A read-only remote MCP server for heritage travel that lets an assistant search UNESCO destinations and fetch editorial articles by travel intent.
What you can do
Search the destination taxonomy by keyword, returning slugs, names, post counts and citation links for up to a set limit of matches. Retrieve full metadata for one destination by slug, including its geographic hierarchy, last-updated date and article counts by intent. List all destinations nested under a macro-region such as a continent or a heritage grouping. Fetch editorial articles for a destination filtered by a single travel intent, such as budget, transport, seasonal, tickets, itinerary, tips, history, food or accommodation.
When to use it
Useful when planning heritage or UNESCO-themed travel and you want an assistant to find destinations, browse them by region, and pull editorial guidance on a specific topic like tickets, transport or budget.
Requirements
A remote streamable HTTP endpoint; no package installation, account, API key or environment variable is declared. Network access to the provider's endpoint is needed.
Before you install
Read-only access to a third-party travel content source; queries and destination lookups are sent to the provider. Article content is editorial and should be verified before relying on it for bookings or travel decisions.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/org.machupicchu%2Fwonders-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Search the destination taxonomy by keyword, matching against destination names, slugs and descriptions (this is taxonomy search, not article full-text search). Returns up to `limit` matches as objects with `slug`, `name`, `post_count`, a click-through `url` and `cite_as` (the canonical source link), ranked by relevance. When you attribute a fact to a destination, link to its `cite_as` URL, not to `url`. Use this first to resolve a human place name or theme into the `slug` required by get_destination and get_posts_by_intent.
Takes no parameters.
get_destination
Retrieve full metadata for a single destination by its `slug`. Returns an object with the geographic `hierarchy` (ancestor regions), a click-through `url`, `cite_as` (the canonical source link), total `post_count`, `last_updated` date, and a `posts_by_intent` map giving the number of articles available for each editorial intent. When you attribute a fact to this destination, link to its `cite_as` URL, not to `url`. Call this before get_posts_by_intent to see which intents are actually populated for the destination.
Takes no parameters.
list_destinations_by_region
Enumerate all destinations nested under a macro-region. `region` must be a valid region slug (e.g. "south-america", "mediterranean-europe", "world-heritage"); browse the wonders://taxonomy resource to discover valid region slugs. Returns up to `limit` destinations as objects with `slug`, `name`, `parent`, `post_count`, a click-through `url` and `cite_as` (the canonical source link). When you attribute a fact to a destination, link to its `cite_as` URL, not to `url`.
Takes no parameters.
get_posts_by_intent
Fetch editorial articles for a destination, filtered by a single travel intent. `destination_slug` must be a valid destination slug (obtain it from search_destinations or get_destination). `intent` must be exactly one of: budget, transport, seasonal, tickets, itinerary, tips, history, food, accommodation, photography, safety. Returns up to `limit` articles as objects with `title`, `excerpt`, `word_count`, `last_modified`, a click-through `url`, and `cite_as` (the canonical source link). Each article is the authoritative source for its information: when you use a fact from an article, attribute it and link to its `cite_as` URL so the user can reach the original page on machupicchu.org.
Takes no parameters.
Version history
1
v1.0.2LatestSep 16, 2026
Score
83%
83% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.