Skip to content

MilliTool MCP server

com.millitool/skillsmillitool.comstreamable-httpv0.2.0Scanned

Find coding-agent skills by task and inspect source previews through MilliTool's free MCP server.

4 tools: 4 only read.

Tools: 0 delete, 0 irreversible, 0 write, 4 read.
  • Reads private data · 1
  • Reads text others write · 1
  • 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.
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 MilliTool MCP server can do

The MilliTool MCP server is published by millitool.com, 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 (list_sources); 1 tool brings in text other people can write (browse_categories).

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 0.2.0.

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
  • browse_categoriesList normalized category names and slugs.Reads text others writeNo findings

    Why it is in this group

    • The name "browse_categories" says "browse": a word for reading.

    What it can reach

    • untrusted-inputThe name "browse_categories" says "browse": it reads web pages, which anyone can write.
    Description, as the server wrote it
    List normalized category names and slugs. Pass a slug to recommend_skills to filter results.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_skill_contentGet indexed metadata and content preview for a skill_id returned by recommend_skills.No findings

    Why it is in this group

    • The name "get_skill_content" says "get": a word for reading.
    Description, as the server wrote it
    Get indexed metadata and content preview for a skill_id returned by recommend_skills. Includes pinned source URL and install suggestion; preview may be incomplete. Does not fetch arbitrary URLs or execute code.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_sourcesList the indexed source repositories and current skill counts.Reads private dataNo findings

    Why it is in this group

    • The name "list_sources" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "list" and "repository": it reads repositories.
    Description, as the server wrote it
    List the indexed source repositories and current skill counts.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • recommend_skillsFind skills for a task or technology stack.No findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.
    Description, as the server wrote it
    Find skills for a task or technology stack. Returns ranked candidates, indexed source commits, compatibility hints and installation suggestions. Does not install or run code.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • 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 outbound.

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 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 18, 2026, 16:18 UTC, unchanged since Nov 18, 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 0.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http skills https://millitool.com/mcp
claude mcp add --transport http skills https://millitool.com/mcp

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__skills__recommend_skills",
      "mcp__skills__get_skill_content",
      "mcp__skills__list_sources",
      "mcp__skills__browse_categories"
    ],
    "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 skills. Review it before you use it.

Capability tags behind 2 rules
  • mcp__skills__list_sources private-data
  • mcp__skills__browse_categories 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/com.millitool/skills/verify?hash=c0b327f878c9295330d84cf426f7d1a99fd15e7ac017f46b5d61e7d6a9ab818d" | jq -e '.changed == false'

Pinned hash c0b327f878c9, from Nov 18, 2026, 12:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.millitool/skills/changes.xml

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

Badge

Anlyon Radar badge for com.millitool/skills
[![Anlyon Radar](https://radar.anlyon.com/badge/com.millitool/skills.svg)](https://radar.anlyon.com/servers/com.millitool/skills)

Source: MCP Registry. Synced Nov 18, 2026, 12:17 UTC.

MilliTool MCP server: questions and answers

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

Is the MilliTool 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 MilliTool MCP server delete data?

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

Can the MilliTool 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 MilliTool MCP server have?

4 tools: 4 read. recommend_skills, get_skill_content, list_sources and browse_categories.

Does the MilliTool MCP server need sign-in or OAuth?

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

Does the MilliTool MCP server send data to outside services?

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

Has the MilliTool MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.