MCP Connector

Query Polarsteps Travel Data with AI

MCP server giving Claude access to Polarsteps travel data - profiles, trip details, and stats via natural language.

Works with polarsteps

90
Spark score
out of 100
Updated Jul 2025
Version 1.0.0
Models
claudeuniversal

Add to Favorites

Why it matters

Enable AI assistants like Claude to access and query your Polarsteps travel data. Understand user profiles, trip details, and travel statistics through natural language.

Outcomes

What it gets done

01

Retrieve user profiles and social statistics.

02

Access detailed trip information and timelines.

03

Search trips by destination, theme, or keywords.

04

Analyze travel statistics and achievements.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-polarsteps | bash

Capabilities

Tools your agent gets

get_user_profile

Retrieve user profile information, social statistics, and travel metrics from Polarsteps

get_trip_details

Access detailed trip information, timelines, and locations for a specific trip

search_trips

Search trips by destination, theme, or keywords with fuzzy matching capabilities

get_travel_statistics

Get comprehensive travel statistics and achievements for a user

Overview

Polarsteps MCP Server

An MCP server that gives Claude access to Polarsteps travel data - user profiles, trip details, and travel statistics - searchable via natural language. It relies on an undocumented Polarsteps API and a user's own remember_token cookie for authentication. Use when you want Claude to answer questions about a specific Polarsteps user's trips or travel stats, after reading the package's legal disclaimer.

What it does

This MCP server gives Claude and other AI assistants access to Polarsteps travel data - user profiles, trip details, timelines and locations, and travel statistics and achievements - queryable and searchable through natural language, including fuzzy search by destination, theme, or keyword.

When to use - and when NOT to

Use it when you want Claude to answer questions about a specific Polarsteps user's trips, travel stats, or history - for example travel stats for a given username, details of a specific trip, or bucket-list suggestions based on past travel. Do NOT use it without first reading the associated legal disclaimer and terms of use: it accesses Polarsteps data through undocumented APIs via the polarsteps-api package, and using this server means agreeing to that package's terms and accepting the associated risks. It also requires the target account's own remember_token authentication cookie, not a public API key.

Capabilities

Four feature areas: user profiles (profile info, social stats, and travel metrics), trip data (detailed trip information, timelines, and locations), smart search (finding trips by destination, theme, or keyword with fuzzy matching), and travel analytics (comprehensive travel statistics and achievements).

How to install

Not yet published to PyPI; install via Smithery:

npx -y @smithery/cli install @remuzel/polarsteps-mcp --client claude

Then obtain your Polarsteps remember_token: log in at polarsteps.com, open browser DevTools (Firefox: Shift+F9 -> Storage tab; Chrome: F12 -> Application tab -> Cookies), find the remember_token cookie for polarsteps.com, and copy its value. Set it as the POLARSTEPS_REMEMBER_TOKEN environment variable, or add it to the env block of the server's entry in your Claude Desktop configuration alongside a command: "uvx" invocation of polarsteps-mcp. Test locally with the MCP Inspector (npx @modelcontextprotocol/inspector uvx --from git+https://github.com/remuzel/polarsteps-mcp polarsteps-mcp), or install from source by cloning the repository and running just setup (or uv sync --dev && uv pip install -e .); just test, just test-mcp, and just lint cover testing and formatting during development.

Who it's for

Polarsteps users, or people with access to a Polarsteps account's remember_token, who want to query their own or another consenting user's travel history conversationally - and who accept the legal risk of relying on an undocumented, unofficial API rather than an official Polarsteps integration.

Source README

Polarsteps MCP Server

A Model Context Protocol (MCP) server that enables Claude and other AI assistants to access Polarsteps travel data. Query user profiles, trip details, travel statistics, and search through travel histories with natural language.

MCP Server Badge Smithery Badge

Features

  • User Profiles: Get profile info, social stats, and travel metrics
  • Trip Data: Access detailed trip information, timelines, and locations
  • Smart Search: Find trips by destination, theme, or keywords with fuzzy matching
  • Travel Analytics: Retrieve comprehensive travel statistics and achievements

Quick Start

Until I add it to PyPI, the quickest way to get started is using Smithery:

npx -y @smithery/cli install @remuzel/polarsteps-mcp --client claude

Then configure your Polarsteps token.

Configuration

You'll need your Polarsteps remember_token to authenticate API requests.

Getting Your Token

  1. Go to https://www.polarsteps.com/ and make sure you're logged in
  2. Open your browser's Dev Tools:
    • Firefox: Shift+F9 → Storage tab
    • Chrome: F12 → Application tab → Cookies
  3. Find the remember_token cookie for https://www.polarsteps.com
  4. Copy the token value

Setting the Token

Set your token as an environment variable:

export POLARSTEPS_REMEMBER_TOKEN="your_remember_token_here"

Usage

With Claude Desktop

Add this configuration to your Claude Desktop settings:

{
  "mcpServers": {
    "polarsteps": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/remuzel/polarsteps-mcp", "polarsteps-mcp"],
      "env": {
        "POLARSTEPS_REMEMBER_TOKEN": "your_remember_token_here"
      }
    }
  }
}

Example Queries

Once configured, you can ask Claude things like:

  • "Show me travel stats for username 'johndoe'"
  • "Tell me about johndoe's trip to Japan"
  • "What country should johndoe add to their bucketlist?"

Local Testing

Test the MCP server locally with the inspector:

npx @modelcontextprotocol/inspector uvx --from git+https://github.com/remuzel/polarsteps-mcp polarsteps-mcp

Installation from Source

For development or manual installation:

# Clone the repository
git clone https://github.com/remuzel/polarsteps-mcp
cd polarsteps-mcp

# Setup development environment
just setup
# or without just:
uv sync --dev && uv pip install -e .

Development

Running Tests

just test

Local MCP Testing

just test-mcp

Code Formatting

just lint

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.