Aventuro MCP server
io.aventuro/mcpaventuro.iostreamable-httpv0.2.6Scanned
Find travel places (sights, museums, parks, beaches) and read place cards. Read-only, no auth.
2 tools: 2 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Aventuro MCP server can do
The Aventuro MCP server is published by aventuro.io, a domain the MCP Registry verified. It has 2 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
2 tools bring in text other people can write (find_places and get_place).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 15, 2026, version 0.2.6.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
2 tools
Only reads 2Show 2 read-only tools
find_placesUse this when the user asks for places, parks, sights, museums, beaches or things to visit in a city, region or near a point.Reads text others writeNo findings
Why it is in this group
- The name "find_places" says "find": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use this when the user asks for places, parks, sights, museums, beaches or things to visit in a city, region or near a point. Finds interesting places (sights, museums, parks, nature, beaches and more), ordered by popularity. Returns name, category, city, country, coordinates, distance, a link to the place page (url), a popularity score, a stored travel description and one verified photo with its credit (image, or null). For more about one place, call get_place with the last part of its url. Give q (a place, city or country name, optionally with a category, e.g. "valencia" or "zoo valencia"), or lat/lng of the area the user asks about, or both (q narrowed to radius_km around lat/lng). Optional filters: categories, needs, tastes, parking, setting; tags only rank matching places higher. Write each place name as a markdown link [name](url) when url is present, and show each place's url as the source link. When image is present, show image.url as a markdown image with the author credit. visit_minutes is the typical time visitors spend there, not the time to see everything. attributes gives the five needs as true (known yes) or null (unknown, never a no), and matched_needs lists which of the requested needs the place has. setting (indoor, outdoor, both or null) and parking ({free, paid}, each true or null) follow the same rule. matched_tastes and matched_tags list which of the requested tastes and tags the place hit. content_status is no_description when no travel description is stored; fallback_reason is translation_unavailable when lang differs from the requested one. With q, search_area shows the area q was read as. filter_semantics says how the filters combine.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- destructiveHint: false
- openWorldHint: true
get_placeUse this when the user picks a place from find_places or asks to tell more about it: pass slug = the last part of that place's url (or the whole url).Reads text others writeNo findings
Why it is in this group
- The name "get_place" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it Use this when the user picks a place from find_places or asks to tell more about it: pass slug = the last part of that place's url (or the whole url). Returns the full details of one Aventuro place: name, category, city, country, coordinates, a link to the place page, the popularity score, the typical time visitors spend there in minutes (visit_minutes, not the time to see everything) and the whole stored travel description (facts, tips, best time, etiquette and more), plus up to 3 verified photos with author and licence credits (images, may be empty). Write the place name as a markdown link [name](url) when url is present and show the url as the source link. When images are present, show each images[].url as a markdown image with its author credit. attributes gives the five needs as true (known yes) or null (unknown, never a no); matched_needs, matched_tastes and matched_tags are always empty here. setting and parking follow the same true-or-null rule. content_status is no_description when no travel description is stored; fallback_reason is translation_unavailable when lang differs from the requested one.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- destructiveHint: false
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:55 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 0
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.2.6. Values in angle brackets are yours to fill in.
claude mcp add --transport http aventuro https://mcp.aventuro.io/mcpclaude mcp add --transport http aventuro https://mcp.aventuro.io/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__aventuro__find_places",
"mcp__aventuro__get_place"
],
"ask": [],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as aventuro. Review it before you use it.
Capability tags behind 2 rules
- mcp__aventuro__find_places untrusted-input
- mcp__aventuro__get_place untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.aventuro/mcp/verify?hash=6acd12eefd370555be62d8738dc9c87df9e2325633227096274c20236f9bdf7f" | jq -e '.changed == false'Pinned hash 6acd12eefd37, from Nov 15, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.aventuro/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.aventuro/mcp)Source: MCP Registry. Synced Oct 21, 2026, 18:13 UTC.
Aventuro MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Aventuro MCP server safe?
- No scan can promise that. What its definitions show: 2 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the Aventuro MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Aventuro MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Aventuro MCP server have?
- 2 tools: 2 read. find_places and get_place.
Does the Aventuro MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Aventuro MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Aventuro MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.