Skip to content

AgentBreakWatch MCP server

io.github.joeyg6393/agentbreakwatch-mcpjoeyg6393streamable-httpv1.2.0Scanned

Audit AI Agent SDKs and MCP servers for breaking changes, schema drift, and migration fixes.

4 tools: 4 only read.

Tools: 0 delete, 0 irreversible, 0 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • 2 findings, 2 high

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 AgentBreakWatch MCP server can do

The AgentBreakWatch MCP server is published by the GitHub account joeyg6393. It has 4 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

None of its tools reads private data, brings in text other people write, or sends data out.

The fixed checks matched 2 findings, 2 of them high severity (sensitive-path). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 9, 2026, version 1.2.0.

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
  • check_stack_driftRead-only audit of a package.json, requirements.txt, or .mcp.json configuration string against 258 live AI Agent SDKs and MCP servers.2 findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    Findings

    • High

      The description refers to ".mcp.json".

      Matched text

      description: "...of a package.json, requirements.txt, or .mcp.json configuration string against 258 live A..."

      What this check looks for
    • High

      The input schema at properties.manifest.description refers to ".mcp.json".

      Matched text

      inputSchema.properties.manifest.description: "Raw contents of .mcp.json, package.json, requirements.txt, or a n..."

      What this check looks for
    Description, as the server wrote it
    Read-only audit of a package.json, requirements.txt, or .mcp.json configuration string against 258 live AI Agent SDKs and MCP servers. Flags breaking major version deltas, unpinned @latest MCP servers, and outdated dependencies with exact pin commands. Requires no authentication and returns a structured JSON report.

    Annotations the server declares

    • title: Audit Stack Configuration for Breaking Drift
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_archived_mcp_replacementsRead-only lookup returning the complete migration matrix for archived or frozen @modelcontextprotocol/server-* reference packages and their official 2026 vendor-maintained replacem…No findings

    Why it is in this group

    • The name "get_archived_mcp_replacements" says "get": a word for reading.
    Description, as the server wrote it
    Read-only lookup returning the complete migration matrix for archived or frozen @modelcontextprotocol/server-* reference packages and their official 2026 vendor-maintained replacements. Takes no parameters and requires no authentication.

    Annotations the server declares

    • title: Get Archived Reference MCP Replacement Matrix
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_package_stabilityRead-only lookup of live npm or PyPI version, publish timestamp, 90-day release velocity, stability score (0-100), MCP tools/list schema drift risk, and before/after migration code…No findings

    Why it is in this group

    • The name "get_package_stability" says "get": a word for reading.
    Description, as the server wrote it
    Read-only lookup of live npm or PyPI version, publish timestamp, 90-day release velocity, stability score (0-100), MCP tools/list schema drift risk, and before/after migration code for a single AI Agent SDK or MCP server. Prefer this over check_stack_drift when inspecting one specific package by name or slug.

    Annotations the server declares

    • title: Get Single Package Stability and Migration Diff
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_volatile_packagesRead-only query that lists the fastest-changing or highest schema-drift-risk AI Agent SDKs and MCP servers from the live AgentBreakWatch telemetry index, sorted descending by 90-da…No findings

    Why it is in this group

    • The name "list_volatile_packages" says "list": a word for reading.
    Description, as the server wrote it
    Read-only query that lists the fastest-changing or highest schema-drift-risk AI Agent SDKs and MCP servers from the live AgentBreakWatch telemetry index, sorted descending by 90-day release velocity. Supports filtering by kind ('sdk', 'mcp', 'all'), category hub slug, and result limit (1-50).

    Annotations the server declares

    • title: List Most Volatile AI Agent SDKs and MCP Servers
    • 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 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 16, 2026, 14:23 UTC, unchanged since Nov 2, 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

Posture changes

  1. Nov 2, 2026
    • Tools that change things, listed without credentials: 1 to 0

Findings

Matches of fixed checks, with the text they matched.

2 high
  • The description refers to ".mcp.json".

    Matched text

    description: "...of a package.json, requirements.txt, or .mcp.json configuration string against 258 live A..."

    What this check looks for
  • The input schema at properties.manifest.description refers to ".mcp.json".

    Matched text

    inputSchema.properties.manifest.description: "Raw contents of .mcp.json, package.json, requirements.txt, or a n..."

    What this check looks for

History

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

  1. Tools1 changed.~1 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 0.View diff
    • Tools that change things, listed without credentials: 1 to 0
  3. Tools4 changed.~4 changedView diff

Install

Pinned to version 1.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentbreakwatch https://agentbreakwatch.com/api/mcp
claude mcp add --transport http agentbreakwatch https://agentbreakwatch.com/api/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__agentbreakwatch__check_stack_drift",
      "mcp__agentbreakwatch__get_package_stability",
      "mcp__agentbreakwatch__list_volatile_packages",
      "mcp__agentbreakwatch__get_archived_mcp_replacements"
    ],
    "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 agentbreakwatch. 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.joeyg6393/agentbreakwatch-mcp/verify?hash=ebbb0ff920f4ef65602e9fbaf78a04110f0d08c9659a26f4c93c0e4884f4b2d8" | jq -e '.changed == false'

Pinned hash ebbb0ff920f4, from Nov 9, 2026, 07:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.joeyg6393/agentbreakwatch-mcp/changes.xml

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

Badge

Anlyon Radar badge for io.github.joeyg6393/agentbreakwatch-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.joeyg6393/agentbreakwatch-mcp.svg)](https://radar.anlyon.com/servers/io.github.joeyg6393/agentbreakwatch-mcp)

Source: MCP Registry · repository. Synced Oct 26, 2026, 01:17 UTC.

AgentBreakWatch MCP server: questions and answers

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

Is the AgentBreakWatch MCP server safe?

No scan can promise that. What its definitions show: 4 tools, all of which only read, and 2 findings (2 high) from fixed checks. Read-only tools can still pass private data to a model.

Can the AgentBreakWatch MCP server delete data?

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

Can the AgentBreakWatch 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 AgentBreakWatch MCP server have?

4 tools: 4 read. check_stack_drift, get_package_stability, list_volatile_packages and get_archived_mcp_replacements.

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

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

Does the AgentBreakWatch MCP server send data to outside services?

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

Has the AgentBreakWatch MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.