hn-mcp-server
io.github.cyanheads/hn-mcp-servercyanheadsstreamable-httpv0.7.0Scanned
Browse Hacker News feeds, threads, and user profiles with full-text search.
4 tools: 4 only read.
- Reads private data · 1
- Reads text others write · 3
- 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 hn-mcp-server can do
The hn-mcp-server is published by the GitHub account cyanheads. 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 (hn_get_thread); 3 tools bring in text other people can write (hn_get_stories, hn_get_thread and hn_search_content).
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, and its tools changed 3 times since Anlyon Radar first saw them.
Last scanned Nov 14, 2026, version 0.7.0.
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
hn_get_storiesFetch stories from an HN feed (top, new, best, ask, show, jobs), with title, URL, score, author, and comment count for each story.Reads text others writeNo findings
Why it is in this group
- The name "hn_get_stories" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Fetch stories from an HN feed (top, new, best, ask, show, jobs), with title, URL, score, author, and comment count for each story.
Annotations the server declares
- readOnlyHint: true
hn_get_threadGet an item and its comment tree as a threaded discussion, with child comments resolved recursively.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "hn_get_thread" says "get": a word for reading.
What it can reach
- private-dataThe name "hn_get_thread" says "get" and "thread": it reads messages.
- untrusted-inputThe name "hn_get_thread" says "get" and "thread": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "comment": it reads comments, which other people can write.
Description, as the server wrote it Get an item and its comment tree as a threaded discussion, with child comments resolved recursively. Use depth 0 for an item-only lookup. A long thread comes back in pages: pass the returned nextCursor as cursor to continue.
Annotations the server declares
- readOnlyHint: true
hn_get_userGet an HN user profile with karma, about, and optionally their most recent submissions resolved into full items.No findings
Why it is in this group
- The name "hn_get_user" says "get": a word for reading.
Description, as the server wrote it Get an HN user profile with karma, about, and optionally their most recent submissions resolved into full items.
Annotations the server declares
- readOnlyHint: true
hn_search_contentSearch Hacker News stories, comments, polls, and jobs via Algolia — by keyword, by filters alone, or both.Reads text others writeNo findings
Why it is in this group
- The name "hn_search_content" says "search": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "search" and "comment": it reads comments, which other people can write.
Description, as the server wrote it Search Hacker News stories, comments, polls, and jobs via Algolia — by keyword, by filters alone, or both. Filterable by content type, author, parent story, date range, minimum points, and minimum comment count.
Annotations the server declares
- readOnlyHint: 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 outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- 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, 19:32 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.
Tools3 changed.~3 changedView diff
- Changed:hn_get_threadOnly readsinputSchema
- Changed:hn_get_userOnly readsinputSchema
- Changed:hn_search_contentOnly readsinputSchema
Tools1 changed.~1 changedView diff
- Changed:hn_search_contentOnly readsdescriptioninputSchema
Tools2 changed.~2 changedView diff
- Changed:hn_get_threadOnly readsinputSchema
- Changed:hn_search_contentOnly readsinputSchema
Install
Pinned to version 0.7.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http hn https://hn.caseyjhand.com/mcpclaude mcp add --transport http hn https://hn.caseyjhand.com/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__hn__hn_get_stories",
"mcp__hn__hn_get_thread",
"mcp__hn__hn_get_user",
"mcp__hn__hn_search_content"
],
"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 hn. Review it before you use it.
Capability tags behind 3 rules
- mcp__hn__hn_get_stories untrusted-input
- mcp__hn__hn_get_thread private-data, untrusted-input
- mcp__hn__hn_search_content 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.github.cyanheads/hn-mcp-server/verify?hash=66c24131f7fa456c9f70b86e0cdaf1cee72c00505f96bbc8001272d906845865" | jq -e '.changed == false'Pinned hash 66c24131f7fa, from Nov 14, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.cyanheads/hn-mcp-server/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.cyanheads/hn-mcp-server)Source: MCP Registry · repository. Synced Nov 14, 2026, 08:17 UTC.
hn-mcp-server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the hn-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 hn-mcp-server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the hn-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 hn-mcp-server have?
- 4 tools: 4 read. hn_get_stories, hn_get_thread, hn_get_user and hn_search_content.
Does the hn-mcp-server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the hn-mcp-server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the hn-mcp-server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 14, 2026. Every change is on this page and in its Atom feed.