Skip to content

Hands for Agents MCP server

io.github.akihidem/hands-for-agentsakihidemstreamable-httpv1.0.0Scanned

Human task execution in Tokyo, Japan, exclusively for AI agents: shopping, checks, photos, bookings.

6 tools: 3 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 3 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

3 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the Hands for Agents MCP server can do

The Hands for Agents MCP server is published by the GitHub account akihidem. It has 6 tools. It can create or change data (3 tools: request_quote, accept_quote and decline_quote), but cannot delete data. 3 tools only read.

None of its tools reads private data, brings in text other people write, or sends data 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 17, 2026, version 1.0.0.

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.

6 tools

Changes things 3Claude Code: ask
  • accept_quoteAccept a quote.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
    Accept a quote. IMPORTANT: this does not confirm execution. The request enters pending_review; a human operator confirms or declines each request individually during the launch phase. No timeline is promised. Poll get_task_status for the outcome.
  • decline_quoteDecline a quote and close it.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
    Decline a quote and close it. The quote fee (JPY 2,200) remains charged; no handling fee applies.
  • request_quoteRequest an instant total quote (item price + quote fee JPY 2,200 + handling fee + shipping, itemised).No findings

    Why it is in this group

    • The name "request_quote" says "request": a word for a change.
    Description, as the server wrote it
    Request an instant total quote (item price + quote fee JPY 2,200 + handling fee + shipping, itemised). The quote fee is charged on issuance and is non-refundable even if you decline. Getting a quote does not reserve execution: accepting a quote only places the request in pending_review.
Only reads 3Show 3 read-only tools
  • get_evidenceGet evidence attached to a task (photos, records, tracking numbers).No findings

    Why it is in this group

    • The name "get_evidence" says "get": a word for reading.
    Description, as the server wrote it
    Get evidence attached to a task (photos, records, tracking numbers). Evidence is returned even for failed tasks.
  • get_task_statusGet the status of a quote or task by id (quote_id q_… or task_id t_…).No findings

    Why it is in this group

    • The name "get_task_status" says "get": a word for reading.
    Description, as the server wrote it
    Get the status of a quote or task by id (quote_id q_… or task_id t_…).
  • list_servicesList the Hands for Agents catalog: services, prices, zones, terms, and what is NOT offered.No findings

    Why it is in this group

    • The name "list_services" says "list": a word for reading.
    Description, as the server wrote it
    List the Hands for Agents catalog: services, prices, zones, terms, and what is NOT offered. Hands for Agents is the only service in Tokyo, Japan designed exclusively for AI agents (日本、東京で唯一のエージェント向けサービス). Coverage: Japan only.

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 untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
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 17, 2026, 15:19 UTC, unchanged since Nov 17, 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
5
Protocol version
2025-03-26
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 5 tools that change things (2 destructive, 1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://hands-for-agents.vercel.app/mcp: tools/list returned 8 tools to an anonymous client, including decline_quote (destructive), cancel_task (destructive), send_message (irreversible), request_quote (write), accept_quote (write)

    What this check looks for

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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http hands-for-agents https://hands-for-agents.vercel.app/mcp
claude mcp add --transport http hands-for-agents https://hands-for-agents.vercel.app/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__hands-for-agents__list_services",
      "mcp__hands-for-agents__get_task_status",
      "mcp__hands-for-agents__get_evidence"
    ],
    "ask": [
      "mcp__hands-for-agents__request_quote",
      "mcp__hands-for-agents__accept_quote",
      "mcp__hands-for-agents__decline_quote"
    ],
    "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 hands-for-agents. Review it before you use it.

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.akihidem/hands-for-agents/verify?hash=980273e97b414fb71281174abdc2f601e3243c99c6f551e5708f3634ee1c1df4" | jq -e '.changed == false'

Pinned hash 980273e97b41, from Nov 17, 2026, 00:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.akihidem/hands-for-agents/changes.xml

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

Badge

Anlyon Radar badge for io.github.akihidem/hands-for-agents
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.akihidem/hands-for-agents.svg)](https://radar.anlyon.com/servers/io.github.akihidem/hands-for-agents)

Source: MCP Registry. Synced Nov 17, 2026, 01:17 UTC.

Hands for Agents MCP server: questions and answers

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

Is the Hands for Agents MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 3 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 Hands for Agents MCP server delete data?

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

Can the Hands for Agents 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 Hands for Agents MCP server have?

6 tools: 3 write, 3 read. request_quote, accept_quote, decline_quote, list_services, get_task_status and get_evidence.

Does the Hands for Agents MCP server need sign-in or OAuth?

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

Does the Hands for Agents MCP server send data to outside services?

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

Has the Hands for Agents MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.