Using slim.to with Gemini

Two ways in: the MCP server (Gemini CLI, Google GenAI SDK) or the REST API (function calling, scripts).

Prerequisite for both: a personal API key.

Approach 1 — MCP server

Gemini CLI

Add the server to ~/.gemini/settings.json (global) or .gemini/settings.json in a project:

{
  "mcpServers": {
    "slimto": {
      "command": "uvx",
      "args": ["--from", "/path/to/slimto/mcp", "slimto-mcp"],
      "env": {
        "SLIMTO_API_KEY": "slim_your_key_here"
      }
    }
  }
}

Restart the CLI and check with /mcp — the four slimto tools should be listed. Then:

You: Generate the launch one-pager as HTML and give me a slim.to link.

Gemini: (writes the file, calls create_link_from_file) Your link: https://slim.to/9c4oww

Google GenAI SDK (Python)

The google-genai SDK accepts a live MCP ClientSession directly as a tool:

import asyncio
from google import genai
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client

client = genai.Client()  # GEMINI_API_KEY in env

server = StdioServerParameters(
    command="uvx",
    args=["--from", "/path/to/slimto/mcp", "slimto-mcp"],
    env={"SLIMTO_API_KEY": "slim_your_key_here"},
)

async def main():
    async with stdio_client(server) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()
            response = await client.aio.models.generate_content(
                model="gemini-2.5-pro",
                contents="Shorten https://example.com/signup as slug 'launch' and report the link.",
                config=genai.types.GenerateContentConfig(tools=[session]),
            )
            print(response.text)

asyncio.run(main())

Approach 2 — REST API

Declare slim.to operations as ordinary Gemini function tools and implement them with HTTP calls:

import os, requests
from google import genai
from google.genai import types

def create_short_link(target_url: str, title: str = "") -> dict:
    """Create a tracked slim.to short link for a URL."""
    r = requests.post(
        "https://slim.to/api/v1/links",
        headers={"X-API-Key": os.environ["SLIMTO_API_KEY"]},
        json={"target_url": target_url, "title": title or None},
    )
    r.raise_for_status()
    return {"short_url": r.json()["short_url"]}

client = genai.Client()
response = client.models.generate_content(
    model="gemini-2.5-pro",
    contents="Shorten https://example.com/pricing and give me the link.",
    config=types.GenerateContentConfig(tools=[create_short_link]),  # auto function calling
)
print(response.text)

For file uploads and analytics, add functions wrapping POST /api/v1/files (multipart) and GET /api/v1/analytics/links/{id} — see the API quickstart for the exact shapes.

Which approach?