Skip to main content
Glama
j4c0bs

mcp-server-sql-analyzer

by j4c0bs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
lint_sqlB
Lint SQL query and return syntax errors

Some syntax errors are not detected by the parser like trailing commas

Args:
    sql: SQL query to analyze
    dialect: Optional SQL dialect (e.g., 'mysql', 'postgres')

Returns:
    error message or "No syntax errors" if parsing succeeds
transpile_sqlA
Transpile SQL statement to another dialect

Args:
    sql: SQL statement to transpile
    read_dialect: SQL dialect to read from
    write_dialect: SQL dialect to write to

Returns:
    transpiled SQL or syntax error
get_all_table_referencesA
Extract table and CTE names from SQL statement

Args:
    sql: SQL statement to analyze
    dialect: Optional SQL dialect (e.g., 'mysql', 'postgres')
Returns:
    JSON object containing tables with catalog, database, and alias attributes
    CTEs are returned as "cte" type
get_all_column_referencesA
Extract column references from SQL statement with table context

Args:
    sql: SQL statement to analyze
    dialect: Optional SQL dialect (e.g., 'mysql', 'postgres')
Returns:
    JSON object containing column references with table context and any errors

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
dialects://all
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.8/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: extracting column references, linting syntax, transpiling dialects, and extracting table references. There is no overlap or ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_object pattern in snake_case (e.g., get_all_column_references, lint_sql), making them predictable and readable.

Tool Count5/5

With 4 tools, the server is well-scoped for SQL analysis. Each tool serves a core function without being excessive or insufficient.

Completeness4/5

The tool set covers key SQL analysis tasks (extracting references, linting, transpilation). Missing features like formatting or optimization advice are minor gaps.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources