# Rowbase (pypi · rowbase-db)

Safe, read-only-by-default MySQL, PostgreSQL & SQLite access for AI agents. TOON output.

- Trust score: 85/100 (high trust)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- pypi · `rowbase-db`: 85/100 (this document), [markdown](https://verifymcp.io/servers/djstreet11-rowbase/rowbase-db.md), [page](https://verifymcp.io/servers/djstreet11-rowbase/rowbase-db)

## Channel facts

- Registry: `pypi`
- Package: `rowbase-db`
- Version: `0.3.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 5 of 21 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to djstreet11/Rowbase).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 9 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 72/100
  - 75% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2431 tokens (~187/item across 13 items; 11 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Rowbase MCP server?

Rowbase runs locally as a PyPI package, launched with uvx rowbase-db. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add djstreet11-rowbase -- uvx rowbase-db
```

### Cursor

```json
{
  "mcpServers": {
    "djstreet11-rowbase": {
      "command": "uvx",
      "args": [
        "rowbase-db"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "djstreet11-rowbase": {
      "command": "uvx",
      "args": [
        "rowbase-db"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add djstreet11-rowbase -- uvx rowbase-db
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "djstreet11-rowbase": {
      "type": "local",
      "command": [
        "uvx",
        "rowbase-db"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add djstreet11-rowbase --command uvx --arg rowbase-db
```

### Hermes

```yaml
mcp_servers:
  djstreet11-rowbase:
    command: "uvx"
    args: ["rowbase-db"]
```

### Netclaw

```json
{
  "McpServers": {
    "djstreet11-rowbase": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "rowbase-db"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add djstreet11-rowbase -t stdio -c uvx -a rowbase-db
```

### Other

```json
{
  "mcpServers": {
    "djstreet11-rowbase": {
      "command": "uvx",
      "args": [
        "rowbase-db"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-17 (score 85, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-16 (score 69, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-15 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 83, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-12 (score 67, −12)

- [security regression] Malware scan: pass → unverified
- [functional regression] Schema quality: 2082 → 2431
- [functional improvement] Stability: unverified → 0.23
- [functional] Package version: 0.2.2 → 0.3.0

### 2026-10-05 (score 79, +29)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 75
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 100

### 2026-10-04 (score 50)

First indexed and scored.

## MCP tools (11)

### `guide` (~63 tokens)

Guide

Read this first, once per session: the Rowbase knowledge base — recommended workflow, safety rules (read-only model, one statement per call), the TOON output format and SQL dialect notes. Use it before any other tool; it needs no connection. Returns a markdown document.

### `connections` (~88 tokens)

List connections

List the user's saved database connections exposed to MCP. Call this first to get the exact connection names every other tool requires. Returns a table connections[N]{name,driver,env,mode,database,tunnel} — mode is the EFFECTIVE read-only/read-write mode for MCP; env 'prod' means be extra careful — plus writes_enabled_in_mcp. No pagination: all exposed connections are returned.

### `databases` (~142 tokens)

List databases

List the databases on a connection's server and which one is current. Use it when a connection has no database selected, or to work in another database (pass `database` to later calls); to list tables inside a database use `tables` instead. Returns current, databases[N] (user databases first) and system[N]. SQLite returns an empty list (one file = one database). On failure returns isError with 'error: <reason>' (e.g. refused statement, unknown table, SQL error).

Input parameters:

- `connection` (string, required): Connection name exactly as returned by `connections` (e.g. "shop"). Unknown or unexposed names return an error.

### `tables` (~213 tokens)

List tables

List all tables and views of a connection/database with approximate row counts — the entry point for browsing. Use `search_schema` instead when you look for a concept (e.g. 'invoice') across table AND column names, and `describe` once you know the table. Returns tables[N]{name,kind,approx_rows} (kind = table|view; approx_rows is an estimate, may be null; use `count` for exact numbers). Returns every match, no pagination. On failure returns isError with 'error: <reason>' (e.g. refused statement, unknown table, SQL error).

Input parameters:

- `connection` (string, required): Connection name exactly as returned by `connections` (e.g. "shop"). Unknown or unexposed names return an error.
- `database` (string): Optional database to use instead of the connection's default (names from `databases`). Omit to use the default.
- `filter` (string): Optional case-insensitive substring of the table name, e.g. order.

### `describe` (~240 tokens)

Describe table

Show the structure of one known table: columns with type, nullability, key, default, foreign-key target (fk = table.column — use it to write JOINs) and comment, plus indexes and the tables that reference it. Use it before writing SQL against a table; use `search_schema` if you don't know the table name yet. Returns table, sql_name (properly quoted name for SQL), columns[N]{name,type,nullable,key,default,fk,comment}, indexes[N]{name,unique,columns} and referenced_by[N]{table,column,ref_column}. On failure returns isError with 'error: <reason>' (e.g. refused statement, unknown table, SQL error).

Input parameters:

- `connection` (string, required): Connection name exactly as returned by `connections` (e.g. "shop"). Unknown or unexposed names return an error.
- `database` (string): Optional database to use instead of the connection's default (names from `databases`). Omit to use the default.
- `table` (string, required): Table or view name as returned by `tables`. PostgreSQL tables outside `public` are written schema.table.

### `search_schema` (~207 tokens)

Search schema

Find tables and columns whose name contains a keyword (case-insensitive substring; on MySQL also column comments). Use it when you know WHAT you are looking for but not WHERE it is stored; use `tables` instead to browse everything and `describe` for one known table. Returns matches[N]{table,column,type}, one row per matching column (a table-name match lists all its columns), capped at 500 rows (truncated: true when cut). On failure returns isError with 'error: <reason>' (e.g. refused statement, unknown table, SQL error).

Input parameters:

- `connection` (string, required): Connection name exactly as returned by `connections` (e.g. "shop"). Unknown or unexposed names return an error.
- `database` (string): Optional database to use instead of the connection's default (names from `databases`). Omit to use the default.
- `text` (string, required): Keyword to look for, e.g. invoice, email, price.

### `sample` (~298 tokens)

Sample rows

Peek at a few real rows of one table (SELECT * … LIMIT n, in storage order, no sorting) to see what the data looks like before writing a query. Use `query` instead for specific columns, joins, sorting or aggregates, and `count` when you only need a number. Returns rows[N]{all columns} plus rows, truncated (true = more rows exist) and ms. Default 20 rows, capped by the server's max rows setting. On failure returns isError with 'error: <reason>' (e.g. refused statement, unknown table, SQL error).

Input parameters:

- `connection` (string, required): Connection name exactly as returned by `connections` (e.g. "shop"). Unknown or unexposed names return an error.
- `database` (string): Optional database to use instead of the connection's default (names from `databases`). Omit to use the default.
- `format` (string): Result format. Default from settings: toon (compact table: rows[N]{cols}: then one line per row).
- `limit` (integer): Rows to return (default 20; capped by settings, usually 200).
- `table` (string, required): Table or view name as returned by `tables`. PostgreSQL tables outside `public` are written schema.table.
- `where` (string): Optional SQL boolean expression WITHOUT the WHERE keyword, e.g. status = 'paid' AND total > 100.

### `count` (~222 tokens)

Count rows

Return the exact number of rows in a table, optionally filtered — use it to size a result before fetching it or to answer 'how many' questions. Use `query` instead for grouped counts (GROUP BY) or counts over joins. Returns a single line: count: N. May be slow on very large unindexed filters (timeout from settings). On failure returns isError with 'error: <reason>' (e.g. refused statement, unknown table, SQL error).

Input parameters:

- `connection` (string, required): Connection name exactly as returned by `connections` (e.g. "shop"). Unknown or unexposed names return an error.
- `database` (string): Optional database to use instead of the connection's default (names from `databases`). Omit to use the default.
- `table` (string, required): Table or view name as returned by `tables`. PostgreSQL tables outside `public` are written schema.table.
- `where` (string): Optional SQL boolean expression WITHOUT the WHERE keyword, e.g. status = 'paid' AND total > 100.

### `query` (~303 tokens)

Run SQL

Run exactly ONE SQL statement — the general tool for answering questions: specific columns, JOINs (follow fk from `describe`), filters, sorting, GROUP BY. Read-only connections accept only SELECT/SHOW/DESCRIBE/EXPLAIN/WITH/VALUES/TABLE (+PRAGMA on SQLite); multiple statements are refused. Prefer `sample`/`count` for simple peeks and totals, `explain` for performance. A LIMIT is added automatically when missing. Returns rows[N]{columns} plus rows, truncated (true = more rows exist — narrow with WHERE or raise limit) and ms; write statements (only if writes are enabled) return affected instead. On failure returns isError with 'error: <reason>' (e.g. refused statement, unknown table, SQL error).

Input parameters:

- `connection` (string, required): Connection name exactly as returned by `connections` (e.g. "shop"). Unknown or unexposed names return an error.
- `database` (string): Optional database to use instead of the connection's default (names from `databases`). Omit to use the default.
- `format` (string): Result format. Default from settings: toon (compact table: rows[N]{cols}: then one line per row).
- `limit` (integer): Max rows (default 100; capped by settings, usually 200).
- `sql` (string, required): A single SQL statement in the connection's dialect, without a trailing ';' chain.

### `explain` (~249 tokens)

Explain query plan

Show how the database will execute a SELECT (its query plan) to diagnose slow queries or check index use — use it instead of `query` when the question is about performance, not data. With analyze=true the statement is actually executed to report real timings (can be slow on big tables). Returns the plan as rows plus a hint: MySQL type=ALL or PostgreSQL 'Seq Scan' means a full table scan (consider an index or a narrower WHERE). SQLite uses EXPLAIN QUERY PLAN. On failure returns isError with 'error: <reason>' (e.g. refused statement, unknown table, SQL error).

Input parameters:

- `analyze` (boolean): true = execute the statement to measure real timings and row counts (EXPLAIN ANALYZE); default false = estimate only, nothing is executed.
- `connection` (string, required): Connection name exactly as returned by `connections` (e.g. "shop"). Unknown or unexposed names return an error.
- `database` (string): Optional database to use instead of the connection's default (names from `databases`). Omit to use the default.
- `sql` (string, required): The SELECT statement to analyze (without EXPLAIN).

### `find_ref` (~349 tokens)

Find referenced object

Find which table holds a UUID value as its primary key — for schemas that store references as UUIDs without foreign keys (1C-style `Ref` keys, columns like SenderAddress or Owner_Ref). Use it when `describe` shows no fk for a column whose values are UUIDs; use `describe` fk + `query` instead when real foreign keys exist. Searches tables whose single-column primary key can hold a UUID: the hint table first, then tables named like the column (SenderAddress → …Addresses), then all of them. Returns matches[N]{table,pk,label} (label = Description/Name/Number/Code of the row) and found_by, or searched_tables when nothing matched. On failure returns isError with 'error: <reason>' (e.g. refused statement, unknown table, SQL error).

Input parameters:

- `column` (string): Optional: column the value was read from, e.g. SenderAddress.
- `connection` (string, required): Connection name exactly as returned by `connections` (e.g. "shop"). Unknown or unexposed names return an error.
- `database` (string): Optional database to use instead of the connection's default (names from `databases`). Omit to use the default.
- `hint` (string): Optional: value of a sibling type column such as Owner_TRef = 'Catalog.Counterparties'.
- `table` (string): Optional: table the value was read from (improves the guess and is remembered).
- `value` (string, required): The UUID to look up, e.g. 7e6056b9-9582-11f1-a74c-005056bd6036.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/djstreet11-rowbase/rowbase-db#diagnostics

## Score history

- 2026-10-17: 85
- 2026-10-16: 69
- 2026-10-15: 84
- 2026-10-14: 83
- 2026-10-13: 83
- 2026-10-12: 67
- 2026-10-05: 79
- 2026-10-04: 50

## Common questions

### What is the Rowbase MCP server?

Rowbase is an MCP server listed in the public MCP registry as io.github.djstreet11/rowbase. Safe, read-only-by-default MySQL, PostgreSQL & SQLite access for AI agents. TOON output. This page covers its PyPI package (rowbase-db).

### Is the Rowbase MCP server safe to use?

Rowbase scores 85 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Rowbase MCP server expose?

Rowbase exposes 11 tools: guide, connections, databases, tables, describe, and 6 more. Their descriptions and schemas cost roughly 2,374 tokens of context every time the server is loaded.

### Is the Rowbase MCP server still maintained?

Rowbase is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Rowbase MCP server under?

Rowbase declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/rowbase-db/
- Socket report: https://socket.dev/pypi/package/rowbase-db
- Repository: https://github.com/djstreet11/Rowbase
- Changelog RSS feed: https://verifymcp.io/servers/djstreet11-rowbase/rowbase-db.xml
- Changelog JSON feed: https://verifymcp.io/servers/djstreet11-rowbase/rowbase-db.json
- HTML version of this page: https://verifymcp.io/servers/djstreet11-rowbase/rowbase-db