{"slug": "show-hn-dbprint-database-context-for-agents", "title": "Show HN: Dbprint – Database Context for Agents", "summary": "Developer Jakub (GitHub handle jakubro) released Dbprint, a command-line tool that produces an offline YAML and Markdown snapshot of a database — DDL, column- and relation-level statistics, and values with frequencies — and exposes it to AI agents via MCP and a web UI. Dbprint supports PostgreSQL, MySQL, Snowflake, ClickHouse, Databricks and BigQuery, and adds annotations, sensitivity-based redaction, and a \"dbprint check\" command for CI schema and data drift detection. The developer said agent-generated SQL queries were inaccurate and slow to produce because answers had to be found in the codebase or a live database.", "body_md": "CLI that produces an offline snapshot of a database (DDL, column- and relation-level statistics, values with frequencies), combines it with annotations written by you or an agent, and exposes it as MCP and as a web UI. Works with PG, MySQL, Snowflake, ClickHouse, Databricks, BigQuery.\n\nHow to try it:\n\n```\n  uvx dbprint context \\\n    arboretum.seedbank.germination_trial \\\n    --purpose query \\\n    --project https://github.com/jakubro/dbprint/blob/main/docs/format/v1/examples/production/.dbprint.yaml\n```\n\nFeatures:\n- Philosophy: snapshots are meant to sit next to your code and versioned so that you have a history of changes and agents can hit them when searching codebase.\n\n- Offline: no need to expose live credentials to agents.\n\n- CI: \"dbprint check\" can verify schema/data drift.\n\n- Annotations: complement statistics by documenting the meaning behind data. An agent can prepare them for you (\"dbprint annotate\").\n\n- Redaction: values can be masked/excluded/hashed either explicitly with FQNs or automatically based on inferred sensitivity and value shape.\n\n- Format: Snapshots are YAML and markdown, so greppable and usable by other tools.\n\nWhy I built this: SQL queries produced by agents were inaccurate, and the overall time to result was slow and costly because of finding the answers in codebase or in live database.\n\nComments URL: [https://news.ycombinator.com/item?id=50305171](https://news.ycombinator.com/item?id=50305171)\n\nPoints: 1\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-dbprint-database-context-for-agents", "canonical_source": "https://github.com/jakubro/dbprint", "published_at": "2026-10-30 15:20:12+00:00", "updated_at": "2026-10-30 15:47:12.556333+00:00", "lang": "en", "topics": ["ai-agents", "agent-protocols", "ai-tools", "developer-tools", "ai-infrastructure"], "entities": ["Dbprint", "Jakub", "PostgreSQL", "MySQL", "Snowflake", "ClickHouse", "Databricks", "BigQuery"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-dbprint-database-context-for-agents", "markdown": "https://wpnews.pro/news/show-hn-dbprint-database-context-for-agents.md", "text": "https://wpnews.pro/news/show-hn-dbprint-database-context-for-agents.txt", "jsonld": "https://wpnews.pro/news/show-hn-dbprint-database-context-for-agents.jsonld"}}