convex-agent-skillz MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

Deep Convex patterns — queries, mutations, actions, HTTP endpoints
Real-time features: presence, streaming, collaborative editing
Durable ops: workflows, queues, scheduled tasks
Auth patterns — universal, plus Clerk and WorkOS specifics
AI agent patterns: threads, tool calling, RAG, persistent message history

Live-Demo

In der Praxis

convex-agent-skillz-skill.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": {
    "convex-agent-skillz-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/PolarCoding85/convex-agent-skillz",
        "~/.claude/skills/convex-agent-skillz"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "convex-agent-skillz-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/PolarCoding85/convex-agent-skillz",
        "~/.claude/skills/convex-agent-skillz"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "convex-agent-skillz-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/PolarCoding85/convex-agent-skillz",
        "~/.claude/skills/convex-agent-skillz"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "convex-agent-skillz-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/PolarCoding85/convex-agent-skillz",
        "~/.claude/skills/convex-agent-skillz"
      ],
      "_inferred": true
    }
  }
}

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

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "convex-agent-skillz-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/PolarCoding85/convex-agent-skillz",
        "~/.claude/skills/convex-agent-skillz"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "convex-agent-skillz-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/PolarCoding85/convex-agent-skillz",
          "~/.claude/skills/convex-agent-skillz"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add convex-agent-skillz-skill -- git clone https://github.com/PolarCoding85/convex-agent-skillz ~/.claude/skills/convex-agent-skillz

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

Anwendungsfälle

Praxisnahe Nutzung: convex-agent-skillz

Add real-time presence to an existing Convex app

👤 Convex devs adding collab features ⏱ ~45 min intermediate

Wann einsetzen: You have an app and want Figma-style 'who's here' indicators without running a socket server.

Voraussetzungen

Skill copied into your project's .claude folder — git clone https://github.com/PolarCoding85/convex-agent-skillz and copy .claude/ to your project root

Ablauf

Describe the feature

Using the Convex skillz — add presence to the documents page. Show cursors and usernames.✓ Kopiert

→ Claude implements with Convex's presence pattern (mutation + reactive query), not a custom WebSocket
Handle disconnection

What about cleanup when users close the tab?✓ Kopiert

→ Specific stale-presence cleanup strategy aligned with Convex conventions

Ergebnis: Working presence with proper cleanup.

Fallstricke

Custom presence pattern that fights Convex's reactivity — Skill steers you toward the idiomatic version; don't override without a reason

Kombinieren mit: filesystem

Integrate Clerk auth with Convex properly

👤 Devs wiring Clerk into a new or existing Convex app ⏱ ~30 min intermediate

Wann einsetzen: You picked Clerk and want its Convex integration right the first time.

Ablauf

Wire the provider

Convex skillz — integrate Clerk auth with Convex. Set up the JWT template and the Convex auth config.✓ Kopiert

→ Claude references the right Clerk JWT template name and auth.config.ts setup
Protect queries

Now gate the documents query so only the owner can read.✓ Kopiert

→ ctx.auth.getUserIdentity() pattern with proper identity check

Ergebnis: Auth that passes code review and doesn't leak across tenants.

Build an AI agent with persistent threads on Convex

👤 Devs building chat or agent products ⏱ ~90 min advanced

Wann einsetzen: You want threaded message history that survives across sessions.

Ablauf

Model threads

Convex skillz — agent threads table + message history + tool calling metadata.✓ Kopiert

→ Schema that covers streaming, partial messages, and tool-call state
Hook up streaming

Stream the assistant response back via a reactive query.✓ Kopiert

→ Partial-message pattern leveraging Convex's reactivity

Ergebnis: A Convex-native agent thread layer ready to scale.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

convex-agent-skillz-skill + github

Open PRs for feature additions with Convex-conventional diffs

Implement the presence feature, commit and open PR with the Convex skill patterns noted.✓ Kopiert

convex-agent-skillz-skill + filesystem

Work across schema, functions, and UI in one session

Update convex/schema.ts, add the mutation, and wire up the React hook.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen
queries_mutations_actions	feature intent	Any convex/ work
realtime_patterns	feature (presence / streaming / collab)	Real-time features
auth_setup	provider (Clerk / WorkOS / custom)	Wiring auth
durable_ops	workflow intent	Long-running or retry-heavy logic
ai_agent_threads	agent feature description	Agent products on Convex

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: None from the skill
Tokens pro Aufruf: Moderate — patterns load as needed by context
Kosten in €: Free — skills are local files. Convex itself has its own pricing.
Tipp: Place skill in project .claude/ rather than global — auto-activation works best scoped to the project.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: No credentials in the skill. Your auth provider secrets live in your own env.

Datenabfluss: None from the skill — code stays local

Auth patterns assume you configure JWT templates correctly in Clerk/WorkOS — read their docs in addition.

Fehlerbehebung

Häufige Fehler und Lösungen

Skill not invoked — Claude writes non-Convex-idiomatic code

Say 'use the Convex skillz' or ensure you're working inside convex/ directory.

Prüfen: ls <project>/.claude/agents/convex-expert.md

SKILL.md frontmatter wrong

Re-copy .claude/ from the repo.

Prüfen: head <project>/.claude/skills/*/SKILL.md

Wrong trigger keywords — auth pattern doesn't use your provider

Name the provider explicitly ('with Clerk' / 'with WorkOS').

Alternativen

convex-agent-skillz vs. andere

Alternative	Wann stattdessen	Kompromiss
Convex official docs	You want primary source rather than a curated skill	No in-agent auto-activation
Hand-rolled patterns	You're an experienced Convex dev	You'll reinvent patterns; skill just makes Claude use yours consistently

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen