io.github.0xmortuex/duckdb-mcp
Related Servers
Alternatives to io.github.0xmortuex/duckdb-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables an AI agent to run read-only SQL over local CSV, Parquet, and JSON files through MCP tools, with directory sandboxing, statement gating, timeouts, and query timeouts that keep access confined to permitted folders. Results are shaped for small context windows with row caps, truncation notices, and markdown/CSV/JSON output.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to explore and analyse local CSV, Parquet or JSON files through validated read-only SELECT queries, with schema discovery, profiling and query-plan tools. Results are capped, timed, PII-masked and audit-logged inside a locked DuckDB sandbox that cannot write, reach the network or read other files.18 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients like Claude Desktop, Claude Code and Cursor to safely explore local CSV, Excel, Parquet and SQLite files by running guarded read-only DuckDB SQL over a sandboxed data directory. It also supports data profiling, chart generation as image content, and exporting query results, without ever allowing writes or access outside the configured folder.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to query SQLite databases and Excel/CSV files read-only, with PII masking, bounded row limits, query timeouts, and audit logging.1MIT
- AlicenseAqualityCmaintenanceTurns a folder of CSV, Parquet, and JSON files into a single SQL-queryable source for AI agents, supporting JOINs across files with read-only sandboxed access.619 PyPI2MIT
- AlicenseAqualityCmaintenanceEnables read-only analytical access to local CSV, Parquet, JSON files or a DuckDB database through MCP, with table discovery, column profiling, guarded SQL querying, and explain plans for safe use with Claude Desktop and Claude Code.81MIT
TDQS
Scored across 6 tools
Each tool has a distinct role: list_files (discovery), describe_file (schema), profile_file (column statistics), sample_file (row preview), query (SQL), explain_query (plan). The main overlap is that describe_file also returns sample rows and profile_file touches type metadata, but descriptions draw clear boundaries (cheaper sampling, stats vs. schema).
Five of six names follow a clean verb_noun pattern (list_files, describe_file, profile_file, sample_file, explain_query). The bare 'query' is the sole deviation but is unambiguous in context.
Six tools is well-scoped for a read-only DuckDB query server, each mapping to a distinct step in the analysis workflow. Nothing feels padded or missing.
The read-only analytical lifecycle is fully covered: discover files, inspect schema, sample rows, profile columns, run SQL, and explain plans. No write operations exist, consistent with the explicit read-only design, so there are no dead ends.