Communication
Connect Mailgun
Developer-focused transactional email sending and routing API.
Communication
Mailgun
Developer-focused transactional email sending and routing API.
Basic authScoped proxy
Connect with basic credentials
The client enters the required username, token, or secret pair in the hosted connect flow. CybrLink keeps credentials out of the agent and enforces provider scope before proxy execution.
Where to get your Mailgun API keyStep 1
Open the portal connect flow
Step 2
Enter provider credentials
Step 3
Limit write scope before launch
Sample request
// 1. Mint a session token for the end user
const session = await link.connect.session({
integrationKey: "mailgun",
userId: "u_42",
});
// 2. After the user enters their provider credentials, proxy a request
const res = await link.proxy("mailgun", "u_42", {
method: "GET",
endpoint: "/api/v1/me",
});More in this category
Mailgun + AI agents: common questions
- How do I connect Mailgun to an AI agent?
- Create a free CybrLink account, open the dashboard, and click Connect on Mailgun. You authorize once with basic credentials; CybrLink stores the credential in its token vault and your agent reaches Mailgun through the CybrLink MCP server or the agent proxy API. The credential itself is never placed in the model's context.
- Does Mailgun work with Claude, GPT, and other MCP clients?
- Yes. CybrLink exposes a remote MCP (Model Context Protocol) server, so any MCP-capable client or agent framework — including Claude, OpenAI-based agents, and custom agents — can call Mailgun once you've connected it. Non-MCP agents can use the authenticated HTTP proxy instead.
- Is it safe to give an AI agent access to Mailgun?
- CybrLink scopes every connection to the permissions you grant, keeps tokens out of the model, logs each call to an activity audit trail, and lets you revoke the Mailgun connection at any time from the dashboard.