sqlscope-mcp
Related Servers
Alternatives to sqlscope-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceEnables AI agents and developers to introspect SQLite schemas, run sandboxed read-only queries with pagination, inspect query plans, and generate token-dense database summaries for LLM context. All operations enforce multi-layer read-only safety so databases can be explored without risk of mutation.5MIT
- AlicenseAqualityCmaintenanceEnables AI agents to explore and query SQLite databases through read-only, sandboxed tools for listing tables, describing schemas, fetching DDL, and running a single capped SELECT statement. Also supports plain-English questions that are converted to SQL and routed through the same sandbox.4MIT
- AlicenseAqualityBmaintenanceEnables AI agents to inspect database schemas and run strictly read-only SQL queries with guardrails against destructive statements, multi-statement chaining, and unbounded scans. Supports SQLite natively and PostgreSQL optionally.4363 PyPIMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to safely query and explore SQLite databases through read-only, guard-protected tools that block writes, sensitive table access, and runaway queries.1MIT
- AlicenseAqualityCmaintenanceEnables AI agents to safely explore and query a SQLite database in read-only mode, allowing them to inspect schema and run analytical SQL queries without risking data modification.3MIT
- AlicenseNot gradedqualityCmaintenanceEnables LLM clients to safely explore SQLite databases through schema discovery, sampling, read-only querying, and query-plan analysis, with schema resources and an analysis prompt.5 npmMIT
TDQS
Scored across 8 tools
Each tool has a reasonably distinct role: overview, single-table deep dive, whole-schema docs, FK graph, ad-hoc query, plan analysis, cross-DB text search and data-quality checks. The main overlap is between schema_docs and schema_graph, since both can emit a mermaid ER diagram, and data_quality partially overlaps with what an agent could do via query. Descriptions give strong cues (db_overview is explicitly 'start here'), so misselection is unlikely but not impossible.
All eight names use consistent snake_case with no camelCase or casing drift. The only inconsistency is grammatical style: some are verb_noun (describe_table, explain_query, find_in_db) while others are noun_noun (schema_docs, schema_graph, db_overview, data_quality) or a bare verb (query). Readable and predictable overall, just not a single uniform pattern.
Eight tools is a well-scoped set for a read-only SQLite inspection server, and each tool maps to a distinct inspection task. Nothing feels padded or redundant enough to merge, and nothing essential appears to be missing from the count.
Coverage of the read-only introspection domain is strong: schema docs, overview, per-table detail, FK graph, query execution, plan explanation, value search and data-quality auditing. Minor gaps exist, such as no explicit lightweight 'list tables/views/trigger names' operation (db_overview reports counts and describe_table requires a known name) and no schema-diff or index-only listing tool. The deliberately read-only scope means no write/migration operations, which is appropriate rather than a gap.