Skip to main content
Glama
sql-explorer-mcp

sql-explorer-mcp

by timsuv

sql-explorer-mcp

Personal, read-only MCP server for browsing/querying a SQL Server database from Claude Code (or any MCP client). Built for local dev use — not intended to be exposed over a network or shared with other people.

Tools exposed

  • list_schemas — list all schemas

  • list_tables — list tables, optionally filtered by schema

  • list_views — list views, optionally filtered by schema

  • list_procedures — list stored procedures, optionally filtered by schema

  • list_functions — list functions (with return type), optionally filtered by schema

  • describe_table — columns, types, nullability, primary key for a table

  • describe_view — columns and the CREATE VIEW definition for a view

  • describe_procedure — parameters and the CREATE PROCEDURE definition (metadata only — never executes it)

  • describe_function — parameters, return type, and the CREATE FUNCTION definition (metadata only — never executes it)

  • browse_table — SELECT TOP N * FROM schema.table (no filter)

  • query_table — same as above with one validated WHERE column op value condition

  • join_tables — SELECT across multiple tables/views with explicit join conditions; every table, alias, and column is validated the same way as the single-table tools

  • run_query — arbitrary read-only SQL: CTEs (WITH ...), subqueries, GROUP BY/aggregates, window functions, UNION, ORDER BY — anything a single SELECT statement can express. See safety notes below.

  • find_similar_names — Jaro-Winkler fuzzy search over table/view/column/procedure/function names, for when you don't remember the exact spelling

  • fuzzy_search_column — Jaro-Winkler fuzzy search over the distinct values of a single text column

Related MCP server: SQL Query Tools MCP Server

Safety notes

  • Point this at a read-only login. Create a SQL login scoped to db_datareader (or equivalent) on whatever database you connect it to. The tool code itself never issues writes, but the real safety boundary should be the DB permission, not the app logic.

  • Every schema/table/column name used in a query is checked against a live INFORMATION_SCHEMA lookup before being used — the server never interpolates an unverified identifier into SQL.

  • Filter values in query_table and join_tables are always passed as parameters (@value), never string-concatenated.

  • join_tables accepts no raw SQL — table/column names are whitelisted per the rule above, and join aliases (which aren't real DB identifiers) are restricted to a safe [A-Za-z_][A-Za-z0-9_]* pattern before being quoted in.

  • run_query is the one tool that accepts raw SQL text, so it doesn't get the whitelist treatment — it gets two layers instead. First, a text-level guard rejects anything but a single SELECT/WITH ... SELECT statement and rejects the query outright if it contains a second ;-separated statement or any of INSERT/UPDATE/DELETE/MERGE/EXEC/EXECUTE/DROP/ALTER/CREATE/ TRUNCATE/GRANT/REVOKE/DENY/OPENROWSET/OPENDATASOURCE/OPENQUERY/BULK/INTO/ sp_executesql. Second, even after passing that check, the query runs inside a transaction that is unconditionally rolled back afterwards — so a write that somehow slips past the text filter still can't persist. Neither layer is a parser, and neither is a substitute for the read-only DB login recommended above — they're defense in depth on top of it, not instead of it.

  • describe_procedure/describe_function only ever read metadata (INFORMATION_SCHEMA.PARAMETERS, OBJECT_DEFINITION()) — there is no tool that calls EXEC, since running a procedure could itself be a write.

  • The fuzzy-search tools (find_similar_names, fuzzy_search_column) compute Jaro-Winkler similarity in-process after a normal validated SELECT; the search term never becomes part of the SQL text.

  • Row limits are capped server-side at 200 regardless of what's requested.

Setup

npm install
npm run build

Environment variables

Variable

Required

Notes

DB_SERVER

yes

e.g. your-server.database.windows.net

DB_NAME

yes

database name

DB_USER

yes

read-only SQL login

DB_PASSWORD

yes

DB_ENCRYPT

no

defaults to true (needed for Azure SQL)

DB_TRUST_CERT

no

set true only for local dev instances with self-signed certs

Claude Code configuration

Add to your MCP config (project-level .mcp.json or global config):

{
  "mcpServers": {
    "sql-browser": {
      "command": "node",
      "args": ["/absolute/path/to/sql-mcp-server/dist/index.js"],
      "env": {
        "DB_SERVER": "your-server.database.windows.net",
        "DB_NAME": "your-db",
        "DB_USER": "readonly_user",
        "DB_PASSWORD": "your-password",
        "DB_ENCRYPT": "true"
      }
    }
  }
}

Don't commit real credentials into .mcp.json if the repo is shared — use a local, gitignored config, or reference environment variables already set on your machine.

Extending

The query_table tool intentionally supports only a single WHERE condition to keep the validation surface small. If you need multiple conditions later, extend the input schema to accept an array of { column, operator, value } and validate each one against getValidColumns() the same way — resist the temptation to accept a raw SQL fragment.

Available Tools

15 tools
browse_tableBrowse tableA

Preview rows from a table (SELECT TOP N *). Max 200 rows, no filtering — use query_table for filtered results.

Inputs: table (required), schema (required), limit.

describe_functionDescribe functionA

Get parameters, return type, and the SQL definition (CREATE FUNCTION body) for a function. This tool only reads the function's metadata — it never executes it.

Inputs: schema (required), function (required).

describe_procedureDescribe stored procedureA

Get parameters and the SQL definition (CREATE PROCEDURE body) for a stored procedure. This tool only reads the procedure's metadata — it never executes it.

Inputs: schema (required), procedure (required).

describe_tableDescribe tableA

Get column names, data types, nullability, and primary key info for a table.

Inputs: table (required), schema (required).

describe_viewDescribe viewA

Get column names/types for a view, plus its SQL definition (CREATE VIEW body).

Inputs: view (required), schema (required).

find_similar_namesFind similar names (fuzzy)A

Jaro-Winkler fuzzy search over table/view/column/procedure/function names — use this when you don't remember the exact spelling of an object.

Inputs: searchTerm (required), kinds, limit.

fuzzy_search_columnFuzzy search column valuesA

Jaro-Winkler fuzzy search over the distinct values of a single text column — use this to find rows whose value is close to (but not an exact match for) a search term. Samples up to sampleSize distinct values server-side, then ranks them client-side.

Inputs: table (required), column (required), schema (required), searchTerm (required), +2 more.

join_tablesJoin tablesA

Select across multiple tables/views with explicit join conditions. Every table and column is validated against the real schema (same as browse_table/query_table) — no raw SQL fragments are accepted. Max 200 rows, up to 6 joins.

Inputs: base (required), joins (required), limit, where, +1 more.

list_functionsList functionsA

List functions in the database, optionally filtered to a single schema. Includes the return data type.

Inputs: schema.

list_proceduresList stored proceduresA

List stored procedures in the database, optionally filtered to a single schema.

Inputs: schema.

list_schemasList schemasA

List all schemas in the connected database.

Inputs: no named parameters.

list_tablesList tablesA

List tables in the database, optionally filtered to a single schema. Returns table_schema and table_name for each.

Inputs: schema.

list_viewsList viewsA

List views in the database, optionally filtered to a single schema. Returns table_schema and table_name for each.

Inputs: schema.

query_tableQuery table with filterA

Select rows from a table with a single WHERE condition (column, operator, value). Column and operator are validated against the real schema. Max 200 rows.

Inputs: table (required), value (required), column (required), schema (required), +2 more.

run_queryRun raw SQL query (read-only)A

Run an arbitrary read-only query — CTEs (WITH ...), subqueries, GROUP BY/aggregates, window functions, UNION, ORDER BY, anything a single SELECT statement can express. Only one SELECT (optionally led by a WITH clause) statement is allowed: the query is rejected before it reaches the database if it contains a second statement or any write/DDL/EXEC keyword, and it additionally always runs inside a transaction that gets rolled back afterwards regardless of outcome, as a second line of defense. Results are capped at 500 rows.

Inputs: query (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 15 tools

    Disambiguation5/5

    Each tool targets a distinct aspect of SQL exploration: listing metadata, describing specific object types, browsing/querying/joining data, running arbitrary read-only queries, and fuzzy-searching names vs column values. Even the query tools have clear boundaries (browse=unfiltered preview, query=single condition, join=multi-table validated, run=arbitrary SQL).

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern (list_*, describe_*, browse_table, query_table, join_tables, run_query, find_similar_names, fuzzy_search_column). The verb accurately reflects the operation and the noun indicates the target object.

    Tool Count5/5

    15 tools is at the upper end of a well-scoped server, but each tool serves a unique and justified purpose—covering listing, describing, querying, joining, arbitrary read-only execution, and fuzzy search. No redundant or trivial tools are present.

    Completeness5/5

    The tool set provides comprehensive coverage for a SQL schema/data explorer: complete metadata listing (schemas, tables, views, procedures, functions), detailed descriptions (columns, definitions, parameters), multiple data retrieval methods (browse/query/join/run_query), and fuzzy search for both object names and column values. No significant gaps are apparent.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Read-only SQL Server MCP server enabling safe database queries, table listing, and schema inspection with built-in security protections.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      MCP server for connecting to SQL Server in readonly mode. Allows any MCP client to explore the schema and run SELECT queries against a SQL Server database.
      6
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A read-only, schema-aware MCP server that connects to SQL databases and provides tools for refining questions, browsing schema, validating, explaining, and running SELECT statements with safety guards.
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      A read-only MCP server for exploring and querying Oracle schemas safely. Provides tools for table listing, schema description, column search, and validated SELECT execution.
      2
      -