Skip to content

ShellWire MCP server

io.github.Kiragu-Maina/shellwireKiragu-Mainastreamable-httpv1.0.1Scanned

Discover and compare software, read chatbot news, and submit applications for private review.

8 tools: 2 change things and 6 only read.

Tools: 0 delete, 0 irreversible, 2 write, 6 read.
  • Reads private data · 1
  • Reads text others write · 2
  • Can send data out · 0
  • 1 finding

Sign-in required, no OAuth metadata. Remote posture

Anlyon alternative

2 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 ShellWire MCP server can do

The ShellWire MCP server is published by the GitHub account Kiragu-Maina. It has 8 tools. It can create or change data (2 tools: verify_homepage_backlink and submit_application), but cannot delete data. 6 tools only read.

1 tool reads private data (get_submission_instructions); 2 tools bring in text other people can write (verify_homepage_backlink and submit_application).

The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.

Last scanned Oct 21, 2026, version 1.0.1.

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.

8 tools

Changes things 2Claude Code: ask
  • submit_applicationRequires email OTP authentication and a verified root homepage backlink.Reads text others writeNo findings

    Why it is in this group

    • The name "submit_application" says "submit": a word for a change.

    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
    Requires email OTP authentication and a verified root homepage backlink. Submit an app or personal agent for private operator review, with optional images uploaded separately by authenticated HTTP. Email must match the verified account. Does not publish. Repeated pending normalized URLs are acknowledged without overwriting. On outcome_unknown inspect list_my_submissions before retrying.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 6Show 6 read-only tools
  • compare_toolsCompare one to four distinct public tool IDs.No findings

    Why it is in this group

    • The name "compare_tools" says "compare": a word for reading.
    Description, as the server wrote it
    Compare one to four distinct public tool IDs. Preserves unknown facts, source evidence and checked dates; no generated ratings.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • fetchFetch one public record ID returned by search.No findings

    Why it is in this group

    • The name "fetch" says "fetch": a word for reading.
    Description, as the server wrote it
    Fetch one public record ID returned by search. Includes citable text and dated facts. Unpublished and unknown IDs are unavailable.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_chatbot_briefRead the same source-reviewed brief shown on the homepage, with at most four labeled stories and related public tools.No findings

    Why it is in this group

    • The name "get_chatbot_brief" says "get": a word for reading.
    Description, as the server wrote it
    Read the same source-reviewed brief shown on the homepage, with at most four labeled stories and related public tools. An empty brief remains empty.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_submission_instructionsAnonymous, credential-free instructions for authenticated private submissions.Reads private data1 finding

    Why it is in this group

    • The name "get_submission_instructions" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "credential": it reads secrets.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "Anonymous, credential-free instructions for authenticated pri..."

      What this check looks for
    Description, as the server wrote it
    Anonymous, credential-free instructions for authenticated private submissions. Includes exact first-party OTP HTTP endpoints, bounded submission fields and binary screenshot uploads. No OAuth authentication is offered.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_my_submissionsRequires a current verified builder token.No findings

    Why it is in this group

    • The name "list_my_submissions" says "list": a word for reading.
    Description, as the server wrote it
    Requires a current verified builder token. Return only this builder account's private submission statuses, optional published tool URL and image previews. Empty means no owned records. Never returns another builder's submission, operator notes or contact email.

    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 write2
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.

Sign-in required, no OAuth metadata

Looked at Nov 20, 2026, 18:58 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
530
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
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

The probe stopped: initialize answered HTTP 530.

Posture changes

  1. Oct 29, 2026
    • HTTP status of an anonymous initialize: 200 to 530
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 2 to 0
    • Protocol version: 2025-06-18 to none

Findings

Matches of fixed checks, with the text they matched.

1 info

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 530; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 2 -> 0 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 200 to 530
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 2 to 0
    • Protocol version: 2025-06-18 to none

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http shellwire https://shellwire.com/mcp
claude mcp add --transport http shellwire https://shellwire.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__shellwire__search",
      "mcp__shellwire__fetch",
      "mcp__shellwire__compare_tools",
      "mcp__shellwire__get_chatbot_brief",
      "mcp__shellwire__get_submission_instructions",
      "mcp__shellwire__list_my_submissions"
    ],
    "ask": [
      "mcp__shellwire__verify_homepage_backlink",
      "mcp__shellwire__submit_application"
    ],
    "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 shellwire. Review it before you use it.

Capability tags behind 3 rules
  • mcp__shellwire__get_submission_instructions private-data
  • mcp__shellwire__verify_homepage_backlink untrusted-input
  • mcp__shellwire__submit_application 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.Kiragu-Maina/shellwire/verify?hash=2a3d92b1c975b47e08ee3ffad758dda322074b47856b18a59ab22afce6c018a8" | jq -e '.changed == false'

Pinned hash 2a3d92b1c975, from Oct 21, 2026, 19:03 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.Kiragu-Maina/shellwire/changes.xml

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

Badge

Anlyon Radar badge for io.github.Kiragu-Maina/shellwire
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.Kiragu-Maina/shellwire.svg)](https://radar.anlyon.com/servers/io.github.Kiragu-Maina/shellwire)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:17 UTC.

ShellWire MCP server: questions and answers

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

Is the ShellWire MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the ShellWire MCP server delete data?

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

Can the ShellWire 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 ShellWire MCP server have?

8 tools: 2 write, 6 read. verify_homepage_backlink, submit_application, search, fetch, compare_tools, get_chatbot_brief, get_submission_instructions and list_my_submissions.

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

Its remote endpoint did not answer the last anonymous look.

Does the ShellWire MCP server send data to outside services?

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

Has the ShellWire MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Oct 21, 2026.