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 workspace (Claude Desktop, Cursor, Antigravity, Windsurf, VS Code, Zed, etc.), your AI can autonomously shorten destination URLs, customize custom slugs/aliases, check plan quotas, and update destination targets.

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.
• Seamless Auth Flow: Supports both OAuth 2.0 (Google/Surli) and Direct API Key (X-API-KEY) authentication.

Quickstart Guide (1-Minute Setup)

Connecting Surli MCP Server to your favorite AI environment takes less than a minute. Choose your AI client below or refer to the complete AI Clients Reference section.

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 JSON-RPC protocol over standard transports like SSE (Server-Sent Events) and HTTP.

Authentication Methods

Surli MCP Server supports two flexible authentication mechanisms: API Key Authentication for direct client integration, and OAuth 2.0 (Google/Surli OAuth) for seamless browser-based authentication.

X-API-KEY: YOUR_SURLI_API_KEY

Endpoints & Transport Protocol

Surli MCP Server supports both Server-Sent Events (SSE) for real-time streaming sessions and Stateless HTTP JSON-RPC endpoints.

AI Client Setup Configurations (11+ Supported AI Clients)

Below are tested, production-ready configuration blocks for 11 popular AI clients and agent frameworks using the production endpoint https://mcp.surl.li/mcp and SSE stream https://mcp.surl.li/mcp/sse.

{
  "mcpServers": {
    "surli": {
      "command": "npx",
      "args": [
        "-y",
        "@openmcp/cli",
        "run",
        "https://mcp.surl.li/mcp/sse"
      ]
    }
  }
}

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

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

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

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

{
  "mcpServers": {
    "surli": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.surl.li/mcp/sse"]
    }
  }
}

{
  "experimental": {
    "mcpServers": [
      {
        "name": "surli",
        "url": "https://mcp.surl.li/mcp/sse"
      }
    ]
  }
}

{
  "context_servers": {
    "surli": {
      "settings": {
        "url": "https://mcp.surl.li/mcp/sse"
      }
    }
  }
}

mcp_servers:
  surli:
    type: sse
    url: https://mcp.surl.li/mcp/sse

mcpServers:
  surli:
    type: sse
    url: https://mcp.surl.li/mcp/sse

from mcp import ClientSession
from mcp.client.sse import sse_client

async def run_surli():
    async with sse_client("https://mcp.surl.li/mcp/sse") 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 { SSEClientTransport } from "@modelcontextprotocol/sdk/client/sse.js";

const transport = new SSEClientTransport(new URL("https://mcp.surl.li/mcp/sse"));
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.