenticated but do not have permission to use that resource. If you signed in with Diga, ask a project administrator to update your role. If you use an API key, update the key’s restrictions in Settings → Project → API Keys, or use a different restricted key with the required permission.

The assistant shows the wrong company or no resources

If you signed in with Diga, ask the assistant to switch to the intended project. If you use an API key, the key determines the project. Replace it with a key created in the intended Diga project, then restart the MCP client so it reloads the configuration.

The client cannot connect to the server

Verify that the URL is exactly https://mcp.diga.io/mcp and that the client supports remote MCP servers using Streamable HTTP. Some clients require a restart after configuration changes.

Security recommendations

Prefer signing in with Diga for interactive use. Access follows your role and ends when you disconnect.
When you use API keys, create a separate key for each MCP client and environment
Grant only the read or write permissions the assistant needs
Review tool calls before approving actions that change or delete resources
Rotate a key immediately if it is exposed

​Prerequisites

​What you can do

​Choose how to authenticate

​Connect your MCP client

​Verify the connection

​Troubleshooting

​Security recommendations

Prerequisites

What you can do

Choose how to authenticate

Connect your MCP client

Verify the connection

Troubleshooting

Security recommendations