Gulliver
Related Servers
Alternatives to Gulliver
No user-submitted related servers found.
Related Servers
- AlicenseAqualityAmaintenanceLets AI agents estimate the cost and result size of BigQuery and Snowflake queries before they run, then execute them only within per-call byte, row, and dollar bounds. Estimates are labeled with an accuracy tier so agents never over-trust an approximate figure.461 PyPI1MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to pre-flight estimate query costs, enforce hard budgets, reconcile actual billed spend, and suggest cheaper rewrites across BigQuery, Snowflake, and Databricks.MIT
- AlicenseAqualityBmaintenanceEnables AI coding agents to preflight SQL, NoSQL, graph, warehouse, and vector queries against real schemas or pasted DDL, estimating cost/risk, suggesting verified rewrites, and explaining plans before execution. It supports 12 database engines and catches costly query patterns without running the query.9MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI assistants to audit dbt project health, profile data, detect schema drift, suggest tests, and safely generate documentation through natural language.-
- FlicenseNot gradedqualityAmaintenanceEnables AI assistants to audit dbt project health, profile warehouse data, detect schema drift, and auto-generate documentation and test suggestions through natural language. It provides tooling for coverage scoring, batched column statistics, and non-destructive schema.yml updates.-
- FlicenseNot gradedqualityAmaintenanceEnables AI assistants to audit dbt project quality, profile warehouse data, detect schema drift, and safely generate or update model documentation and tests through natural language.-
TDQS
Scored across 16 tools
Each tool owns a distinct resource+action and every description explicitly disambiguates it from its nearest neighbours (e.g. 'use gulliver_fix for a single slow query', 'use gulliver_drift for schema changes, gulliver_diff for rows'). The potentially overlapping cluster of lint/fix/preflight/rehearse/run forms a strict, well-explained pipeline rather than competing tools, and diff/check/drift and impact/review/lint are likewise cleanly separated.
Every tool follows the same predictable gulliver_<single lowercase word> pattern with no camelCase, hyphenation or multi-word drift. Although the suffix is a topic word rather than a strict verb_noun pair, the convention is uniform and immediately readable across all 16 tools.
16 tools is slightly above the comfortable band but justified by an unusually broad domain (lint, rewrite, costing, execution, diffing, lineage, drift, translation, checks, workload and PR review). Each tool covers a genuinely different lifecycle stage, so none feels like filler, though a couple of pairs could conceivably be merged.
The SQL safety/cost lifecycle is covered end to end: inspect → lint → fix → preflight → rehearse → run → receipt, plus drift, diff, lineage, checks, incremental advice and PR review. Minor gaps remain: there is no tool to add/edit connections or budgets (status is read-only), no way to list recent receipts, and no explicit approval action even though runs can return needs_approval.