The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Fixzi — MCP & API Schema Drift Monitor listing page.
Monitor MCP servers, API contracts, and AI output schemas — from inside Claude Code, Cursor, or any MCP client.
Your MCP servers, APIs, and AI outputs can break while still returning 200. Fixzi watches the contracts your integrations depend on, classifies every change (breaking / warning / info), and alerts you before your users hit it. This MCP server lets your AI tools query and operate those monitors directly.
Or add to your project's .mcp.json:
Add to claude_desktop_config.json:
Get your API token at https://fixzi.ai/settings/api-tokens. When creating the token, grant the abilities for the tools you want to use (see below).
| Tool | What it does | Ability required |
|---|---|---|
fixzi_list_monitors | List all your monitors (MCP / API contract / AI validator) with health status | — |
fixzi_get_monitor_status | Current status, last check result, consecutive failures for one monitor | — |
fixzi_get_recent_changes | Change log for a monitor: severity, what changed, before/after (filter by date/severity) | — |
fixzi_get_current_snapshot | Current tool list of a monitored MCP server (names, descriptions, schemas) | — |
fixzi_run_check_now | Trigger a check immediately (async — poll status after) | monitors:write |
fixzi_create_mcp_monitor | Create a new MCP server monitor from a URL | monitors:write |
| Tool | What it does | Ability required |
|---|---|---|
fixzi_list_validators | List your AI output validators | validators:read |
fixzi_get_validator | Details of a specific validator | validators:read |
fixzi_run_check | Run a validation check right now | validators:check |
fixzi_list_checks | Recent check history | validators:read |
Once connected, ask your agent things like:
fixzi_list_monitors → fixzi_get_recent_changes