# wander-agent

Connects your AI client to live flight searches, hotel listings, visa rules, and weather forecasts. Useful for building complete travel plans without manual lookups.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 8
- Author: VirajMishra1
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/VirajMishra1/wander-agent
- Updated: 2026-10-04
- HTML: https://affpapa.org/en/nevibecode/mcp/wander-agent

## What it does

This server connects coding agents to travel aggregators and public datasets. It checks flight combinations across Google Flights and Kiwi simultaneously, uncovering split-ticket routes and hidden-city layovers. It also queries accommodation listings, estimates spending across 220 cities, and pulls nearby venue details from OpenStreetMap.

The integration handles documentation checks. It reviews transit requirements, evaluates visa-free access using 2024 Henley rankings, and contrasts allowances between two separate passports. Travelers also get safety updates from the US State Department, jet lag schedules, and 16-day climate projections via Open-Meteo.

You need Python 3.10 or newer on your machine. No third-party API tokens are required, so the server operates straight out of the box through `uvx`.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add wander-agent -- uvx wander-agent
```
uvx runs the command named after the package; if the README names another one, use uvx --from wander-agent <command>

### Codex

**Platform CLI**
```bash
codex mcp add wander-agent -- uvx wander-agent
```
uvx runs the command named after the package; if the README names another one, use uvx --from wander-agent <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "wander-agent": {
            "command": "uvx",
            "args": [
                "wander-agent"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from wander-agent <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "wander-agent": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "wander-agent"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from wander-agent <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add wander-agent uvx wander-agent
```
uvx runs the command named after the package; if the README names another one, use uvx --from wander-agent <command>

## When to use it
- find split-ticket flights and hidden-city fare discounts
- verify transit and entry visa rules between specific countries
- calculate daily trip costs for target cities
- generate multi-day travel schedules paired with 16-day weather forecasts

## Example prompts
- Check hidden-city and split-ticket flight options from New York to Tokyo for next month.
- Build a 10-day travel schedule for two in Bali on a $3,000 budget including entry rules and weather.
- Compare my two passports to see which destinations are unlocked by each one.

## Similar
- [trvl](https://affpapa.org/en/nevibecode/mcp/trvl.md) — MCP server · ★ 90
- [LetsFG — Flights & Hotels](https://affpapa.org/en/nevibecode/mcp/letsfg-flights-hotels.md) — MCP server · ★ 2197
- [Viajante](https://affpapa.org/en/nevibecode/mcp/viajante.md) — MCP server · ★ 36
- [Gondola Award Travel Search](https://affpapa.org/en/nevibecode/mcp/gondola-award-travel-search.md) — MCP server · ★ 9
- [travel-search-and-booking-api-and-skills](https://affpapa.org/en/nevibecode/plugins/travel-search-and-booking-api-and-skills.md) — plugin · ★ 1272
- [variflight-mcp](https://affpapa.org/en/nevibecode/mcp/variflight-mcp.md) — MCP server · ★ 33

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md