AgentBreakWatch MCP Server

by joeyg6393 Your server? Claim it

not responding

AgentBreakWatch is listed as active in the registry but did not answer our last check. It exposes 4 tools. Last commit 6 Nov 2026.

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

Uptime history 14 days of history · worst day 0%

14 days agonow

0.0%

Uptime 24h

0 of 92 checks

Tools

read from the server

116 ms

Response time

average over 24h

Stars

last commit 6 Nov 2026

AgentBreakWatch does not always answer

Over the last week it answered 0.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agentbreakwatch-mcp --transport http https://agentbreakwatch.com/api/mcp

Settings → Connectors → Add custom connector, then paste this address

https://agentbreakwatch.com/api/mcp

~/.codex/config.toml

[mcp_servers.agentbreakwatch-mcp]
url = "https://agentbreakwatch.com/api/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "agentbreakwatch-mcp": {
      "url": "https://agentbreakwatch.com/api/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agentbreakwatch-mcp": {
      "type": "http",
      "url": "https://agentbreakwatch.com/api/mcp"
    }
  }
}

Available tools 4

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

archived

get_archived_mcp_replacements

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.

package

get_package_stability

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.

stack

check_stack_drift

Read-only audit of a package.json, requirements.txt, or .mcp.json configuration string against 256 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 Flags breaking major version deltas, unpinned @latest MCP servers, and outdated dependencies with exact pin commands.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.

volatile

list_volatile_packages

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).

Endpoints

URL	Transport	State	Latency	Checked
https://agentbreakwatch.com/api/mcp	streamable-http	answering	116 ms	1 min ago

Alternatives to AgentBreakWatch

same job, measured the same way

Fixzi — MCP & API Schema Drift Monitor

by rohitcodilya

Monitor MCP servers, API contracts and AI outputs for schema drift. Alerts on breaking changes.

answering

Specwise MCP

by bytestay

OpenAPI and JSON Schema validation and OpenAPI breaking-change diffs for AI agents.

1 101 installs/wk local only

Deprecation MCP

by tsvillain

MCP server for cross-vendor API/SDK deprecation and breaking-change tracking

48 installs/wk local only

ActionGuard Protocol Inspector Agent

by lsendel

Diff and poisoning detection for MCP servers: catch schema drift and prompt poisoning.

2 tools answering

MCP Server Change Health Monitor

by mambabuilt

Checks MCP servers for uptime and tool changes since the last run, breaking changes marked

local only

LogPulse

by lovable-release-ripple-roadmap

Changelogs for coding agents: versions, breaking changes, migrations. Free changelog-to-JSON.

9 tools answering

AI SEO

by automatelab-tech

MCP server for AI-SEO auditing: schema, robots.txt, llms.txt, citation scoring, and AEO/GEO rewrites

74 installs/wk local only

Omnicord

by orygnscode

Discord server management MCP for AI agents: chat, moderation, admin, and full server building.

89 installs/wk local only

AgentBreakWatch — questions

Answers built from our own checks of this server.

What can AgentBreakWatch do?

It exposes 4 tools, read directly from the server on our last check. Among them: check_stack_drift, get_archived_mcp_replacements, get_package_stability, list_volatile_packages. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is AgentBreakWatch working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 0 of 92 checks got a reply (0.0%), average response time 116 ms. The bar chart above shows every period we have measured.

The registry lists AgentBreakWatch as active — why does it not respond?

The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.

How do I connect AgentBreakWatch?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does AgentBreakWatch need an API key?

No. AgentBreakWatch completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 4 of them are readable on this page. This is what we observed, not what the docs claim.

Is AgentBreakWatch open source?

The code is open source: it is published under the MIT licence, written in JavaScript and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at agentbreakwatch.com, which runs on its operator's own terms.