SafeSelect MCP server
io.github.antonillos/safeselect·v0.8.0Fail-closed, read-only PostgreSQL and MongoDB access for AI agents over MCP.
not scanned yet
0 stars
Reviews
Write oneNobody has reviewed SafeSelect MCP yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
SafeSelect MCP tools
No tool declarations could be read from the package source. They show once the server is installed.
How SafeSelect MCP compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 88/100
- higher than 75% of 48,243 servers
Release history: 3 versions in the registry since 2026-09-12, latest 2026-10-18, typically one every 26 days.
Install SafeSelect MCP in Claude Code, Cursor or VS Code
The registry entry has no remote endpoint or installable package.
What the publisher says
From the SafeSelect MCP repository's README, as published. We do not edit it. Read it on GitHub
SafeSelect
Agents can look. They cannot mutate.
Read-only PostgreSQL & MongoDB access for coding agents.
Debug with real database context, without exposing write tools. Local, project-scoped policy—even when your existing credentials allow writes.
Get started → · Demo · Agents · Security · Docs · Website
What you can do
- Inspect PostgreSQL — discover tables, indexes and query plans; read bounded rows.
- Explore MongoDB — discover collections, infer sampled schemas and run bounded reads.
- Reuse your connections — import from DBeaver, Docker Compose or MongoDB Compass.
- Connect your coding agent — install a project/environment-pinned MCP entry.
- Keep control — local stdio, project policy, external secrets and audit metadata.
Roadmap
[!NOTE]
Coming soon: Snowflake support.
We’re planning a dedicated, read-only Snowflake backend with the same
fail-closed approach used for supported databases. Initial scope will focus on
bounded SQL reads and schema discovery; Snowflake is not supported yet.
[!IMPORTANT]
Read-only applies to SafeSelect's database tools, not to an agent's shell,
other MCP servers or direct credentials. Start with development data or a
sanitized replica and use least-privilege database users. Review the
threat model and limits before connecting sensitive data.
See it in action
Complete onboarding: from Homebrew to a protected agent
Install SafeSelect from Homebrew, import an SSH-backed DBeaver connection, keep the password in macOS Keychain, install the OpenCode integration, and see the agent read a paid order while its DELETE attempt is rejected. Focused agent and backend clips remain in the complete demo gallery.
Quick Start
Run setup from your repository root. You will need a PostgreSQL or MongoDB connection and a Java 17+ runtime for database commands.
1. Install
On macOS with Homebrew:
brew install antonillos/tap/safeselectOther installation methods: prebuilt binaries and asdf
Prebuilt binaries (macOS & glibc Linux)
Download a platform-specific, prebuilt binary for macOS or glibc-based Linux from the latest GitHub release. The verified installer selects the matching macOS or glibc Linux architecture, checks the published SHA-256 digest, and installs to ~/.local/bin:
curl -fsSL https://raw.githubusercontent.com/antonillos/safeselect/main/packaging/install/install-release.sh | shShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
SafeSelect MCP: common questions
- Is SafeSelect MCP server safe?
- Yes, by our scan: it is graded A (88/100). Read the SafeSelect MCP safety report
- Does SafeSelect MCP need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is SafeSelect MCP maintained?
- The last commit was 33 days ago (2026-10-03). The latest release is v0.8.0.