{
  "markdown": "### Prerequisites\n```bash\n# Install dependencies\npip install -r requirements.txt\n\n# Install FastMCP globally (if not already installed)\npip install fastmcp\n```\n\n### COMMAND CHEATSHEET\n```bash\n# Run FastMCP directly for testing\nSQLITE_DB_PATH=/Users/owner/claude-code/agentic-ai-learnings/hw3/sqlite-explorer-fastmcp-mcp-server/financial_data.db fastmcp run sqlite_explorer.py\n\n# Test with inspector (if available)\nSQLITE_DB_PATH=/Users/owner/claude-code/agentic-ai-learnings/hw3/sqlite-explorer-fastmcp-mcp-server/financial_data.db fastmcp inspect sqlite_explorer.py\n\n# To install SQLite Explorer\nSQLITE_DB_PATH=/Users/owner/claude-code/agentic-ai-learnings/hw3/sqlite-explorer-fastmcp-mcp-server/financial_data.db fastmcp install sqlite_explorer.py --name \"SQLite Explorer\"\n\n# To launch SQLite Explorer via a web-based testing interface. Run with `--transport sse` for HTTP-based communication  \nSQLITE_DB_PATH=/Users/owner/claude-code/agentic-ai-learnings/hw3/sqlite-explorer-fastmcp-mcp-server/financial_data.db fastmcp dev sqlite_explorer.py\n\n# To set up the MCP server with Claude Desktop\nSQLITE_DB_PATH=/Users/owner/claude-code/agentic-ai-learnings/hw3/sqlite-explorer-fastmcp-mcp-server/financial_data.db fastmcp claude-desktop add sqlite_explorer.py --name \"SQLite Explorer\"\n\n# Need to define the SQLITE_DB_PATH variable before running smithery playground \nSQLITE_DB_PATH=/Users/owner/claude-code/agentic-ai-learnings/hw3/sqlite-explorer-fastmcp-mcp-server/financial_data.db smithery playground\n```\n\nAfter launching Smithery playground, we can now talk to the MCP server using this URL: https://smithery.ai/playground?mcp=https%3A%2F%2Fee09cd8f.ngrok.smithery.ai%2Fmcp\n\n#### For VSCode with Cline\n```bash\n# Add this configuration to Cline MCP settings:\n{\n  \"sqlite-explorer\": {\n    \"command\": \"uv\",\n    \"args\": [\n      \"run\",\n      \"--with\",\n      \"fastmcp\",\n      \"--with\",\n      \"uvicorn\",\n      \"fastmcp\",\n      \"run\",\n      \"/Users/owner/claude-code/agentic-ai-learnings/hw3/sqlite-explorer-fastmcp-mcp-server/sqlite_explorer.py\"\n    ],\n    \"env\": {\n      \"SQLITE_DB_PATH\": \"/Users/owner/claude-code/agentic-ai-learnings/hw3/sqlite-explorer-fastmcp-mcp-server/financial_data.db\"\n    }\n  }\n}\n```\n\n#### Example output. MCP server provides four components. SQLite Explorer provides those tools.\nServer\n  Name:         SQLite Explorer\n  Generation:   2\n\nComponents\n  Tools:        3\n  Prompts:      0\n  Resources:    0\n  Templates:    0\n\nEnvironment\n  FastMCP:      2.12.4\n  MCP:          1.15.0\n\n  This will open an interactive inspector where you can test the MCP tools:\n  - list_tables - to see what tables are in your database\n  - describe_table - to see the structure of a specific table\n  - read_query - to run SELECT queries on your data\n\n\n### Notes\nEven though we're running the MCP locally, still have a web interface\nFor locally deployed MCP server SQLite Explorer, this is the MCP server URL that we can access as a client: http://localhost:6274/?MCP_PROXY_AUTH_TOKEN=e01acfa4461c1af5227669c2c0051e7cf9c280fb61a43a146a672463441f4c1b#tools\nIn the future, once deployed, we'll have the same thing - HTTP or HTTPS, but instead of a local host, it'll be my server and the port. The rest will be something else. \nLocal host is the server name, so the server is a local host. But if deployed somewhere, then it'll be a different host name. The port serves as a channel to talk to multiple MCP servers. HTTPS is a secure HTTP. \n\n#### Sample Questions to Ask Your AI Assistant\n\nOnce the MCP server is connected, you can ask questions like:\n\n- \"What tables are in my database?\"\n- \"Show me the structure of my financial data\"\n- \"What are the first 10 rows from [table_name]?\"\n- \"How many records are in each table?\"\n- \"Show me all transactions over $1000\"\n- \"What's the average amount in the transactions table?\"\n\nNOTE: The tables starting with SQLite are called system tables. We never created those tables.\n\n### Troubleshooting\n\n```bash\n# Check FastMCP version and available commands\nfastmcp --help\nfastmcp version\n\n# Verify your database file exists\nls -la /Users/owner/claude-code/agentic-ai-learnings/hw3/sqlite-explorer-fastmcp-mcp-server/financial_data.db\n\n# Test database directly with sqlite3\nsqlite3 /Users/owner/claude-code/agentic-ai-learnings/hw3/sqlite-explorer-fastmcp-mcp-server/financial_data.db \".tables\"\n```\n\n### HW 3 Documentation\n\n#### Step 1\nCloned this GitHub repository: https://github.com/hannesrudolph/sqlite-explorer-fastmcp-mcp-server\n\n#### Step 2\n\nAsked Claude Code: I was asked to evaluate the following deployment platforms: AWS, Vercel, \nRailway, and Smithery for my MCP server. I want the simplest and cheapest \ndeployment. Which option should I select? \n\n⏺ Based on your MCP server and requirements, I recommend Smithery.\n\n  Here's why:\n\n  Simplest: Smithery is specifically designed for MCP servers. It has the\n  most straightforward deployment process for this exact use case.\n\n  Cheapest: Smithery offers a free tier for MCP server hosting, making it\n  the most cost-effective option for your SQLite Explorer MCP server.\n\n  Other options comparison:\n  - AWS: Most complex setup, requires managing infrastructure, not\n  cost-effective for simple MCP servers\n  - Vercel: Designed for web apps/APIs, not optimized for MCP servers,\n  serverless model may not fit well\n  - Railway: Good platform but more expensive than Smithery's free tier,\n  more general-purpose\n\n  For a read-only SQLite MCP server like yours, Smithery's MCP-specific\n  infrastructure is the best match for \"simplest and cheapest.\"\n\n#### Step 3\n\nTested this locally via Cline. In VS Code, we configured the system settings to launch a web-based interface with the following JSON file. See URL: http://localhost:6274/?MCP_PROXY_AUTH_TOKEN=a164e503687338cb23938baf05ae738ebe5cd0eaefa629e419cea7ef6ef51563#tools\n\n#### Step 4\n\nsmithery playground URL : https://smithery.ai/playground?mcp=https%3A%2F%2F143c4151.ngrok.smithery.ai%2Fmcp\n\n\n",
  "bytes": 5944,
  "sha": "fea5c833ccc2e51de21a8112ed1c0dad88fbaff9f6e97370b066b9dfa4447d00",
  "repo_slug": "wgong/sqlite-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_smithery_wgong_sqlite_mcp_server_01e8569b/readme"
}