Skip to main content
Gumloop supports connecting to any Model Context Protocol (MCP) server. This lets you extend your agents with specialized tools, internal services, or any MCP-compatible API.
Gumloop already has 50+ pre-built MCP servers for popular services like GitHub, Slack, Notion, HubSpot, and more. These work out of the box with agents. Browse available integrations before setting up a custom server.

​
Adding a custom MCP server

Setting up a custom MCP server takes just a few steps.
1

Go to Connectors

Select Customize in the left sidebar, then the Connectors tab. Click the + button in the top-right corner of the page. On wider screens, this button is labeled Add Custom MCP. The Connect MCP Server dialog opens.
Connectors page with the + button highlighted in the top-right corner
2

Enter the server URL

Enter your server’s address in MCP Server URL, then click Connect.
Connect MCP Server dialog with the MCP Server URL field and Connect button highlighted
When connecting at the organization level, if your organization has a Managed Tunnel and you have permission to manage tunnels, the dialog first asks for a Connection type:
3

Configure authentication

Gumloop probes the server and shows the Detected Auth method. If the server supports OAuth, click Authenticate and sign in to connect your account. For key-based authentication, open the Authentication dropdown and select API Key / Credentials to supply a token, API key, or custom header.
Configure dialog showing Detected Auth: OAuth 2.0, with the Authentication selector and Authenticate button highlighted
4

Add it to your agent

Open your agent and click + Add in the Connectors section.
Agent Connectors section with the + Add button highlighted
In the Add Connectors dialog, search for the server you just added in Search connectors, then click + next to it.
Add Connectors dialog with the search field and the + button next to an example MCP server highlighted
Click Save in the top-right corner of the dialog.
Add Connectors dialog with Save highlighted after selecting an MCP server
You can also click Add Custom MCP at the top of the dialog’s left sidebar to connect a new server without leaving the agent.
Team vs Personal credentials: You can store credentials at the personal level (only you can use them) or team level (shared with your team). Choose the appropriate scope when setting up. Learn more about credentials here

​
Requirements

Custom MCP servers must meet these requirements:
Local MCP servers cannot be connected directly. Make your server accessible through a public URL or, for Enterprise organizations, a Managed Tunnel. Services like Cloudflare Tunnels or ngrok can expose local servers if needed.
On Enterprise? Managed Tunnels reaches MCP servers inside your network without opening inbound ports or running your own tunnel. Each becomes an organization-wide Proxied MCP rather than a personal credential.

​
Authentication options

Gumloop supports multiple authentication methods:
  • Bearer tokens: Standard OAuth/API key authentication. When you provide an Access Token / API Key, Gumloop sends it as an Authorization: Bearer <token> header with every request to your MCP server.
  • Custom headers: For services requiring specific header formats. The Additional Header field accepts a single header in Header-Name: value format (for example, X-API-Key: my-secret-key). This is useful for MCP servers that expect authentication in a non-standard header.
  • OAuth discovery: Automatic OAuth flow discovery (RFC 8414) for compatible servers

​
Using custom MCP servers with agents

Once configured, you can add your custom MCP servers to any agent. The agent can discover all available tools and use them naturally in conversation.
1

Open Agent Configuration

Go to your agent’s settings and find the Connectors section.
2

Select MCP server

Click + Add in the Connectors section, search for your configured MCP server in Add Connectors, add it, and click Save.
3

Use your agent

Your agent now has access to all tools from the MCP server. It automatically discovers and uses them based on conversation context.
What agents give you:
  • Conversational context: The agent maintains conversation history and can use tools across multiple turns
  • Automatic tool selection: The agent chooses the right tool based on your request
  • Multi-server support: Connect multiple MCP servers and let the agent orchestrate between them
  • Available everywhere: Use immediately in chat, Slack, or embedded pages

​
Model-specific differences

Custom MCP servers work across all models in Gumloop, but how they run depends on the provider:
  • Native MCP: The provider (OpenAI/Anthropic) connects directly to your MCP server and executes tools.
  • Backend connector (Gumloop executes tool calls): Gumloop connects to your server and presents tools as regular function calls. When the model invokes one, Gumloop executes it and returns the result to the model.

​
Header handling by model

Anthropic models don’t forward custom headers. If your MCP server relies on a custom header (for example, X-API-Key), use the Access Token / API Key field with a Bearer token instead, or choose OpenAI, Gemini, or Groq.

​
Security considerations

Information in your prompts may be sent to your MCP server. Be mindful of sensitive data and review your server’s data handling policies.
All tools exposed by your MCP server are immediately available to the AI. There are no approval prompts before tool execution. Use appropriate authorization scopes to limit access.
When using multiple MCP servers, consider that data retrieved from one server could be passed to another. Design your prompts accordingly.

​
Troubleshooting

Test with discovery first. Ask your agent to “list available tools” to verify the connection is working before relying on it.

​
Further reading