SW

shaikhspeare/wanderlog-mcp

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

162 stars 66 forks 质量 90 趋势 38MIT

shaikhspeare/wanderlog-mcp 是从 https://github.com/shaikhspeare/wanderlog-mcp. 导入的 MCP 服务器候选

概览

shaikhspeare/wanderlog-mcp 是从 https://github.com/shaikhspeare/wanderlog-mcp. 导入的 MCP 服务器候选

概述(AI 翻译)

一个MCP服务器,允许Claude(或任何兼容MCP的代理)通过对话查看并构建Wanderlog行程。

你不必点击Wanderlog的UI来规划行程,只需询问:

“创建为期14天的日本黄金路线之旅——东京、箱根、京都、奈良和大阪。”

客服会调用工具,交错地点和每日笔记,添加酒店楼、渡轮、公交车、火车、租车和清单,几分钟内你就能完成满员的Wanderlog之旅。

看真实例子: 14天日本黄金路线——完全由AI代理使用该MCP服务器构建。

最新消息(未发行)

  • 自定义列表生命周期操作现在拒绝重复或歧义的节标题,而不是静默更改第一个匹配。
  • wanderlog_search_hotels — 在 Airbnb、Expedia、Google 和 Kayak 上搜索 Wanderlog 的酒店聚合器。退货排名优惠,支持按供应商价格比较和分面筛选发现,使 LLM 无需记忆 Wanderlog 内部枚举值。

本页由 AI 翻译,技术细节请以原文为准。

README

以下为原文 README 节选,完整内容请查看原文。

wanderlog-mcp

An MCP server that lets Claude (or any MCP-compatible agent) view and build Wanderlog trip itineraries through conversation.

Instead of clicking through the Wanderlog UI to plan a trip, you just ask:

“Create a 14-day Japan Golden Route trip — Tokyo, Hakone, Kyoto, Nara, and Osaka.”

The agent calls the tools, interleaves places and notes for each day, adds hotel blocks, ferries, buses, trains, rental cars, and checklists, and you end up with a fully populated Wanderlog trip in a few minutes.

See a real example: 14-day Japan Golden Route — built entirely by an AI agent using this MCP server.

What’s New (Unreleased)

  • Custom-list lifecycle operations now reject duplicate or ambiguous section headings instead of silently changing the first match.
  • wanderlog_search_hotels — search Wanderlog’s hotel aggregator across airbnb, expedia, google, and kayak. Returns ranked offers with per-vendor price comparison and faceted filter discovery so the LLM never has to memorise Wanderlog’s internal enum values.
  • A failed startup authentication probe now gets one shared retry on the first tool call, allowing valid sessions to recover from a transient network or proxy error without restarting the server.
  • wanderlog_add_place accepts an optional place_id, so wanderlog_search_places (response_format: "detailed") now has somewhere to send its results — pass the id straight through to add the exact candidate when a name matches multiple branches or the wrong city, instead of hoping the top autocomplete match is right.
  • wanderlog_annotate_place now replaces a place’s existing note instead of appending the new text to it, including notes that contain images.
  • Place lookups no longer fail with “Place not found” when Wanderlog’s autocomplete returns an entry with no place ID ahead of the real result. This affected adding places, hotels, journal stops and transit endpoints, and wanderlog_search_places listed those entries as undefined.

What’s New in v0.3.1

  • Wanderlog rate-limits rapid edits — burst mutations (an LLM building a full itinerary) now retry automatically with backoff instead of failing with an opaque “Submit op timeout”.
在 GitHub 查看完整 README

安装

npx wanderlog-mcp
新手?先看 mcpskill.org 教程 →

配置

{ "mcpServers": { "wanderlog": { "command": "npx", "args": ["wanderlog-mcp"], "env": { "WANDERLOG_COOKIE": "s%3A...your value here..." } } } }