# codeDB Lens (oci · ghcr.io/codedb-io/codedb-lens)

Read-only health checks and data questions for SQL Server and PostgreSQL, with your saved profiles.

- Trust score: 45/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- oci · `ghcr.io/codedb-io/codedb-lens`: 45/100 (this document), [markdown](https://verifymcp.io/servers/codedb-io-codedb-lens/ghcr-io-codedb-io-codedb-lens.md), [page](https://verifymcp.io/servers/codedb-io-codedb-lens/ghcr-io-codedb-io-codedb-lens)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/codedb-io/codedb-lens`
- Version: `0.9.1`
- 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 2026-11-06.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 35/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 7 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1452 tokens (~103/item across 14 items; 14 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the codeDB Lens MCP server?

codeDB Lens runs locally as a container image, launched with docker run --rm -i -e CODEDB_LENS_PASSWORD ghcr.io/codedb-io/codedb-lens:0.9.1 mcp, plus the required --engine and --server, which you supply. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add codedb-io-codedb-lens -- docker run --rm -i -e CODEDB_LENS_PASSWORD ghcr.io/codedb-io/codedb-lens:0.9.1 mcp
```

This image reads CODEDB_LENS_PASSWORD. Set it in your client's env block for this server; docker run -e passes it through to the container. Incomplete: the registry marks --engine and --server as required and gives no value we can show, so they are not in this command. Add them before you run it.

### Cursor

```json
{
  "mcpServers": {
    "codedb-io-codedb-lens": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "CODEDB_LENS_PASSWORD",
        "ghcr.io/codedb-io/codedb-lens:0.9.1",
        "mcp"
      ]
    }
  }
}
```

This image reads CODEDB_LENS_PASSWORD. Set it in your client's env block for this server; docker run -e passes it through to the container. Incomplete: the registry marks --engine and --server as required and gives no value we can show, so they are not in this command. Add them before you run it.

### VS Code

```json
{
  "servers": {
    "codedb-io-codedb-lens": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "CODEDB_LENS_PASSWORD",
        "ghcr.io/codedb-io/codedb-lens:0.9.1",
        "mcp"
      ]
    }
  }
}
```

This image reads CODEDB_LENS_PASSWORD. Set it in your client's env block for this server; docker run -e passes it through to the container. Incomplete: the registry marks --engine and --server as required and gives no value we can show, so they are not in this command. Add them before you run it.

### Codex

```bash
codex mcp add codedb-io-codedb-lens -- docker run --rm -i -e CODEDB_LENS_PASSWORD ghcr.io/codedb-io/codedb-lens:0.9.1 mcp
```

This image reads CODEDB_LENS_PASSWORD. Set it in your client's env block for this server; docker run -e passes it through to the container. Incomplete: the registry marks --engine and --server as required and gives no value we can show, so they are not in this command. Add them before you run it.

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "codedb-io-codedb-lens": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "-e",
        "CODEDB_LENS_PASSWORD",
        "ghcr.io/codedb-io/codedb-lens:0.9.1",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

This image reads CODEDB_LENS_PASSWORD. Set it in your client's env block for this server; docker run -e passes it through to the container. Incomplete: the registry marks --engine and --server as required and gives no value we can show, so they are not in this command. Add them before you run it.

### Hermes

```yaml
mcp_servers:
  codedb-io-codedb-lens:
    command: "docker"
    args: ["run", "--rm", "-i", "-e", "CODEDB_LENS_PASSWORD", "ghcr.io/codedb-io/codedb-lens:0.9.1", "mcp"]
```

This image reads CODEDB_LENS_PASSWORD. Set it in your client's env block for this server; docker run -e passes it through to the container. Incomplete: the registry marks --engine and --server as required and gives no value we can show, so they are not in this command. Add them before you run it.

### Netclaw

```json
{
  "McpServers": {
    "codedb-io-codedb-lens": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "-e",
        "CODEDB_LENS_PASSWORD",
        "ghcr.io/codedb-io/codedb-lens:0.9.1",
        "mcp"
      ]
    }
  }
}
```

This image reads CODEDB_LENS_PASSWORD. Set it in your client's env block for this server; docker run -e passes it through to the container. Incomplete: the registry marks --engine and --server as required and gives no value we can show, so they are not in this command. Add them before you run it.

### Other

```json
{
  "mcpServers": {
    "codedb-io-codedb-lens": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "CODEDB_LENS_PASSWORD",
        "ghcr.io/codedb-io/codedb-lens:0.9.1",
        "mcp"
      ]
    }
  }
}
```

This image reads CODEDB_LENS_PASSWORD. Set it in your client's env block for this server; docker run -e passes it through to the container. Incomplete: the registry marks --engine and --server as required and gives no value we can show, so they are not in this command. Add them before you run it.

## 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.

### 2026-11-06 (score 45, +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.

### 2026-11-04 (score 44, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 43, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 42, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 41, 0)

- [security regression] Stability: 0.03 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional] Package version: 0.9.0 → 0.9.1

### 2026-10-28 (score 41, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 40)

First indexed and scored.

## MCP tools (14)

### `check` (~99 tokens)

Run the codeDB Lens health check on a profile (read-only, 10-60 s): A-F grade with its coverage, findings with severity, confidence, evidence preview and next action, and rules without data. Saves the report in the profile's history, like the app does.

Input parameters:

- `profile` (string, required): profile name from list_profiles
- `redact` (boolean): mask host, database, object, login and file names and drop query text

Output parameters:

- `coverage` (number)
- `findings` (null|array)
- `grade` (string)
- `no_data` (null|array)
- `note` (string)
- `passed` (integer)
- `report` (string)
- `score` (number)
- `server` (object)

### `compare` (~93 tokens)

Compare two runs of the same instance: new, resolved and persisting findings and the grade change. Default: the two latest runs. Needs the user's free key (codedb-lens register).

Input parameters:

- `a` (string): older run path from history; default: the second latest
- `b` (string): newer run path from history; default: the latest
- `profile` (string, required): profile name from list_profiles

Output parameters:

- `after` (object)
- `before` (object)
- `changed` (null|array)
- `new` (null|array)
- `persisting` (null|array)
- `report` (string)
- `resolved` (null|array)
- `warnings` (null|array)

### `describe_table` (~100 tokens)

Columns (type, nullable, default), primary key, foreign keys with the referenced table, indexes and estimated rows of one table or view. Use it before writing a query, so column names are right.

Input parameters:

- `database` (string): database name from list_databases; default: the profile's
- `profile` (string, required): profile name from list_profiles
- `table` (string, required): table or view: schema.name, or name in the default schema

Output parameters:

- `columns` (null|array)
- `estimated_rows` (null|integer)
- `foreign_keys` (null|array)
- `indexes` (null|array)
- `name` (string)
- `primary_key` (null|array)
- `schema` (string)
- `type` (string)

### `explain_rule` (~71 tokens)

Explain one rule: what it measures, why it matters, the next action, how to verify the fix, the permission it needs, its SQL and its documentation link.

Input parameters:

- `rule_id` (string, required): rule ID, e.g. MSSQL-BACKUP-001 or PG-AUTOVAC-001

Output parameters:

- `category` (string)
- `caveat` (string)
- `doc_url` (string)
- `engine` (string)
- `id` (string)
- `impact` (string)
- `kind` (string)
- `next_action` (string)
- `permission` (string)
- `severity` (string)
- `sql` (string)
- `title` (string)
- `verify` (string)

### `get_finding` (~95 tokens)

Full detail of one rule in a saved run: status, impact, next action, how to verify the fix, and all evidence rows. Default run: the latest.

Input parameters:

- `profile` (string, required): profile name from list_profiles
- `rule_id` (string, required): rule ID from check, e.g. MSSQL-BACKUP-001
- `run` (string): run path from history; default: the latest run

Output parameters:

- `caveat` (string)
- `columns` (null|array)
- `confidence` (string)
- `doc_url` (string)
- `id` (string)
- `impact` (string)
- `next_action` (string)
- `reason` (string)
- `rows` (null|array)
- `run` (string)
- `run_at` (string)
- `severity` (string)
- `status` (string)
- `title` (string)
- `total_rows` (integer)
- `truncated` (boolean)
- `verify` (string)

### `history` (~75 tokens)

Saved check runs of a profile, newest first: date, grade, coverage and number of findings. Each run's path can be passed to get_finding or compare.

Input parameters:

- `limit` (integer): how many runs, newest first (default 10, at most 50)
- `profile` (string, required): profile name from list_profiles

Output parameters:

- `runs` (null|array)

### `list_databases` (~46 tokens)

Databases this profile's login can open: name, state, recovery model or encoding, collation and size in bytes.

Input parameters:

- `profile` (string, required): profile name from list_profiles

Output parameters:

- `columns` (null|array)
- `note` (string)
- `rows` (null|array)
- `truncated` (boolean)

### `list_profiles` (~35 tokens)

List the saved connection profiles you may use: name, engine, host, initial database and language. Never returns passwords or connection strings.

Output parameters:

- `note` (string)
- `profiles` (null|array)

### `list_recordings` (~71 tokens)

Recordings (activity sampled every 15 s for 1 or 24 h) kept with a profile's reports, newest first. Recordings made elsewhere can still be read with recording_report and their folder.

Input parameters:

- `profile` (string): profile name; empty lists the recordings of every profile you may use

Output parameters:

- `recordings` (null|array)

### `list_rules` (~57 tokens)

List the Lens rule catalog (health checks): ID, engine, category, severity and title. Kind "series" rules judge recordings, the others run in a check.

Input parameters:

- `engine` (string): mssql or pg; empty lists both

Output parameters:

- `rules` (null|array)

### `list_tables` (~113 tokens)

Tables and views visible to the profile's login in a database: schema, name, type, estimated rows, size and whether the login can read them. Start here, then describe_table, then query.

Input parameters:

- `database` (string): database name from list_databases; default: the profile's
- `filter` (string): name pattern: plain text matches anywhere in the name, or a LIKE pattern with %
- `profile` (string, required): profile name from list_profiles
- `schema` (string): only this schema

Output parameters:

- `columns` (null|array)
- `note` (string)
- `rows` (null|array)
- `truncated` (boolean)

### `query` (~192 tokens)

Run one read-only SELECT (or WITH ... SELECT) on a profile and get columns and rows. Aggregate in SQL (GROUP BY, TOP/LIMIT) instead of fetching raw rows: results stop at the profile's row limit (500 unless the user changed it), cells at 2 KB, and truncated: true means the answer is partial. Writes, EXEC, multiple statements and functions with side effects are refused; quote a column named like an SQL keyword. SQL Server reads uncommitted data, like the health check.

Input parameters:

- `database` (string): database name from list_databases; default: the profile's
- `max_rows` (integer): row limit; default and ceiling: the profile's
- `profile` (string, required): profile name from list_profiles
- `sql` (string, required): one SELECT or WITH ... SELECT statement
- `timeout_s` (integer): seconds; default and ceiling: the profile's

Output parameters:

- `columns` (null|array)
- `elapsed_ms` (integer)
- `note` (string)
- `rows` (null|array)
- `truncated` (boolean)
- `warning` (string)

### `record_command` (~107 tokens)

The command the user runs in a terminal (or on the server) to record a profile for up to 1 h, or 24 h with the free key. You cannot start a recording: give the user this command.

Input parameters:

- `duration` (string): how long to record, e.g. 30m, 1h or 24h (default 1h; more than 1h needs the free key)
- `profile` (string, required): profile name from list_profiles

Output parameters:

- `command` (string)
- `note` (string)
- `report_command` (string)
- `server_command` (string)

### `recording_report` (~129 tokens)

Analyse a recording, optionally for a period (e.g. an incident): time coverage, gaps without data, findings as episodes (blocking, waits, long queries, workers or connections), peak of each chart and the top queries. Also writes the HTML report into the recording folder.

Input parameters:

- `folder` (string, required): recording folder, from list_recordings or given by the user
- `from` (string): start of the period, RFC 3339 (default: start of the recording)
- `to` (string): end of the period, RFC 3339 (default: end of the recording)

Output parameters:

- `charts` (null|array)
- `coverage` (number)
- `findings` (null|array)
- `from` (string)
- `gaps` (null|array)
- `report` (string)
- `server` (object)
- `started` (string)
- `stop_reason` (string)
- `stopped` (string)
- `to` (string)
- `top_queries` (object)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/codedb-io-codedb-lens/ghcr-io-codedb-io-codedb-lens#diagnostics

## Score history

- 2026-11-06: 45
- 2026-11-05: 44
- 2026-11-04: 44
- 2026-11-03: 43
- 2026-11-02: 43
- 2026-11-01: 43
- 2026-10-31: 42
- 2026-10-30: 42
- 2026-10-29: 41
- 2026-10-28: 41
- 2026-10-27: 40

## Common questions

### What is the codeDB Lens MCP server?

codeDB Lens is an MCP server listed in the public MCP registry as io.github.codedb-io/codedb-lens. Read-only health checks and data questions for SQL Server and PostgreSQL, with your saved profiles. This page covers its container image (ghcr.io/codedb-io/codedb-lens).

### Is the codeDB Lens MCP server safe to use?

codeDB Lens scores 45 out of 100 on VerifyMCP. 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 codeDB Lens MCP server expose?

codeDB Lens exposes 14 tools: check, compare, describe_table, explain_rule, get_finding, and 9 more. Their descriptions and schemas cost roughly 1,283 tokens of context every time the server is loaded.

### Is the codeDB Lens MCP server still maintained?

codeDB Lens is still listed as active in the MCP registry. We last reached this channel on 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the codeDB Lens MCP server?

VerifyMCP ran 12 checks on codeDB Lens, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about codeDB Lens: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- GitHub Container Registry: https://ghcr.io/codedb-io/codedb-lens
- Repository: https://github.com/codedb-io/codedb-lens
- Website: https://lens.codedb.com.br/mcp/
- Changelog RSS feed: https://verifymcp.io/servers/codedb-io-codedb-lens/ghcr-io-codedb-io-codedb-lens.xml
- Changelog JSON feed: https://verifymcp.io/servers/codedb-io-codedb-lens/ghcr-io-codedb-io-codedb-lens/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/codedb-io-codedb-lens/ghcr-io-codedb-io-codedb-lens.json
- HTML version of this page: https://verifymcp.io/servers/codedb-io-codedb-lens/ghcr-io-codedb-io-codedb-lens