PerformanceMonitor MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

50+ diagnostic tools across CPU, memory, waits, blocking, deadlocks, file I/O, plans
Built-in 30-rule PlanAnalyzer for surfacing common query anti-patterns
Localhost-only HTTP binding — never exposed on the network
Works against SQL Server 2016-2025, Azure SQL, and AWS RDS
Read-only diagnostics — cannot modify data, schema, or server config

Live-Demo

In der Praxis

performancemonitor.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "performancemonitor": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/erikdarlingdata/PerformanceMonitor"
      ],
      "_inferred": true
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "performancemonitor": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/erikdarlingdata/PerformanceMonitor"
      ],
      "_inferred": true
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "performancemonitor": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/erikdarlingdata/PerformanceMonitor"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "performancemonitor": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/erikdarlingdata/PerformanceMonitor"
      ],
      "_inferred": true
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "performancemonitor",
      "command": "TODO",
      "args": [
        "See README: https://github.com/erikdarlingdata/PerformanceMonitor"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "performancemonitor": {
      "command": {
        "path": "TODO",
        "args": [
          "See README: https://github.com/erikdarlingdata/PerformanceMonitor"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add performancemonitor -- TODO 'See README: https://github.com/erikdarlingdata/PerformanceMonitor'

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: PerformanceMonitor

Triage a slow SQL Server during an incident

👤 DBAs, SREs on call for database issues ⏱ ~5 min intermediate

Wann einsetzen: Users are reporting timeouts and you need to know what's blocking whom in the next 60 seconds.

Voraussetzungen

PerformanceMonitor app installed and connected to target server — Download from the GitHub releases and point it at your monitoring DB
Target login has VIEW SERVER STATE — GRANT VIEW SERVER STATE TO [monitor_login]
MCP registered with your client — claude mcp add --transport http --scope user sql-monitor http://localhost:5151/

Ablauf

Get the health overview

Run the health check — any red flags on waits, blocking, or memory pressure right now?✓ Kopiert

→ Short list of elevated metrics
Drill into the top offender

If blocking is the top issue, show me the head blocker chain and the SQL text of the blocking session.✓ Kopiert

→ Specific SPID + query text
Get a recommendation

Should I kill that SPID, wait it out, or is there a missing index that would prevent this? Be specific.✓ Kopiert

→ One clear recommended action with rationale

Ergebnis: A diagnosed incident with a specific next action — kill, wait, index, or escalate — in under 5 minutes.

Fallstricke

Killing a blocker that was about to commit can cause more damage — Always ask for how long it's been running and whether it holds an open transaction before killing
Metrics from the monitoring DB lag the real server by the collector interval — For live view, use the 'current state' tools rather than aggregated history

Kombinieren mit: sentry

Analyze a slow query plan with AI-assisted review

👤 Backend devs and DBAs tuning queries ⏱ ~15 min intermediate

Wann einsetzen: A query is slow and the plan is 200 operators — you don't want to read it manually.

Ablauf

Fetch the plan

Get the most recent plan for query hash 0xA1B2C3 and run the PlanAnalyzer against it.✓ Kopiert

→ Plan + list of rule hits
Explain the worst rule hit

Explain the #1 rule hit in plain English — what's happening and why it's bad.✓ Kopiert

→ 2-3 sentence explanation in English, not jargon
Suggest a fix

Suggest the smallest change to fix it: index, rewrite, or stats update. Estimate impact.✓ Kopiert

→ Concrete DDL or rewrite

Ergebnis: A specific tuning action backed by both plan evidence and the PlanAnalyzer rule.

Fallstricke

Plan was cached under a different parameter sniffing path — Regenerate the plan with OPTION(RECOMPILE) before trusting its shape

Produce a weekly SQL Server health summary

👤 Database owners who want passive monitoring, not live on-call ⏱ ~20 min beginner

Wann einsetzen: Friday afternoon wrap-up; know before users tell you.

Ablauf

Pull week-over-week stats

Compare top waits and top queries this week vs last week. Flag anything that got materially worse.✓ Kopiert

→ Deltas with percentages
Draft a team-readable summary

Write a one-page health summary — good/bad/ugly — for the engineering channel.✓ Kopiert

→ Markdown post ready to paste

Ergebnis: A shareable weekly health post with concrete items to track next week.

Kombinieren mit: sentry

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

performancemonitor + sentry

Sentry flags a timeout spike; cross-reference with SQL Server blocking at the same timestamp

Sentry event at 14:03 UTC shows SqlException. What was happening on the DB between 14:02 and 14:04 — any blocking or waits spikes?✓ Kopiert

performancemonitor + github

Find the commit that introduced a slow query

Query hash 0xA1B2 started showing up in the top 10 on 2026-03-22. Find GitHub commits to the data-access layer around that date.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
get_top_waits	server_name?: str, hours_back?: int	First stop in any triage — what is the server actually waiting on	1 SQL query on the monitoring DB
get_active_blocking	server_name?: str	Live blocking investigation	1 query
get_deadlocks	server_name?: str, hours_back?: int	Any time someone says 'we got a deadlock'	1 query
analyze_query_plan	plan_handle: bin, or xml: str	Tuning a specific slow query	1 query + 30 rule evaluations
get_memory_clerks	server_name?: str	Memory pressure investigation	1 query
get_tempdb_usage	server_name?: str	Tempdb filling up or spills in plans	1 query

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: No external quota; bounded by your monitoring DB capacity
Tokens pro Aufruf: Most tools return 200-2000 tokens; plan XML can be 10k+
Kosten in €: Free, open-source (Lite and Full editions)
Tipp: Lite edition is enough for most single-instance shops. Full adds cross-server monitoring.

Sicherheit

Rechte, Secrets, Reichweite

Minimale Scopes: VIEW SERVER STATE on the target instance

Credential-Speicherung: Monitoring DB connection string managed in the app's settings — stays on your box

Datenabfluss: MCP binds to localhost only; no outbound calls from the MCP process

Niemals gewähren: sysadmin or db_owner — VIEW SERVER STATE is enough

Plan XML and query text may contain sensitive data — be careful pasting into shared chat logs.
Run the collector under a dedicated login, not your personal account.

Fehlerbehebung

Häufige Fehler und Lösungen

Cannot connect to http://localhost:5151/

The app isn't running or MCP is disabled in Settings. Open the app, enable MCP, and confirm the port.

Prüfen: curl http://localhost:5151/

Login failed for user

Monitoring DB credentials are wrong. Re-enter in the app and confirm VIEW SERVER STATE.

Prüfen: sqlcmd -S <server> -U <user> -P <pwd> -Q 'SELECT 1'

Plan analyzer returns no findings on clearly slow query

Plan may not be in cache. Re-run the query with OPTION(RECOMPILE) and try again.

Prüfen: SELECT plan_handle FROM sys.dm_exec_query_stats WHERE ...

Port 5151 already in use

Change the MCP port in Settings (range 1024-65535) and re-register with your client.

Prüfen: netstat -an | grep 5151

Alternativen

PerformanceMonitor vs. andere

Alternative	Wann stattdessen	Kompromiss
sp_BlitzFirst / Brent Ozar scripts	You prefer running T-SQL procs directly without an app	No MCP — you paste output into the chat yourself
SentryOne / Redgate SQL Monitor	Enterprise environments that already have a commercial monitor	Paid; most don't expose an MCP surface
postgres MCP	You're on Postgres, not SQL Server	Different DB entirely

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen