local-data-mcp
Exposes a local SQLite database as structured read-only tools, enabling table listing, schema inspection, ad-hoc SELECT/WITH/EXPLAIN queries, product search, customer lookup with order history, and sales summaries, plus access to the database schema as a resource.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
local-data-mcp
An MCP server that exposes a local SQLite database to LLM clients (Claude Desktop, Claude Code, MCP Inspector, …) as structured, read-only tools.
Every tool returns a Pydantic model, so clients get both an outputSchema up front and typed
structuredContent in each result (plus a JSON text fallback for older clients).
Quick start
uv sync
uv run local-data-mcp --seed # creates data/store.db with sample store data
uv run pytest # 16 tests, incl. a real stdio round-trip
uv run local-data-mcp # serve over stdioPoint it at your own database with --db path/to/file.db or LOCAL_DATA_DB=.... The generic tools
(list_tables, describe_table, run_query) work on any SQLite file. The domain tools assume the
sample schema, so replace them with ones that fit your data (see "Adapting" below).
Related MCP server: Read-Only SQLite Shop Database MCP Server
What it exposes
Kind | Name | Purpose |
tool |
| Tables + row counts |
tool |
| Columns, FKs, row count, 3 sample rows |
tool |
| Ad-hoc read-only SQL ( |
tool |
| Filter by name, category, price range, stock |
tool |
| Customer by id/email + lifetime value + recent orders with items |
tool |
| Revenue/units/orders grouped by month, category or product, with a date range |
resource |
| Full DDL |
prompt |
| Canned analysis workflow using the tools above |
All tools carry readOnlyHint / idempotentHint annotations.
Safety model
Connections open the file with
mode=ro, so SQLite itself refuses writes.run_queryalso installs a SQLite authorizer that denies everything except SELECT/READ/FUNCTION/RECURSIVE. That covers cases likeWITH x AS (...) DELETE ...,ATTACHand pragmas.Only one statement is allowed per call, and results are capped at
limit(max 1000), with atruncatedflag.Table names in
describe_tableare checked againstsqlite_masterand never interpolated from raw input.Bad input becomes a tool error (
isError: true) that the model can read and recover from, not a crash.
Connect a client
Claude Code
claude mcp add local-data -- uv --directory /ABSOLUTE/PATH/local-data-mcp run local-data-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"local-data": {
"command": "uv",
"args": ["--directory", "/ABSOLUTE/PATH/local-data-mcp", "run", "local-data-mcp"],
"env": { "LOCAL_DATA_DB": "/ABSOLUTE/PATH/local-data-mcp/data/store.db" }
}
}
}MCP Inspector (interactive debugging)
npx @modelcontextprotocol/inspector uv run local-data-mcpOver HTTP: uv run local-data-mcp --transport streamable-http serves at http://127.0.0.1:8000/mcp.
In stdio mode, stdout carries the protocol. Never
print()to stdout in server code; log to stderr.
Layout
src/local_data_mcp/
__init__.py CLI entry point (--db, --seed, --transport)
server.py MCPServer: tools, resource, prompt
models.py Pydantic output models -> outputSchema / structuredContent
db.py read-only SQLite access + authorizer
seed.py deterministic sample database
tests/ in-memory client tests + stdio end-to-end testAdapting to your own data
Swap
Databaseindb.pyfor your source (CSV viacsv/DuckDB, a JSON folder, Postgres, …).Model each answer shape in
models.py.Add one
@mcp.tool()per question the model should be able to answer. Give each a clear docstring (it becomes the tool description) andAnnotated[..., Field(description=...)]parameters (they become the input schema).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Astra DB tools for agents: schema, find, vector search, guarded writes, and interactive views.
Explore, query, and inspect SQLite databases with ease. List tables, preview results, and view det…
PostgreSQL, MySQL, and SQL Server in one session. 26 read-only MCP tools for AI agents.
Text-to-SQL MCP server: read-only queries on PostgreSQL, MySQL and SQL Server with your real schema
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceExposes a SQLite database to AI assistants with structured, read-safe access. Includes five tools for schema exploration, querying, and sampling data.-
- FlicenseAqualityDmaintenanceEnables AI agents to safely inspect and query an SQLite e-commerce database with tools for listing tables, describing schemas, and running read-only SQL queries while blocking destructive operations.4-
- FlicenseAqualityDmaintenanceEnables AI agents to read-only query an online store's SQLite database, listing tables, inspecting schemas, and running SELECT queries over customers, products, orders, and order items.3-
- FlicenseAqualityDmaintenanceGives AI agents read-only analytical access to an e-commerce SQLite database (customers, orders, order_items, products) via SQL queries, table listing, and schema inspection.3-