AgentBreakWatch
Server Details
Audit AI Agent SDKs and MCP servers for breaking changes, schema drift, and migration fixes.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- joeyg6393/agentbreakwatch-mcp
- GitHub Stars
- 0
- Server Listing
- AgentBreakWatch MCP Server
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool targets a distinct scope: bulk stack audit, archived-package migration matrix, single-package deep lookup, and a telemetry ranking list. The get_package_stability description even explicitly states when to prefer it over check_stack_drift, eliminating the only plausible overlap.
All four tools follow a consistent verb_noun snake_case convention (check_, get_, list_). The resource nouns are descriptive and unambiguous.
Four tools is on the lean side but each covers a genuinely different angle of the same advisory domain, so nothing feels redundant. A slightly richer surface (e.g. a lookup-by-name search) would round it out.
The read-only advisory lifecycle is well covered: audit a whole stack, resolve migrations for archived packages, inspect a single package's stability, and discover risky packages. Minor gaps include no way to search or enumerate packages by name outside the volatility-ranked list.
Available Tools
4 toolscheck_stack_driftARead-onlyIdempotentInspect
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 Flags breaking major version deltas, unpinned @latest MCP servers, and outdated dependencies with exact pin commands.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.
Inputs: manifest (required).
get_archived_mcp_replacementsARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
get_package_stabilityARead-onlyIdempotentInspect
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.
Inputs: package (required).
list_volatile_packagesARead-onlyIdempotentInspect
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).
Inputs: kind, limit, category.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Monitor MCP servers, API contracts and AI outputs for schema drift. Alerts on breaking changes.
Free MCP contract auditing for AI agents and developers. Check tool schemas, detect potential breaking changes between versions, and get structured compatibility findings before deployment. Static analysis only.
Statically audits MCP tool surfaces for token cost, schema quality, and design issues.
AI agent security, MCP 2026 schema & graph audits, <250ms guardrails, and compliance dossiers
Related MCP Servers
- AlicenseAqualityBmaintenanceChecks the MCP server you're building the way clients and agents meet its tool list. It flags what agents misread (vague parameters, writes marked read-only), what breaks clients or prompt caches (tools that appear mid-session, schemas that change on every call), and breaking changes between releases with the version bump they need. Same input, same answer: no LLM involved.6865 npmMIT
- AlicenseNot gradedqualityBmaintenanceAudits MCP server configurations for security risks including capability inventory, SSRF, prompt injection, and drift detection. Works in read-only mode and can also be used as an MCP server to let AI agents audit their own attack surface.182 PyPI4MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that enables AI coding agents to pre-validate packages before installation, audit code changes for duplicated boilerplate and lazy placeholders, and detect when modified files drift from the original task intent.67 npmApache 2.0
- AlicenseAqualityDmaintenanceAn MCP server that exposes three tools for auditing, scaffolding, and triaging agent intent specs against a unified template, helping prevent intent failures in AI agents.3MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.