# bricksentry

> bricksentry is an open-source MCP server for databases. Pre-merge safety verdicts for Databricks table changes made by pipelines and agents. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** CLI, self-hosted
- **Website:** https://bricksentry.org
- **Repository:** https://github.com/bricksentry/bricksentry
- **MCP Registry name:** io.github.bricksentry/bricksentry
- **Categories:** databases, analytics and data
- **Listing updated:** 2026-11-14

## About

The check runs four steps in order: diff the data, map the blast radius, apply policy, and prepare a rollback. The diff matches production and the change on key columns and counts added, removed and changed rows, schema changes, column totals and duplicate keys, and finds where the change concentrates. Blast radius walks Unity Catalog lineage for jobs, dashboards and queries, with owners and tags.

Verdicts come from rules in `policy.yml`, with no LLM in the decision, so the same change gets the same answer. The output includes a next step such as "Do not merge", and the Delta history yields the exact RESTORE command. Everything runs as SQL on your warehouse and no data leaves the workspace.

It is open source under Apache-2.0, installable from PyPI, usable in CI with `--fail-on needs_human`, and a local DuckDB demo runs without a Databricks account.

## Features

- **Data diff:** Counts added, removed and changed rows, duplicate keys and total shifts.
- **Blast radius:** Uses Unity Catalog lineage to list downstream tables, jobs and dashboards.
- **Policy verdicts:** Deterministic rules decide safe, warn, needs_human or block.
- **Rollback ready:** Reads Delta history to produce the restore command.
- **CI and agent use:** Fails a CI check or tells an agent not to merge.

## Good for

- Review an agent's DELETE before it reaches production
- Catch a MERGE that duplicates keys
- Notify owners of a certified downstream table
- Fail a pull request on risky data changes

## Install

### Claude Code (Terminal)

```sh
claude mcp add bricksentry --env DATABRICKS_TOKEN='<DATABRICKS_TOKEN>' -- uvx bricksentry-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "bricksentry": {
      "command": "uvx",
      "args": [
        "bricksentry-mcp"
      ],
      "env": {
        "DATABRICKS_TOKEN": "<DATABRICKS_TOKEN>"
      }
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "bricksentry": {
      "command": "uvx",
      "args": [
        "bricksentry-mcp"
      ],
      "env": {
        "DATABRICKS_TOKEN": "<DATABRICKS_TOKEN>"
      }
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "bricksentry": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "bricksentry-mcp"
      ],
      "env": {
        "DATABRICKS_TOKEN": "<DATABRICKS_TOKEN>"
      }
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "bricksentry": {
      "command": "uvx",
      "args": [
        "bricksentry-mcp"
      ],
      "env": {
        "DATABRICKS_TOKEN": "<DATABRICKS_TOKEN>"
      }
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "bricksentry": {
      "command": "uvx",
      "args": [
        "bricksentry-mcp"
      ],
      "env": {
        "DATABRICKS_TOKEN": "<DATABRICKS_TOKEN>"
      }
    }
  }
}
```

## FAQ

### Is an LLM involved in the verdict?

No. Policy rules decide, so the same change always gets the same answer.

### Where does it run?

As SQL on your Databricks SQL warehouse; data stays in your workspace.

### Is it open source?

Yes, under Apache-2.0.

### Can I try it without Databricks?

Yes, a local DuckDB demo runs on a 20,000-row sample.

### Is bricksentry free?

Yes. bricksentry is open source, so you can use and self-host it for free.

### How do I add bricksentry to Claude Code?

Run this command in your terminal: claude mcp add bricksentry --env DATABRICKS_TOKEN='<DATABRICKS_TOKEN>' -- uvx bricksentry-mcp

### What are the best alternatives to bricksentry?

The closest alternatives to bricksentry are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Tapetide - Indian Stock Market MCP, Midplane and World Monitor.

## Alternatives

- [Agent-Native Analytics](https://ai-powered.com/mcp/agent-native-analytics): Agent-Native Analytics is an open-source MCP server for analytics and data.
- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [Tapetide - Indian Stock Market MCP](https://ai-powered.com/mcp/tapetide-indian-stock-market-mcp): Tapetide - Indian Stock Market MCP is a freemium MCP server for finance and payments.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.
- [World Monitor](https://ai-powered.com/mcp/world-monitor): World Monitor is a freemium MCP server for analytics and data.
- [CompanyData](https://ai-powered.com/mcp/companydata): CompanyData is a paid MCP server for analytics and data.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.
- [Quantivex Research](https://ai-powered.com/mcp/quantivex-research): Quantivex Research is a free MCP server for finance and payments.

---
Source: https://ai-powered.com/mcp/bricksentry
