Skip to content

varg how to MCP server

ai.varg/how-tovarg.aistreamable-httpv1.0.2Scanned

Video how-to search for AI agents: 2,000+ video skills, tutorials and FFmpeg recipes. No key.

3 tools: 1 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 1 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 varg how to MCP server can do

The varg how to MCP server is published by varg.ai, a domain the MCP Registry verified. It has 3 tools. It can create or change data (1 tool: rate_how_to), but cannot delete data. 2 tools only read.

1 tool brings in text other people can write (get_how_to).

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 once since Anlyon Radar first saw them.

Last scanned Nov 10, 2026, version 1.0.2.

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.

3 tools

Changes things 1Claude Code: ask
  • rate_how_toRate how well a varg how to skill or tutorial worked, 1–5, after it was used: did it work (yes / partly / no) and one line on what was great or wrong.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Rate how well a varg how to skill or tutorial worked, 1–5, after it was used: did it work (yes / partly / no) and one line on what was great or wrong. Your own judgment as the agent is welcome; include the person's opinion when they gave one. One rating per caller per card — rating again updates it.

    Annotations the server declares

    • title: Rate a varg how to card
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 2Show 2 read-only tools
  • get_how_toRead one varg how to card in full as Markdown: a how-to tutorial (best skills with install commands, the options to show the person with example videos, the steps, how it runs on v…Reads text others writeNo findings

    Why it is in this group

    • The name "get_how_to" 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.
    Description, as the server wrote it
    Read one varg how to card in full as Markdown: a how-to tutorial (best skills with install commands, the options to show the person with example videos, the steps, how it runs on varg) or a skill, component or video type page. Pass the kind and slug from search_how_to.

    Annotations the server declares

    • title: Read a varg how to page
    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: true
  • search_how_toFind how to make any AI video: searches 2,000+ agent skills, step-by-step how-to tutorials, FFmpeg recipes, video formats, prompts and styles by the task in plain words, in any lan…No findings

    Why it is in this group

    • The name "search_how_to" says "search": a word for reading.
    Description, as the server wrote it
    Find how to make any AI video: searches 2,000+ agent skills, step-by-step how-to tutorials, FFmpeg recipes, video formats, prompts and styles by the task in plain words, in any language ("ugc ad for my serum", "burn captions into a reel", "субтитры для рилс"). Returns ranked cards with a Markdown link to read next. Call it before improvising a video pipeline.

    Annotations the server declares

    • title: Search varg how to
    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false

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 write1
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.

Tools listed without sign-in

Looked at Nov 19, 2026, 17:23 UTC, unchanged since Nov 5, 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
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.varg.ai/.well-known/oauth-protected-resource
Authorization servers
https://jawyggwaylpehmatvwni.supabase.co/auth/v1
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.varg.ai/how-to: tools/list returned 3 tools to an anonymous client, including rate_how_to (write)

    What this check looks for

Posture changes

  1. Nov 5, 2026
    • Tools that change things, listed without credentials: 0 to 1
    • RFC 9728 protected resource metadata: none to https://mcp.varg.ai/.well-known/oauth-protected-resource
    • Authorization servers: none to https://jawyggwaylpehmatvwni.supabase.co/auth/v1
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to no

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.

  1. Tools1 added, 2 changed.+1 added~2 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 0 -> 1; RFC 9728 protected resource metadata: none -> https://mcp.varg.ai/.well-known/oauth-protected-resource; Authorization servers: none -> https://jawyggwaylp…View diff
    • Tools that change things, listed without credentials: 0 to 1
    • RFC 9728 protected resource metadata: none to https://mcp.varg.ai/.well-known/oauth-protected-resource
    • Authorization servers: none to https://jawyggwaylpehmatvwni.supabase.co/auth/v1
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to no

Install

Pinned to version 1.0.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http how-to https://mcp.varg.ai/how-to
claude mcp add --transport http how-to https://mcp.varg.ai/how-to

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__how-to__search_how_to",
      "mcp__how-to__get_how_to"
    ],
    "ask": [
      "mcp__how-to__rate_how_to"
    ],
    "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 how-to. Review it before you use it.

Capability tags behind 1 rule
  • mcp__how-to__get_how_to 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/ai.varg/how-to/verify?hash=7815cadcfe5e6a69f586a0b38570d2da9a862dd233a71efdb5e610e7eb6ba88f" | jq -e '.changed == false'

Pinned hash 7815cadcfe5e, from Nov 10, 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/ai.varg/how-to/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for ai.varg/how-to
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.varg/how-to.svg)](https://radar.anlyon.com/servers/ai.varg/how-to)

Source: MCP Registry. Synced Oct 29, 2026, 06:17 UTC.

varg how to MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the varg how to MCP server safe?

No scan can promise that. What its definitions show: 3 tools, 1 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 varg how to MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the varg how to 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 varg how to MCP server have?

3 tools: 1 write, 2 read. rate_how_to, search_how_to and get_how_to.

Does the varg how to MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the varg how to MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the varg how to MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.