Surli MCP Server Overview

The Surli Model Context Protocol (MCP) Server connects AI assistants directly to Surli's URL shortener infrastructure, enabling AI models to programmatically create, manage, inspect, and update short links in real-time.

By integrating Surli's MCP Server into your AI agent or desktop workspace (Claude Desktop, Cursor, Google Antigravity, VS Code, Windsurf, etc.), your AI can autonomously shorten URLs, customize aliases, check quotas, and update destinations. Claude Desktop connects with zero API keys via native 1-click OAuth, while clients without OAuth (such as Google Antigravity, Windsurf, Zed, or CLI tools) authenticate by passing a Surli API key via HTTP headers (Authorization: Bearer and X-API-KEY).

Key Features & Capabilities:

• Zero-friction URL Shortening: Create shortened URLs directly from AI chat conversations.
• Dynamic Destination Updates: Remap existing short link destinations on the fly.
• Custom Alias Management: Assign custom slugs/aliases to your short URLs.
• Real-Time Quota Tracking: Track link usage, plan tiers, and remaining monthly quota.
• Flexible Authentication: 1-click browser OAuth for Claude Desktop (zero keys required) and header-based API key auth (Authorization & X-API-KEY) for Google Antigravity & non-OAuth tools.

Quickstart Guide (1-Minute Setup)

Connecting Surli MCP Server to your AI environment takes less than a minute. For Claude Desktop, no API key is needed (native 1-click OAuth). For Google Antigravity and other clients without OAuth, pass your Surli API key in headers.

{"mcpServers":{"surli":{"url":"https://mcp.surl.li/mcp"}}}

{"mcpServers":{"surli":{"serverUrl":"https://mcp.surl.li/mcp","headers":{"Authorization":"Bearer YOUR_API_KEY","X-API-KEY":"YOUR_API_KEY"}}}}

What is MCP (Model Context Protocol)?

The Model Context Protocol (MCP) is an open specification created by Anthropic that standardizes how Artificial Intelligence applications (LLMs, AI agents, IDEs) communicate with external data sources, APIs, and tools.

Instead of custom API integrations for every single AI app, MCP provides a unified protocol supporting OAuth 2.0 and API Key (Bearer Token) authorization over standard transports like HTTP and SSE (Server-Sent Events).

Authentication Protocol

Surli MCP Server supports two authentication paths: Native 1-Click OAuth 2.0 (zero API keys needed) and API Key Headers (required for clients without OAuth).

{
  "mcpServers": {
    "surli": {
      "serverUrl": "https://mcp.surl.li/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY",
        "X-API-KEY": "YOUR_API_KEY"
      }
    }
  }
}

Endpoints & Transport Protocol

Surli MCP Server supports both API Key (Authorization & X-API-KEY) authentication and OAuth 2.0 Authorization alongside standard HTTP JSON-RPC and Server-Sent Events (SSE) streaming transports.

AI Client Setup Configurations (11+ Supported AI Clients)

Surli MCP Server supports two authentication paths: Native 1-Click OAuth 2.0 and API Key Headers.

{
  "mcpServers": {
    "surli": {
      "url": "https://mcp.surl.li/mcp"
    }
  }
}

{"mcpServers":{"surli":{"url":"https://mcp.surl.li/mcp"}}}

{
  "mcpServers": {
    "surli": {
      "serverUrl": "https://mcp.surl.li/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY",
        "X-API-KEY": "YOUR_API_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "surli": {
      "serverUrl": "https://mcp.surl.li/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY",
        "X-API-KEY": "YOUR_API_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "surli": {
      "serverUrl": "https://mcp.surl.li/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY",
        "X-API-KEY": "YOUR_API_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "surli": {
      "serverUrl": "https://mcp.surl.li/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY",
        "X-API-KEY": "YOUR_API_KEY"
      }
    }
  }
}

{
  "experimental": {
    "mcpServers": [
      {
        "name": "surli",
        "url": "https://mcp.surl.li/mcp",
        "requestOptions": {
          "headers": {
            "Authorization": "Bearer YOUR_API_KEY",
            "X-API-KEY": "YOUR_API_KEY"
          }
        }
      }
    ]
  }
}

{
  "context_servers": {
    "surli": {
      "settings": {
        "serverUrl": "https://mcp.surl.li/mcp",
        "headers": {
          "Authorization": "Bearer YOUR_API_KEY",
          "X-API-KEY": "YOUR_API_KEY"
        }
      }
    }
  }
}

mcp_servers:
  surli:
    serverUrl: https://mcp.surl.li/mcp
    headers:
      Authorization: "Bearer YOUR_API_KEY"
      X-API-KEY: "YOUR_API_KEY"

mcpServers:
  surli:
    serverUrl: https://mcp.surl.li/mcp
    headers:
      Authorization: "Bearer YOUR_API_KEY"
      X-API-KEY: "YOUR_API_KEY"

{
  "mcpServers": {
    "surli": {
      "serverUrl": "https://mcp.surl.li/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY",
        "X-API-KEY": "YOUR_API_KEY"
      }
    }
  }
}

from mcp import ClientSession
from mcp.client.http import http_client

async def run_surli():
    headers = {
        "Authorization": "Bearer YOUR_API_KEY",
        "X-API-KEY": "YOUR_API_KEY"
    }
    async with http_client("https://mcp.surl.li/mcp", headers=headers) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()
            tools = await session.list_tools()
            print("Connected to Surli MCP! Tools available:", [t.name for t in tools.tools])

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { HTTPClientTransport } from "@modelcontextprotocol/sdk/client/http.js";

const transport = new HTTPClientTransport(new URL("https://mcp.surl.li/mcp"), {
  requestInit: {
    headers: {
      "Authorization": "Bearer YOUR_API_KEY",
      "X-API-KEY": "YOUR_API_KEY"
    }
  }
});
const client = new Client({ name: "SurliAgent", version: "1.0.0" }, { capabilities: {} });
await client.connect(transport);

const tools = await client.listTools();
console.log("Surli Tools:", tools);

Usage Examples & AI Prompts

Once Surli MCP Server is enabled in your AI agent, you can talk to your AI in plain conversational language. The AI agent will automatically call the appropriate Surli MCP tool.