SafeSelect MCP Server

by antonillos Your server? Claim it

local only

SafeSelect MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 15 Oct 2026.

Fail-closed, read-only PostgreSQL and MongoDB access for AI agents over MCP.

—

Installs / week

not published

Stars

0 open issues

15 Oct 2026

Last commit

from GitHub

MIT

License

Rust

What the code does

We read the source, 22 h ago · rules ccca72095570

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

Claims read-only, but the code runs commands tools/ci/release.py:22, tools/distribution/update_lobehub_manifest.py:54, tools/ci/prepare_promotion.py:9

    return subprocess.check_output(args, text=True, **kwargs).strip()

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command tools/ci/release.py:22, tools/distribution/update_lobehub_manifest.py:54, tools/ci/prepare_promotion.py:9

    return subprocess.check_output(args, text=True, **kwargs).strip()

Builds a database query by concatenation packaging/install/install-release.sh:98, .github/workflows/prepare-release.yml:121, .github/workflows/publish-package-managers.yml:66

    cp safeselect "${installed_binary}"
    chmod +x "${installed_binary}"

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch SafeSelect MCP and you get told the day something new turns up.

Alternatives to SafeSelect MCP

same job, measured the same way

Data

by thinair

PostgreSQL, MySQL, and SQL Server in one session. 26 read-only MCP tools for AI agents.

answering

QueryBear

by spencerpauly

Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.

answering

Universal DB (read-only)

by alghanim

Read-only, guarded SQL access for AI agents: PostgreSQL, MySQL, ClickHouse, Oracle, SQL Server, Db2

local only

Quarry

by wangggym

Safety-railed database access for agents: Postgres, MySQL, Redis. Read-only by default.

local only

Rowbase

by djstreet11

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

324 installs/wk local only

JDBC MCP Server

by igorolv

Read-only SQL, plans, schema for AI agents: PostgreSQL, Oracle, SQL Server, Firebird, SQLite, JDBC

local only

MCP DB Connect

by phatngoit

MCP server for Oracle, MSSQL, PostgreSQL, MySQL, SQLite, MongoDB, and Qdrant vector search access.

55 installs/wk local only

MCP Postgres Nl Query

by infoinlet-marketplace

RLS/tenant-aware Postgres for AI agents — schema, read-only SQL, NL→SQL with safety rails.

33 installs/wk local only

SafeSelect MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for SafeSelect MCP?

SafeSelect MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone.

Is SafeSelect MCP open source?

Yes — it is published under the MIT licence, written in Rust and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.