orbator-mcp server
io.orbator/orbator-mcporbator.iostreamable-httpv0.1.0Scanned
AI visibility checks, software recommendations and tool comparisons from measured AI answer data
4 tools: 4 only read.
- Reads private data · 1
- 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 orbator-mcp server can do
The orbator-mcp server is published by orbator.io, a domain the MCP Registry verified. It has 4 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool reads private data (find_tools); 2 tools bring in text other people can write (find_tools and get_facts).
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 18, 2026, version 0.1.0.
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.
4 tools
Only reads 4Show 4 read-only tools
compareCompare software/tools side by side — a fact-by-fact comparison of two products (pricing, features, integrations, limits) with source URLs and verified dates for every claim.No findings
Why it is in this group
- The name "compare" says "compare": a word for reading.
Description, as the server wrote it Compare software/tools side by side — a fact-by-fact comparison of two products (pricing, features, integrations, limits) with source URLs and verified dates for every claim. Use for "X vs Y" software comparison questions. Accepts product names or domains; pair order does not matter.
find_toolsSoftware recommendations backed by measured AI answer data: find the best software/tools for a category or job, ranked by how often AI assistants (ChatGPT, Claude, Gemini, Perplexi…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "find_tools" says "find": a word for reading.
What it can reach
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
Description, as the server wrote it Software recommendations backed by measured AI answer data: find the best software/tools for a category or job, ranked by how often AI assistants (ChatGPT, Claude, Gemini, Perplexity) actually recommend them in real buyer-style queries — not by ads or affiliate placement. Use when asked "what software/tool should I use for X", "best X tools", or for vendor-neutral software recommendations. Pass the category in plain words (e.g. "uptime monitoring", "CRM for freelancers"); it is fuzzy-matched against published Index categories, and near-miss inputs return suggested categories to retry with. Returns ranked products with recommendation share %, 4-week trend, and per-engine breakdown.
get_ai_indexAI visibility check — which software AI recommends for a category.No findings
Why it is in this group
- The name "get_ai_index" says "get": a word for reading.
Description, as the server wrote it AI visibility check — which software AI recommends for a category. Returns the full AI Recommendation Index for one software category: the complete measured ranking of products AI assistants (ChatGPT, Claude, Gemini, Perplexity) recommend, with recommendation share %, average answer position, per-engine breakdown, 4-week trend, sample size, and methodology. Use to answer "does AI recommend <product>" (look up its row and rank), "who is winning AI recommendations in <category>", or to cite AI recommendation-share data. Pass category in plain words or as a slug; omit it (or pass "categories") to list all published categories.
get_factsCanonical software product facts with sources — pricing, features, integrations, platform, and limits, where every fact carries a source URL and a last-verified date.Reads text others writeNo findings
Why it is in this group
- The name "get_facts" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it Canonical software product facts with sources — pricing, features, integrations, platform, and limits, where every fact carries a source URL and a last-verified date. Use to verify software claims (e.g. current pricing) or to gather grounded data before recommending or comparing tools. Accepts a product name or domain (e.g. "hubspot.com").
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 outbound.
- Reads private data1
- 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, 19:14 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 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http orbator https://api.orbator.io/api/mcpclaude mcp add --transport http orbator https://api.orbator.io/api/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__orbator__find_tools",
"mcp__orbator__get_ai_index",
"mcp__orbator__get_facts",
"mcp__orbator__compare"
],
"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 orbator. Review it before you use it.
Capability tags behind 2 rules
- mcp__orbator__find_tools private-data, untrusted-input
- mcp__orbator__get_facts 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.orbator/orbator-mcp/verify?hash=f68d2e75d838d65c089c4a1eddda1a408de8270484a6ef3577a7cb96268474f0" | jq -e '.changed == false'Pinned hash f68d2e75d838, from Nov 18, 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.orbator/orbator-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.orbator/orbator-mcp)Source: MCP Registry. Synced Oct 21, 2026, 18:52 UTC.
orbator-mcp server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the orbator-mcp server safe?
- No scan can promise that. What its definitions show: 4 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 orbator-mcp server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the orbator-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 orbator-mcp server have?
- 4 tools: 4 read. find_tools, get_ai_index, get_facts and compare.
Does the orbator-mcp server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the orbator-mcp server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the orbator-mcp server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.