Skip to main content
Glama

Related Servers

Alternatives to schemagate

  • A
    license
    A
    quality
    C
    maintenance
    Lets an LLM explore a cryptic legacy ERP schema in plain language through a semantic layer (table listing, column descriptions, published dictionary) and run single read-only SELECT queries that return capped results. Enforces safety at the database engine level: only reads are authorized, sensitive columns are masked to NULL, queries are aborted after a few seconds, and every call is written to an append-only audit log.
    3
    MIT

Related Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    Provides a guarded semantic layer for text-to-SQL, offering tools for schema discovery, semantic profiling, and query verification to enable safe and reliable SQL generation on enterprise databases.
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Serves prebuilt schema maps to AI agents over MCP, enabling table search, table descriptions, ranked join paths, key lookups, and business-context retrieval so text-to-SQL agents can write accurate queries without exploring the production database.
    3
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables natural-language queries over data warehouses with catalog-grounded semantics and per-query authorization, returning answers with attached reasoning.
    Apache 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to understand and query your database safely by providing a semantic layer of metadata, with tools to search, explain, validate, and generate safe SQL.
    2
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Lets AI clients ask natural-language questions about a SQL database with production-safe guardrails, schema grounding, and read-only enforcement.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI assistants to understand an entire SQL database by serving schema facts, business semantics, verified joins and metrics, a knowledge graph, and long-term memories, while supporting read-only validation queries and learning from corrections.
    MIT

TDQS

A4.4/5.0

Scored across 9 tools

Disambiguation4/5

The core workflow (select_schema -> run_query, with describe_object/list_objects/refresh_catalog/health as clear supporting utilities) is unambiguous, and descriptions explicitly steer clients away from answer/deep_answer. However, answer, deep_answer, and semantic_query all wrap model-driven querying and share the same read-only checks, so an agent must read carefully to pick among them, especially when the deep/semantic features are disabled by env flags.

Naming Consistency4/5

Eight of nine names follow a predictable snake_case verb_noun or noun_verb form (run_query, select_schema, describe_object, list_objects, refresh_catalog, semantic_query). The outliers are the bare 'answer' and noun-only 'health', plus the adjective-prefixed 'deep_answer', which are readable but break the verb pattern.

Tool Count5/5

Nine tools is well-scoped for a read-only schema gateway: a discovery path, a query path, three catalog/ops utilities, and two optional model-assisted modes. Each tool has a distinct role and none feels like filler.

Completeness4/5

The surface covers the full read-only lifecycle: discover objects, inspect DDL, select relevant schema, execute scoped SQL, refresh the catalog, and check health, with no writes needed by design. Minor gaps remain, such as no dedicated column/value search tool (select_schema relies on question phrasing and top_k) and no way to sample values without enabling the off-by-default deep mode.

Maintenance

ActivityActive
ResponsivenessLimited data