Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

SQLX

OCI · GHCR.IO/OTTERMIND/SQLX

Run SQL on 30+ databases through saved, encrypted connections; credentials stay local.

+3 this week 48 Trust /100

Last scanned (51 minutes ago)

Scores higher than 71% of OCI servers

Category Databases

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security0
  • 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.Unverified
  • Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency32
Schema Quality & AI Usability76
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 973 tokens (~108/item across 9 items; 9 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management73
  • Stability observed for 22 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 94% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

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.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

  • 2 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

  • 31 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

  • 28 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 26 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 24 Oct 26 +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.

  • 22 Oct 26 +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.

  • 20 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Analysed oci/ghcr.io/ottermind/sqlx@0.1.21

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem oci
Reason No attestation published

Background: How many MCP packages publish verified provenance →

MCP tools · 9 exposed · ~843 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
sqlx_datasource_list ~31

List the saved SQLX datasources with their non-secret connection settings. Never returns usernames or passwords.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

sqlx_datasource_setup ~130

Start adding a datasource the user finishes in a local browser page, and return that page's `url`. The connection object carries no credentials: the user types the username and password there, so they never enter this conversation. Give the user the complete URL, then call sqlx_datasource_setup_status with the returned `request_id` until it reports the outcome.

NameTypeReqDescription
connectionobjectyesConnection settings without credentials, in the shape --connection-stdin accepts: database_type, host, port, database, service, tls, properties
namestringyesName for the new datasource

No output schema declared.

No examples provided.

sqlx_datasource_setup_status ~59

Report the outcome of a setup started by sqlx_datasource_setup, without retrieving credentials. Read-only: it never contacts the database again.

NameTypeReqDescription
request_idstringyesSetup request UUID from the sqlx_datasource_setup response

No output schema declared.

No examples provided.

sqlx_datasource_show ~36

Show one saved datasource by its stable ID or unique name.

NameTypeReqDescription
idstringyesDatasource UUID or unique name

No output schema declared.

No examples provided.

sqlx_datasource_test ~39

Open one connection and report whether the datasource is reachable. Executes no SQL.

NameTypeReqDescription
idstringyesDatasource UUID or unique name

No output schema declared.

No examples provided.

sqlx_prefetch ~149

Download the components that would otherwise be fetched during a first query or page: mysql, mariadb, tidb, greatsql, oceanbase, starrocks, doris, postgres, cockroachdb, yugabytedb, opengauss, oracle, sqlserver, clickhouse, trino, tdengine, dameng, kingbase, redis, mongodb, sqlite, duckdb, h2, presto, hive, kylin, xugu, db2, informix, sundb, gbase8s, ui, skill, all. A first download can take minutes, so wait for the call instead of treating it as hung.

NameTypeReqDescription
componentsarrayyes–

No output schema declared.

No examples provided.

sqlx_results_rows ~142

Read one page of a result that sqlx_sql_execute stored because it did not fit the printed preview. Pass the result `id` from that response; `statement` and `set` select the result set, which defaults to the first one. Read-only: it never contacts the database again.

NameTypeReqDescription
idstringyesResult UUID from the execute response
limitinteger–Rows to return, 50 by default
offsetinteger–First row to return
setinteger–Result set index of that statement, counted from zero
statementinteger–Statement index inside the result, counted from zero

No output schema declared.

No examples provided.

sqlx_sql_execute ~174

Execute one or more complete SQL statements through SQLX and return the table-shaped result: `results[].cols`, `rows` and `count` per statement. A result set larger than the preview is stored under `results[].file` and read with sqlx_results_rows. Each statement is a separate driver statement and the batch stops at the first error. Statements may modify data: only call this after the user authorized that exact operation and scope. Results are never replayed automatically.

NameTypeReqDescription
datasourcestringyesDatasource UUID or unique name
fullboolean–Print every row instead of a preview and store nothing. Use it only when the caller cannot read the stored file, because a large result then fills the response.
statementsarrayyesComplete SQL statements, executed in order on one connection

No output schema declared.

No examples provided.

sqlx_sql_view ~83

Execute the statements once in the local SQLX service and return a local result-page URL for the user. The same authorization rule as sqlx_sql_execute applies, and the page's Refresh action reruns the batch.

NameTypeReqDescription
datasourcestringyesDatasource UUID or unique name
statementsarrayyesComplete SQL statements, executed in order on one connection

No output schema declared.

No examples provided.

Install

How do I install the SQLX MCP server?

SQLX runs locally as a container image, launched with docker run --rm -i ghcr.io/ottermind/sqlx:0.1.21. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

oci · ghcr.io/ottermind/sqlx

# add to Claude Code
claude mcp add ottermind-sqlx -- docker run --rm -i ghcr.io/ottermind/sqlx:0.1.21
Common questions

What is the SQLX MCP server?

SQLX is an MCP server listed in the public MCP registry as io.github.OtterMind/sqlx. Run SQL on 30+ databases through saved, encrypted connections; credentials stay local. This page covers its container image (ghcr.io/ottermind/sqlx).

Is the SQLX MCP server safe to use?

SQLX scores 48 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 SQLX MCP server expose?

SQLX exposes 9 tools: sqlx_datasource_list, sqlx_datasource_show, sqlx_datasource_test, sqlx_datasource_setup, sqlx_datasource_setup_status, and 4 more. Their descriptions and schemas cost roughly 843 tokens of context every time the server is loaded.

Is the SQLX MCP server still maintained?

SQLX is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.