# AgentBreakWatch

> AgentBreakWatch is a freemium MCP server for developer tools. Breaking-change and tools/list schema drift checks for AI agent SDKs and MCP servers. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $9 a month
- **Platforms:** API, CLI
- **Website:** https://agentbreakwatch.com
- **Repository:** https://github.com/joeyg6393/agentbreakwatch-mcp
- **MCP Registry name:** io.github.joeyg6393/agentbreakwatch-mcp
- **Categories:** developer tools, AI models and LLM tooling
- **Listing updated:** 2026-11-15

## About

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.

## Features

- **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

## Install

### Claude Code (Terminal)

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

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://agentbreakwatch.com/api/mcp
```

### Cursor (~/.cursor/mcp.json)

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

### VS Code (.vscode/mcp.json)

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

### Windsurf (~/.codeium/windsurf/mcp_config.json)

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

### Other clients (your client's MCP settings (most use this shape))

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

## Tools

- `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

## 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

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/agentbreakwatch
