Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@android-sqlite-inspector list tables in my app's database"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server that inspects and queries SQLite databases on Android devices via ADB.
Node.js 18+
ADB installed and in PATH
A debuggable Android app (debug builds)
Related MCP server: mcp-sqlite-manager
npm install
npm run buildSet via environment variables:
Variable | Description | Default |
| App package name |
|
| ADB device serial (for multiple devices) | (auto-detect) |
| Custom path to ADB binary |
|
Add to ~/.claude/settings.json:
{
"mcpServers": {
"android-sqlite-inspector": {
"command": "node",
"args": ["/Users/andromeda/StudioProjects/android-sqlite-inspector/dist/index.js"],
"env": {
"ANDROID_PACKAGE": "com.hortusys"
}
}
}
}Tool | Description |
| List all |
| List all tables in a database |
| Show column schema for a table |
| Execute a SELECT query (returns JSON) |
| Execute INSERT/UPDATE/DELETE (pushes changes back to device) |
Each read operation pulls a fresh copy of the database from the device via adb shell run-as <package> cat databases/<db>
Queries run locally using better-sqlite3
Write operations (execute) pull the db, modify locally, then push back via ADB
Show the schema (columns, types, constraints) for a specific table.
Inputs: table (required), database (required).
Execute an INSERT, UPDATE, or DELETE SQL statement. Pulls the database, modifies it locally, then pushes it back to the device.
Inputs: sql (required), database (required).
Execute a SELECT query and export results to a local file as JSON or CSV.
Inputs: sql (required), format (required), database (required), file_path (required).
List all SQLite database files for the Android app (com.hortusys)
Inputs: no named parameters.
List all Android devices/emulators connected via ADB.
Inputs: no named parameters.
List third-party packages installed on the device. Useful for finding the correct package name.
Inputs: no named parameters.
List all tables in a SQLite database. Pulls a fresh copy from the device.
Inputs: database (required).
Execute multiple read-only SQL SELECT queries in a single call. More efficient than calling query multiple times.
Inputs: queries (required), database (required).
Execute a read-only SQL SELECT query. Returns results as JSON. Pulls a fresh copy from the device before querying.
Inputs: sql (required), database (required).
Execute a SELECT query with LIMIT/OFFSET pagination. Returns results plus total row count.
Inputs: sql (required), limit (required), database (required), offset.
Show Room database metadata: schema version, identity hash, and managed entities.
Inputs: database (required).
Compare schemas of two databases. Shows added/removed tables and columns.
Inputs: database_new (required), database_old (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Scored across 12 tools
Most tools target distinct actions and resources, but the query variants (query, multi_query, query_paginated, export) overlap in purpose and could be confused if descriptions are not read carefully. The read-only vs. write distinction between query and execute is clear, and schema_diff/room_info are well-separated from the rest.
The list_* tools follow a clear, consistent pattern, and describe_table, schema_diff, and export are also descriptive. However, room_info breaks the verb-noun pattern, and the query variants mix styles (query, multi_query, query_paginated) though they remain readable.
Twelve tools is well-scoped for an Android SQLite inspector, covering discovery, schema inspection, querying, and modification without unnecessary bloat. Each tool has a meaningful role in the workflow.
The tool surface covers the full inspection lifecycle: device discovery, package/database/table enumeration, schema details, read/write operations, pagination, batch queries, Room metadata, schema diffing, and export. No obvious dead ends or critical missing operations are apparent for the stated purpose.
Explore, query, and inspect SQLite databases with ease. List tables, preview results, and view det…
Explore your Messages SQLite database to browse tables and inspect schemas with ease. Run flexible…
Run SOQL queries to explore and retrieve Salesforce data. Inspect records, fields, and relationshi…
Kotlin compile-time SQL library. Docs, code validation, and SQLite execution tools.
