AskHound MCP server
dev.haullabs/askhoundhaullabs.devstreamable-httpv0.1.5Scanned
Find people asking for or seeking alternatives to a product, live from Stack Exchange and Bluesky.
4 tools: 1 do something that can't be undone, 1 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- 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 AskHound MCP server can do
The AskHound MCP server is published by haullabs.dev, a domain the MCP Registry verified. It has 4 tools. It can do things that cannot be undone, such as sending, paying or publishing (reply_policy) and create or change data (1 tool: run_intent_pack), but cannot delete data. 2 tools only read.
1 tool reads private data (find_conversations); 1 tool brings in text other people can write (find_conversations); 1 tool can send data out of your system (reply_policy). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
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 0.1.5.
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
Can't be undone 1Claude Code: ask
reply_policyThe honest-reply rules AskHound users agree to.Can send data outNo findings
Why it is in this group
- The name "reply_policy" says "reply": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "reply_policy" says "reply": it sends or publishes something to other people.
Description, as the server wrote it The honest-reply rules AskHound users agree to. Read before drafting any reply.
Changes things 1Claude Code: ask
run_intent_packbuild_intent_queries + find_conversations for every phrase, merged and deduplicated, newest first.No findings
Why it is in this group
- The name "run_intent_pack" says "run": a word for a change.
Description, as the server wrote it build_intent_queries + find_conversations for every phrase, merged and deduplicated, newest first.
Only reads 2Show 2 read-only tools
build_intent_queriesTurn a product description into buying-intent search phrases (competitor alternatives, switching, export, pricing pain, recommendations).No findings
Why it is in this group
- The name "build_intent_queries" says "query": a word for reading.
Description, as the server wrote it Turn a product description into buying-intent search phrases (competitor alternatives, switching, export, pricing pain, recommendations).
find_conversationsFind recent public posts where people ask for a tool, an alternative, or help with a job, so you can decide whether an honest, disclosed reply would help them.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "find_conversations" says "find": a word for reading.
What it can reach
- private-dataThe name "find_conversations" says "find" and "conversation": it reads messages.
- untrusted-inputThe name "find_conversations" says "find" and "conversation": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "find" and "post": it reads posts, which other people can write.
Description, as the server wrote it Find recent public posts where people ask for a tool, an alternative, or help with a job, so you can decide whether an honest, disclosed reply would help them. Remote server covers Stack Exchange (incl. softwarerecs) and Bluesky; for Hacker News + GitHub run the local MCP: npx -y https://askhound.haullabs.dev/askhound.tgz mcp. Returns url, title, snippet, date, source and required attribution. Never auto-post replies.
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.
1 path in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__askhound__reply_policy"
]
}
}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, 18:52 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
- 2
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://askhound.haullabs.dev/api/mcp: tools/list returned 4 tools to an anonymous client, including reply_policy (irreversible), run_intent_pack (write)
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 0.1.5. Values in angle brackets are yours to fill in.
claude mcp add --transport http askhound https://askhound.haullabs.dev/api/mcpclaude mcp add --transport http askhound https://askhound.haullabs.dev/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__askhound__find_conversations",
"mcp__askhound__build_intent_queries"
],
"ask": [
"mcp__askhound__run_intent_pack",
"mcp__askhound__reply_policy"
],
"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 askhound. Review it before you use it.
Capability tags behind 2 rules
- mcp__askhound__find_conversations private-data, untrusted-input
- mcp__askhound__reply_policy outbound
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/dev.haullabs/askhound/verify?hash=83220660ec59de5d43996ca46d385e5956227e18dc5e30293c9d86f06806109b" | jq -e '.changed == false'Pinned hash 83220660ec59, from Nov 15, 2026, 02:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.haullabs/askhound/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.haullabs/askhound)Source: MCP Registry. Synced Oct 21, 2026, 18:11 UTC.
AskHound MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AskHound MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the AskHound MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AskHound MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: reply_policy.
What tools does the AskHound MCP server have?
- 4 tools: 1 irreversible, 1 write, 2 read. reply_policy, run_intent_pack, find_conversations and build_intent_queries.
Does the AskHound MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AskHound MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): reply_policy.
Has the AskHound MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.