Skip to content
MCP server

AgentBreakWatch

Breaking-change and tools/list schema drift checks for AI agent SDKs and MCP servers

Install
Pricing
Freemium
Platforms
API, CLI
Runs
Remotely
Version
1.2.0
Listing updated
2 days ago

About AgentBreakWatch

AgentBreakWatch is a freemium MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.

Paste a .mcp.json, package.json, requirements.txt or pyproject.toml and the server flags major version jumps, unpinned @latest dependencies with schema drift risk, and archived packages, with exact version pin commands. Its sample audit lines include notes like a filesystem server's 1.0.2 to 2.3.0 delta and a Firecrawl v3 change that requires a schema or prompt for extraction.

It tracks 32 core agent SDKs and 226 MCP servers (258 packages) on npm and PyPI, and gives each a 0-100 stability score, 90-day release velocity and before/after migration code. A separate tool returns the migration matrix from archived reference servers such as server-github and server-postgres to vendor-maintained replacements.

The hosted endpoint needs no install, and a stdio version runs through npx. The site also publishes category hubs, a weekly digest and llms.txt files. Alerts and webhooks are on paid plans.

Install

Run in a terminal

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

Add to Settings → Connectors → Add custom connector

https://agentbreakwatch.com/api/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "agentbreakwatch-mcp": {
      "url": "https://agentbreakwatch.com/api/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

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

Add to ~/.codeium/windsurf/mcp_config.json

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

Add to your client's MCP settings (most use this shape)

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

Tools this server provides (4)

Taken from the project documentation; the running server may differ.

check_stack_drift
Audit a config or dependency file for breaking jumps, unpinned servers and archived packages
get_package_stability
Get version, release velocity, stability score and drift risk for a tracked package
list_volatile_packages
List the fastest-changing SDKs and MCP servers over 90 days
get_archived_mcp_replacements
Show replacements for archived reference MCP servers

What it does

Stack drift audit
Checks config and dependency files for risky version jumps and unpinned servers.
Stability scores
Gives version, release velocity and drift risk per package.
Migration snippets
Copy-paste before and after code for breaking changes.
Volatile package list
Ranks fastest-changing SDKs and servers over 90 days.
Archived replacements
Maps archived reference servers to current ones.
Alerts on paid plans
Email and webhook alerts for breaking releases.

Good for

  • Audit an .mcp.json before deploying agents
  • Find which SDK release broke a tool call
  • Pin risky @latest MCP servers
  • Plan a migration off archived reference servers
  • Watch the packages an agent stack depends on

Pricing

Freemium, from $9 a month

Free plan; Indie Pro $9/month or $90/year, Team $29/month or $290/year, 7-day trial

Prices change. Check agentbreakwatch.com before you buy.

AgentBreakWatch FAQ

What does it track?

32 core AI agent SDKs and 226 MCP servers, 258 packages in all.

What does it cost?

Free covers audits and 3 watched packages; Indie Pro is $9/month and Team $29/month.

Is there a trial?

Paid plans have a 7-day trial that needs a card.

How do I connect?

Use https://agentbreakwatch.com/api/mcp, or run it locally with npx.

Which files can I audit?

A .mcp.json, package.json, requirements.txt or pyproject.toml.

Is AgentBreakWatch free?

AgentBreakWatch has a free plan, with paid plans for more usage or features. Paid plans start at $9 a month.

How do I add AgentBreakWatch to Claude Code?

Run this command in your terminal: claude mcp add --transport http agentbreakwatch-mcp https://agentbreakwatch.com/api/mcp

What are the best alternatives to AgentBreakWatch?

The closest alternatives to AgentBreakWatch are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to AgentBreakWatch

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools