SQL Check
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port for the hosted Streamable HTTP mode (node src/server.mjs --http serves stateless MCP at POST /mcp). Default 3000. | |
| SQL_CHECK_TIMEOUT_MS | No | The engines run in a worker thread with a time limit (10 s per call, SQL_CHECK_TIMEOUT_MS to change it): a statement that never ends is stopped, reported with its number, and the engine is replaced. |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_sqlA | Runs SQL on real PostgreSQL 18 or SQLite 3.49 in memory, after your schema (DDL, migrations, sample INSERTs). Each statement gets the engine's verdict: error with line, column and hint, constraint violations, or the rows it returns (up to max_rows). All inside a rolled-back transaction. dialect both compares the two. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of selecting the wrong one. Its purpose (validating/running SQL statements against real engines) is unambiguous.
The single name check_sql follows a clear verb_noun convention. No mixed conventions are present since there is only one tool.
A single tool is thin against the typical 3-15 range, though the server's scope (execute and report on SQL) is narrow enough that one entry point is defensible. It packs multiple modes (dialect comparison, max_rows, rollback) into one surface.
For a stateless SQL execution/validation service the core operation is covered, including error reporting, constraints, and dialect comparison. Minor extras like EXPLAIN/plan output or schema-diff tooling are absent but not essential.