Polarsteps MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Polarsteps MCP Server show me my travel stats"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This MCP server uses the polarsteps-api package to access Polarsteps data through undocumented APIs. Important: Please read the associated legal disclaimer and terms of use before using this tool. By using this MCP server, you agree to the terms outlined in the API package and acknowledge the associated risks.
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.
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
Related MCP server: Flight Ticket MCP Server
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 claudeThen configure your Polarsteps token.
Configuration
You'll need your Polarsteps remember_token to authenticate API requests.
Getting Your Token
Go to https://www.polarsteps.com/ and make sure you're logged in
Open your browser's Dev Tools:
Firefox: Shift+F9 → Storage tab
Chrome: F12 → Application tab → Cookies
Find the
remember_tokencookie for https://www.polarsteps.comCopy 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-mcpInstallation 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 testLocal MCP Testing
just test-mcpCode Formatting
just lintAvailable Tools
7 toolsget_tripA
Get comprehensive details about a specific trip including summary, timeline, route information, individual steps/locations, weather data, and engagement metrics. Use after get_trip_log when you need detailed information about specific locations or comprehensive trip data.
Inputs: trip_id (required), n_steps.
get_trip_logB
Get an overview of the specific trip; this includes just a list of summarized steps, each including timestamp/title/description/location. Use this first for trip overviews before diving into detailed information.
Inputs: trip_id (required).
get_tripsA
Fetch a list of a user's recent trips with summary information including trip names, dates, duration, and basic stats. Ideal for browsing someone's travel history or finding trip IDs for detailed exploration. Use n_trips parameter to control how many recent trips to retrieve (default: 5).
Inputs: username (required), n_trips.
get_user_profileC
Get a users' profile overview including their living location and their number of countries visited & trips.
Inputs: username (required).
get_user_socialC
Get a users' social information including: followers, followees, their count and if they're considered popular.
Inputs: username (required).
get_user_statsB
Get available travel statistics and metrics for a Polarsteps user, including countries visited, total distance traveled, trip counts, and detailed travel analytics. Perfect for getting a complete picture of someone's travel history and achievements.
Inputs: username (required).
search_tripsA
Search through a user's trips by name/title using fuzzy matching to find specific trips. Ideal for finding trips by destination (e.g., 'japan', 'italy'), themes (e.g., 'honeymoon', 'business'), or partial name matches. Supports flexible search terms that don't need to match exactly - the fuzzy matching will find relevant trips even with approximate spelling or partial keywords. Use this as the first step when looking for specific trips by destination, theme, or name.
Inputs: username (required), name_query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
The tools are mostly distinct with clear purposes, but there is some overlap between get_trip and get_trip_log that could cause confusion. get_trip_log is described as an 'overview' with summarized steps, while get_trip provides 'comprehensive details', but the descriptions suggest using get_trip_log first before get_trip, which might lead to misselection if an agent needs just basic info versus full details. Other tools like get_user_profile, get_user_social, and get_user_stats are well-differentiated.
All tool names follow a consistent verb_noun pattern with underscores, such as get_trip, get_trips, get_user_profile, and search_trips. There are no deviations in naming conventions, making the set predictable and easy to understand for an agent.
With 7 tools, the server is well-scoped for a Polarsteps travel data domain. Each tool serves a specific purpose, from fetching user profiles and social info to retrieving trip details and searching, without feeling too sparse or overloaded. The count aligns well with the apparent scope of accessing travel history and user data.
The tool set covers key aspects of the Polarsteps domain, including user profiles, social information, statistics, and trip retrieval with search capabilities. However, there are minor gaps, such as no tools for updating or creating trips (e.g., create_trip or update_trip), which might limit full CRUD operations, but the existing tools support comprehensive read and search workflows effectively.
Maintenance
Related MCP Connectors
Polarsteps MCP server for ChatGPT, Claude and any AI agent: export trip, import steps and list trips in your own Polarsteps account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Polarsteps yourself; Cotlet does not store your password and you need no Polarsteps API key. About the official Polarsteps API: Polarsteps has no public API and no official MCP server (checked 11 Oct 2026). The only official way out of the app is "Download my data", an archive of your whole account that arrives by email, and there is no way to create trips or add steps from outside the app and website. Setup and FAQ: https://cotlet.dev/integrations/polarsteps-api-mcp-server
All-in-one travel planner and tracker for perpetual travelers and digital nomads, in your AI chat.
Plan trips with your AI: cards, itinerary, board, files and comments, with role-aware OAuth access.
Travel ledger for AI agents. Log journeys, stays and expenses from booking emails, then get tax-residency day counts, Schengen 90/180 status and your current country from your own travel history.
Related MCP Servers
- AlicenseAqualityDmaintenanceA TypeScript server that acts as a bridge to the Strava API, enabling LLMs to access users' activities, routes, segments, and athlete data through natural language interaction.24496 npm509MIT
- AlicenseBqualityDmaintenanceA server that provides real-time flight information query capabilities to AI assistants, allowing them to access detailed flight statuses, airport details, and related travel information.1051MIT
- AlicenseNot gradedqualityDmaintenanceA comprehensive travel aggregation server that enables AI assistants to search for flights and hotels, track flight statuses in real-time, and retrieve airport information. It integrates with Amadeus and AviationStack APIs to provide data on pricing, schedules, and travel routes through natural language.4MIT
- FlicenseCqualityDmaintenanceEnables AI assistants to manage a self-hosted AirTrail flight tracking instance, providing natural language access to flight data, travel history, and statistics.33-