SQLite MCP in Claude Code

Quick answer: Install the SQLite MCP server with npx -y @modelcontextprotocol/server-sqlite /Users/you/data/app.db, add the JSON block below to ~/.claude/settings.json, restart Claude Code, and run /mcp to confirm the connection. Setup runs about 5 minutes on a fresh machine, verified on @modelcontextprotocol/server-sqlite as of April 15, 2026.

The SQLite MCP server gives Claude Code direct query access to a local SQLite file. For small personal projects, test fixtures, or cached datasets, SQLite is the fastest way to give Claude a structured data backend without spinning up a server. The MCP server ships from Anthropic as @modelcontextprotocol/server-sqlite and takes the database path as a single positional argument.

This guide covers what you get after the wiring is done, the exact config, verification steps, prompt patterns that tend to work well, and the 4 issues that trip people up most often in the first week.

What you get when it is connected

Once the SQLite server is attached, Claude Code can call the server tools from inside any conversation. You do not invoke the tools by hand. When you ask Claude a question the model decides which tool to call and parses the response for you. For teams that live inside SQLite day to day, this replaces dozens of context switches per week with a single line in chat.

Tools exposed: read_query, write_query, create_table, list_tables, describe_table, append_insight. The append_insight tool writes a memo to an internal insights table the server creates on first launch, which Claude uses to remember findings across sessions. If you want a clean slate, drop the mcp_insights table between sessions.

Prerequisites

A .sqlite or .db file on disk, and Node 20 or later. No network is involved. The database can be created ahead of time with the sqlite3 CLI or any GUI tool.

If you use a version manager like nvm or asdf for Node, confirm the version Claude Code inherits. Open a terminal, run node -v, and note the output. Claude Code uses the Node it sees on PATH at launch, so a shell profile that sets the right version is the reliable path.

Install via npx

Run the package once with npx to verify it starts cleanly:

npx -y @modelcontextprotocol/server-sqlite /Users/you/data/app.db

The first run downloads the package (a few MB) and starts the server on stdio. The server does not print much on success - it waits for MCP protocol messages on stdin. Press Ctrl-C to stop it. The actual runtime setup happens through Claude Code itself in the next step.

If the install fails with a network error, your npm registry may be blocked. Set npm config set registry https://registry.npmjs.org and retry. Behind a corporate proxy, also set HTTP_PROXY and HTTPS_PROXY in your shell.

Add the config block to ~/.claude/settings.json

Open ~/.claude/settings.json in your editor. If the file does not exist yet, create it with {} as the starting content. Add an mcpServers object with an entry for this server:

{
  "mcpServers": {
    "sqlite": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sqlite",
        "/Users/you/data/app.db"
      ]
    }
  }
}

Save the file. If you already have other MCP servers defined, merge the new entry into the existing mcpServers object rather than replacing it.

Restart Claude Code fully (quit and reopen, not just close the window). The server is spawned lazily on the first tool call in a session, not at launch, but the config is read once per Claude Code start.

Verify the connection

Open a new Claude Code session and type /mcp at the prompt. You should see the server listed with a green or connected indicator. If it shows as failed, click into it for the stderr output - the error message usually points at the problem directly (bad token, wrong path, missing Node).

Run a trivial first prompt to confirm round trips work. Good smoke tests:

• For read servers: ask for a list of whatever resource type it exposes.
• For write servers: ask for a describe on a known resource first, then try a safe write on a test resource.

If the first prompt works, the wiring is done. From here on you interact with the server purely through normal prompts in Claude Code.

Example prompts that work well

Here are prompts that tend to get good responses once the server is attached:

• Describe every table in the database and show me how many rows each one holds.
• Run a SELECT on the users table joined against orders, and tell me the top five customers by lifetime value.
• Check for any NULL values in the email column of users and return the count plus the first 10 offending row IDs.
• Write a query that finds duplicate entries in the products table based on sku, then run it.
• Export the last 30 days of entries from the logs table to a CSV at tmp/recent_logs.csv.
• Run EXPLAIN QUERY PLAN on SELECT * FROM orders WHERE customer_id = 42 and tell me whether it hits an index.

Claude will chain tool calls on its own when the prompt implies several steps. For a summarize-then-write flow the model will often call read tools first, then a single write tool at the end. If a prompt keeps burning tool calls, narrow it: specify the resource ID, the time range, or the exact field you want rather than asking Claude to scan everything.

Environment variable security

The database path is a positional argument rather than an env var, so there are no secrets to manage. For sensitive local databases, set file permissions to 600 so only your user can read the file. On shared hosts, consider a per-user copy rather than pointing multiple Claude Code instances at the same file.

A general rule across every MCP server: never paste secrets directly into settings.json that lives in a shared or git-tracked directory. Keep the actual secret values in your shell profile (~/.zshrc, ~/.bashrc, or a 1Password-cli helper), export them at shell start, and reference the variable names from the Claude config. That way the secret stays on your machine and the config file is safe to share with teammates.

On macOS, terminals launched from Spotlight or from the Dock both inherit the shell profile. If you launch Claude Code from a GUI shortcut that does not go through a shell, env vars may not propagate - launch from a terminal instead.

Troubleshooting

Server reports unable to open database file. The path is wrong or the file is not readable by your user. Check with ls -l and make sure the path in your config is absolute. Relative paths resolve against whatever directory Claude Code was launched from, which is rarely what you want.

Writes fail with readonly database. The server opens the file in read-write mode by default, but if the parent directory is read-only or the file has the read-only flag set, writes fail. Run chmod u+w path/to/app.db to fix.

Concurrent access from another app locks the file. SQLite locks on write. If a background process is writing to the same file, Claude queries will block or fail with SQLITE_BUSY. Ask Claude to retry, or enable WAL mode with PRAGMA journal_mode=WAL to allow concurrent reads during writes.

Large result sets truncate. The server caps results at a few thousand rows per call. Rewrite the query with LIMIT and paginate, or aggregate server-side with GROUP BY so the model does not need the raw rows.

For any issue not listed here, the first step is /mcp inside Claude Code to see the current status and any recent stderr from the server. The second step is running the exact npx command from your terminal to see if the server starts cleanly outside Claude Code. Between those two checks, most problems become obvious within a minute.

Next steps

Once the SQLite server is attached and verified, the useful next move is writing a short prompt template you keep in your notes. List the 3 or 4 prompts you run most often against this server, and paste them into Claude Code when needed. Over a few weeks you build a personal command library that gets real work done without typing much.

For team projects, commit a .mcp.json at the repo root with the same structure. Everyone on the team gets the server wired up automatically on first open, and individual secrets stay in shell profiles. That is the setup pattern that scales past a single developer.