whodb-cli
OfficialRelated Servers
Alternatives to whodb-cli
- FlicenseBqualityFmaintenanceFireproof ledger database with multi-user sync49 npm31-
- AlicenseNot gradedqualityNot gradedmaintenanceAn MCP server that provides tools for interacting with Supabase databases, storage, and edge functions.45MIT
- AlicenseNot gradedqualityDmaintenanceProvides a natural language interface for querying and managing PostgreSQL, MySQL, MariaDB, MSSQL, and SQLite databases using the Model Context Protocol. Users can explore database schemas and visualize query results through an integrated web dashboard.15 npmMIT
Related Servers
- AlicenseAqualityAmaintenanceOne config, one CLI that turns your databases (Postgres, MySQL, SQLite, MongoDB) into MCP servers for Claude, GPT, Cursor, and any MCP-compatible agent.31MIT
- FlicenseAqualityCmaintenanceMCP Chat is a CLI application that enables interactive chat with AI models via the Anthropic API, supporting document retrieval, command-based prompts, and extensible MCP tool integrations.2-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants like Claude to interact with MongoDB databases through standardized MCP tools. Supports full CRUD operations, aggregations, and natural language queries with Clean Architecture and dual transport modes (STDIO/HTTP).MIT
- AlicenseNot gradedqualityAmaintenanceMulti-database management tool and MCP server supporting MySQL, PostgreSQL, SQLite, and Dameng DM8, enabling AI assistants to query and manage databases via stdio or HTTP.MIT
- AlicenseAqualityCmaintenanceA database MCP server providing 33 tools across PostgreSQL, MySQL, and SQLite, with connection groups, rollback, dump/restore, and schema auto-discovery via natural language.3442 npm2MIT
- AlicenseNot gradedqualityAmaintenanceThe Multi DB MCP Server is a high-performance implementation of the Database Model Context Protocol designed to revolutionize how AI agents interact with databases. Currently supporting MySQL and PostgreSQL databases.468MIT
TDQS
Scored across 156 tools
The surface is riddled with overlapping read tools that all answer 'what's in my project' (workspace_summary, workspace_map, project_health, project_resources, data_model_summary, resource_graph, next_actions, gap_analysis), and four competing write paths (generic create/update/action, typed source_create/create_dataset wrappers, preview, write_plan, workflow_apply). The near-identical preview_* family (preview_create_package, preview_import_package, preview_install_package, preview_shared_import, preview_shared_install) and the product-specific ontology query/rows/aggregate/stats/follow_link set are better delimited, but an agent must read long prose to choose correctly.
Everything uses snake_case with the whodb_platform_ prefix, which helps, but there is no consistent verb_noun scheme: list tools are bare nouns (sources, datasets, ontologies, packages, teams), reads use inspect/read/view/get variably, and there are singular/plural pairs (app_sdk/app_sdks, app_view/app_views, project_access/resource_access, installation vs installations). The lone whodb_mcp_setup breaks the prefix convention entirely.
156 tools is far beyond any reasonable scope and will swamp an agent's context and selection accuracy, even for a broad hosted data platform. Many entries are thin variations of each other, so the count reflects surface sprawl rather than earned capability.
Coverage is genuinely deep: CRUD for sources, datasets, ontologies, transforms, functions, apps and packages, plus sharing, lineage, versions, storage, org/team admin, confirmation lifecycle and workflow persistence. Some operations are only reachable through the catch-all whodb_platform_action and external schema document, which is a minor gap but not a dead end.