Executes SQL in a real ephemeral database: rows, typed errors with suggestions, plans, diffs.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Answer "do these two queries return the same thing?" — the self-check for query refactors. Executes query_a and query_b against identical fresh databases and compares result multisets (order-insensitive; order divergence reported separately when ORDER BY is present). Returns equal:boolean, row counts, and capped row-level diffs (only_in_a / only_in_b).
DDL statements.
Original query.
Refactored/alternative query.
Optional seed rows: {"table_name": [{"col": value, ...}, ...]}. Max 10MB total.
Engine. Server-side supports 'sqlite' (default). 'duckdb' runs in the browser demo at sqlai.dev only.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Answer "do these two queries return the same thing?" — the self-check for query refactors. Executes query_a and query_b against identical fresh databases and compares result multisets (order-insensitive; order divergence reported separately when ORDER BY is present). Returns equal:boolean, row counts, and capped row-level diffs (only_in_a / only_in_b).
| Argument | Type | Description |
|---|---|---|
| seed | object | Optional seed rows: {"table_name": [{"col": value, ...}, ...]}. Max 10MB total. |
| engine | string | Engine. Server-side supports 'sqlite' (default). 'duckdb' runs in the browser demo at sqlai.dev only. |
| schema* | string | DDL statements. |
| query_a* | string | Original query. |
| query_b* | string | Refactored/alternative query. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"schema",
"query_a",
"query_b"
],
"properties": {
"seed": {
"type": "object",
"description": "Optional seed rows: {\"table_name\": [{\"col\": value, ...}, ...]}. Max 10MB total.",
"additionalProperties": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {}
}
}
},
"engine": {
"enum": [
"sqlite",
"duckdb"
],
"type": "string",
"description": "Engine. Server-side supports 'sqlite' (default). 'duckdb' runs in the browser demo at sqlai.dev only."
},
"schema": {
"type": "string",
"description": "DDL statements."
},
"query_a": {
"type": "string",
"description": "Original query."
},
"query_b": {
"type": "string",
"description": "Refactored/alternative query."
}
},
"additionalProperties": false
}Return the engine-native query plan for a query (SQLite: EXPLAIN QUERY PLAN) plus full-table-scan warnings. Use it to check whether an index would be used before recommending one. Example: "SELECT * FROM orders WHERE status=?" on an unindexed column → plan ["SCAN orders"], warning about the full scan.
| Argument | Type | Description |
|---|---|---|
| query* | string | ONE SQL statement to explain. |
| engine | string | Engine. Server-side supports 'sqlite' (default). 'duckdb' runs in the browser demo at sqlai.dev only. |
| schema* | string | DDL statements (include your indexes!). |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"schema",
"query"
],
"properties": {
"query": {
"type": "string",
"description": "ONE SQL statement to explain."
},
"engine": {
"enum": [
"sqlite",
"duckdb"
],
"type": "string",
"description": "Engine. Server-side supports 'sqlite' (default). 'duckdb' runs in the browser demo at sqlai.dev only."
},
"schema": {
"type": "string",
"description": "DDL statements (include your indexes!)."
}
},
"additionalProperties": false
}Execute a SQL query against a fresh ephemeral in-memory database built from your schema (and optional seed rows). Returns real rows (max 500, truncation flagged), column names+types, row_count, and dialect notes. Errors come back as structured JSON with type/position/suggestion — a failed query is a useful answer, not a failure of this tool. Example: schema "CREATE TABLE t(id INTEGER, name TEXT);", query "SELECT name FROM t WHERE id=1", seed {"t":[{"id":1,"name":"ada"}]} → rows [["ada"]].
| Argument | Type | Description |
|---|---|---|
| seed | object | Optional seed rows: {"table_name": [{"col": value, ...}, ...]}. Max 10MB total. |
| query* | string | ONE SQL statement to execute. Stacked statements are rejected. |
| engine | string | Engine. Server-side supports 'sqlite' (default). 'duckdb' runs in the browser demo at sqlai.dev only. |
| schema* | string | DDL statements (CREATE TABLE ...; multiple statements allowed). |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"schema",
"query"
],
"properties": {
"seed": {
"type": "object",
"description": "Optional seed rows: {\"table_name\": [{\"col\": value, ...}, ...]}. Max 10MB total.",
"additionalProperties": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {}
}
}
},
"query": {
"type": "string",
"description": "ONE SQL statement to execute. Stacked statements are rejected."
},
"engine": {
"enum": [
"sqlite",
"duckdb"
],
"type": "string",
"description": "Engine. Server-side supports 'sqlite' (default). 'duckdb' runs in the browser demo at sqlai.dev only."
},
"schema": {
"type": "string",
"description": "DDL statements (CREATE TABLE ...; multiple statements allowed)."
}
},
"additionalProperties": false
}Run up to 10 queries against the same schema+seed. Each query executes in its OWN fresh database — writes in one query are NOT visible to the next (use this for testing variants, not for multi-statement transactions). Returns an array of run_sql results in order.
| Argument | Type | Description |
|---|---|---|
| seed | object | Optional seed rows: {"table_name": [{"col": value, ...}, ...]}. Max 10MB total. |
| engine | string | Engine. Server-side supports 'sqlite' (default). 'duckdb' runs in the browser demo at sqlai.dev only. |
| schema* | string | DDL statements. |
| queries* | array | Up to 10 statements, one per entry. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"schema",
"queries"
],
"properties": {
"seed": {
"type": "object",
"description": "Optional seed rows: {\"table_name\": [{\"col\": value, ...}, ...]}. Max 10MB total.",
"additionalProperties": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {}
}
}
},
"engine": {
"enum": [
"sqlite",
"duckdb"
],
"type": "string",
"description": "Engine. Server-side supports 'sqlite' (default). 'duckdb' runs in the browser demo at sqlai.dev only."
},
"schema": {
"type": "string",
"description": "DDL statements."
},
"queries": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"description": "Up to 10 statements, one per entry."
}
},
"additionalProperties": false
}Validate a SQL query against a schema WITHOUT executing it (parse + name/type binding via EXPLAIN). Returns ok with referenced tables, or a structured error: {type: unknown_column|unknown_table|syntax|..., message, position, suggestion}. The suggestion is rule-based (edit distance against your schema). Example: query "SELECT nmae FROM users" → error type unknown_column, suggestion 'did you mean "name"?'.
| Argument | Type | Description |
|---|---|---|
| query* | string | ONE SQL statement to validate. |
| engine | string | Engine. Server-side supports 'sqlite' (default). 'duckdb' runs in the browser demo at sqlai.dev only. |
| schema* | string | DDL statements. |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"schema",
"query"
],
"properties": {
"query": {
"type": "string",
"description": "ONE SQL statement to validate."
},
"engine": {
"enum": [
"sqlite",
"duckdb"
],
"type": "string",
"description": "Engine. Server-side supports 'sqlite' (default). 'duckdb' runs in the browser demo at sqlai.dev only."
},
"schema": {
"type": "string",
"description": "DDL statements."
}
},
"additionalProperties": false
}