Developer Tools
sqlai.dev
Provides ephemeral in-memory SQL database for validating, executing, and comparing queries.
ENDPOINT 1
https://mcp.sqlai.dev/mcp
MCP server metadata
- Name
- sqlai-dev-sql-verifier
- Version
- 1.0.0
Known tools 5
run_sqlExecute a SQL query against a fresh ephemeral in-memory database built from your schema (and optional seed rows).
Potential side effectsvalidate_sqlValidate a SQL query against a schema WITHOUT executing it (parse + name/type binding via EXPLAIN).
Inferred read-onlyexplain_planReturn the engine-native query plan for a query (SQLite: EXPLAIN QUERY PLAN) plus full-table-scan warnings.
Inferred read-onlydiff_resultsAnswer "do these two queries return the same thing?" — the self-check for query refactors.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.sqlai-dev-sql-verifier]
url = "https://mcp.sqlai.dev/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"sqlai-dev-sql-verifier": {
"type": "http",
"url": "https://mcp.sqlai.dev/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: sqlai-dev-sql-verifier
Remote MCP URL: https://mcp.sqlai.dev/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"sqlai-dev-sql-verifier": {
"url": "https://mcp.sqlai.dev/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"sqlai-dev-sql-verifier": {
"type": "http",
"url": "https://mcp.sqlai.dev/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "sqlai-dev-sql-verifier",
"transport": "streamable-http",
"url": "https://mcp.sqlai.dev/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.