CACHLY_JWT=your-jwt npx @cachly-dev/mcp-server setup

CACHLY_JWT=your-jwt npx @cachly-dev/mcp-server init \
  --instance-id your-instance-id \
  --editor vscode

"Create a free cachly instance called my-app-cache"
"List all my cache instances"
"Get the connection string for instance abc-123"
"Delete my test-cache instance"

CACHLY_JWT=your-jwt npx @cachly-dev/mcp-server setup

{
  "mcpServers": {
    "cachly": {
      "command": "npx",
      "args": ["-y", "@cachly-dev/mcp-server"],
      "env": { "CACHLY_JWT": "your-jwt-token-here" }
    }
  }
}

{
  "servers": {
    "cachly": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cachly-dev/mcp-server"],
      "env": { "CACHLY_JWT": "your-jwt-token-here" }
    }
  }
}

{
  "mcpServers": {
    "cachly": {
      "command": "npx",
      "args": ["-y", "@cachly-dev/mcp-server"],
      "env": { "CACHLY_JWT": "your-jwt-token-here" }
    }
  }
}

User: Create a free cache instance for my OpenAI project

Copilot: I'll create a free cachly instance for you.
[calls create_instance(name="openai-cache", tier="free")]

✅ Instance **openai-cache** (FREE) created and provisioning started!
   ID: `a1b2c3d4-...`
   Status: provisioning

Use `get_connection_string` to get your Redis URL in ~30 seconds.

User: Get the connection string

Copilot: [calls get_connection_string(instance_id="a1b2c3d4-...")]

Connection string for openai-cache:
  redis://:password@my-node.cachly.dev:30101

Environment variable:
  REDIS_URL="redis://:password@my-node.cachly.dev:30101"

# Run against local API
CACHLY_JWT=your-token CACHLY_API_URL=http://localhost:3001 npm run dev

You: "Analyze the authentication architecture"
AI:  [reads 47 files, takes 30 seconds]
     The auth uses Keycloak with JWT tokens. The flow is:
     1. User hits /sign-in → NextAuth redirect
     2. Keycloak validates credentials
     3. JWT returned, stored in session
     
     [calls remember_context("auth_architecture", "The auth uses Keycloak...")]
     🧠 Context saved for future sessions.

--- Next day, new session ---

You: "How does auth work?"
AI:  [calls smart_recall("auth")]
     🧠 Found cached context:
     The auth uses Keycloak with JWT tokens...
     
     (No file reading needed — instant answer!)

You: "List all my cachly instances and their status"
AI:  Using cachly_list_instances...
     
     You have 3 instances:
     1. prod-api (Pro, running) — redis://:***@prod.cachly.dev:30101
     2. staging (Dev, running) — redis://:***@staging.cachly.dev:30102  
     3. ml-pipeline (Speed, running) — redis://:***@ml.cachly.dev:30103
     
     Total MRR: €72/month

You: "Check the analytics for my prod-api instance"
AI:  Using cachly_semantic_stats...
     
     ⚠️ Hit rate dropped 23% in the last 24h (82% → 63%)
     
     Anomaly detected: near-miss spike (+140%)
     → 47 queries are hitting similarity 0.80-0.84 (just below your 0.85 threshold)
     
     Recommendation: Lower threshold to 0.82 to capture these near-misses.
     
You: "Do it"
AI:  Using cachly_set_threshold... ✅ Threshold set to 0.82 for namespace cachly:sem

You: "Warm up the staging cache with our top 50 support questions"
AI:  Using cachly_batch_index with your FAQ embeddings...
     
     ✅ Indexed 50 entries in 340ms (batch pipeline)
     Namespace: cachly:sem:qa
     
     Your cache is ready — first users will get instant responses.

You: "How much has cachly saved me this month?"
AI:  Using cachly_semantic_stats...
     
     📊 This month's savings:
     - Total cache hits: 12,847
     - Estimated savings: $384.21 (vs. direct LLM calls)
     - Efficiency score: 84/100 (Grade: A)
     - Best namespace: cachly:sem:qa (94% hit rate)

You: "Check if any cache anomalies would block a deploy"
AI:  Using cachly_analytics_anomalies...
     
     ✅ No critical anomalies detected.
     1 info-level notice: stale cache in namespace "translations" 
     (12 near-misses/24h, 0 new entries)
     
     Recommendation: Run warmup after deploy for translations namespace.
     Deploy is safe to proceed.