safeselect

 SafeSelect MCP

Agents can look.They cannot mutate.

Read-only PostgreSQL & MongoDB access for coding agents.

Debug with real database context, without exposing write tools—even when your

existing credentials allow writes. SafeSelect puts local, project-scoped policy

between your agent and your data.

**Get started →** ·

Website ·

Compare approaches ·

DBeaver → Codex guide

Runtime and distribution

Discover structure, inspect bounded rows, explain queries, and diagnose

connectivity—without giving the agent write-capable tools or database credentials.

Start with development data or a sanitized replica, then review the policy and

effective database permissions before connecting to a more sensitive environment.

> [!NOTE]

> SafeSelect is a safety boundary for agent access, not a replacement for database permissions. Use least-privilege database users when you can; SafeSelect still constrains overpowered credentials when agents connect through it.

Current backend support: PostgreSQL and MongoDB.

Where It Helps

• Debug an application against realistic data without exposing mutation tools.
• Let an agent inspect schemas, indexes, query plans, and bounded rows during development.
• Explore MongoDB collections through bounded reads and sampled schema inference.
• Reuse existing DBeaver, Docker Compose, or MongoDB Compass connections.
• Give coding agents database context while keeping policy, limits, secrets, and audit under your control.

Why SafeSelect?

SafeSelect is intentionally narrower than general-purpose database MCP servers. It is not a tool builder, SQL workbench, or remote database gateway. It is a local safety boundary for agents that need database visibility, not database power.

What Makes It Different?

The combination matters: PostgreSQL and MongoDB inspection, a fixed database

read surface, local stdio, project policy, connection import and reproducible

security evidence. Read-only modes and layered controls also exist in other

projects; they are not exclusive to SafeSelect.

See the dated comparison for DBHub, MongoDB MCP Server,

Postgres MCP Pro and SchemaBrain—including when each is a better fit.

Agents can look, but they cannot mutate through SafeSelect's database tools.

This boundary does not cover a shell, another MCP server or direct credentials

also available to the agent. Use least-privilege database users and review the

threat model and limits.

Backend Support

Architecture

The agent talks to SafeSelect through MCP stdio. SafeSelect enforces policy in Rust, stores secrets outside project files, and reaches databases through an embedded Java sidecar: JDBC for SQL backends and the MongoDB driver for MongoDB. The Rust to Java channel is JSON-lines over stdin/stdout: no sockets, no open ports.

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

Install SafeSelect with one of the following methods:

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 | sh

Set `PREFIX` to choose another installation directory. SafeSelect still needs

a Java 17+ runtime at execution time.

Homebrew (macOS)

brew install antonillos/tap/safeselect

asdf (macOS & Linux)

asdf plugin add safeselect https://github.com/antonillos/asdf-safeselect.git
asdf install safeselect latest
SAFESELECT_VERSION="$(asdf latest safeselect | sed -n '$p')"
asdf set -u safeselect "${SAFESELECT_VERSION}"
asdf reshim safeselect "${SAFESELECT_VERSION}"

After installing the binary, configure a project database and its MCP entry:

# Import a project database
safeselect import-dbeaver ~/Downloads/dbeaver-export.zip
# or:
# safeselect import-compose
# safeselect import-compass --path "$HOME/.config/MongoDB Compass"

# Verify the environment
safeselect check --environment testing

# Install the MCP entry. If this is the only environment, its name is inferred.
safeselect agent install opencode

# Verify exactly what was installed and where.
safeselect agent status

SafeSelect uses any available Java 17+ runtime rather than requiring a specific

package-manager formula. If Java is missing or too old, install or select a

Java 17+ runtime before running database commands. On macOS with Homebrew, you

can install one with `brew install openjdk@17`.

The generated MCP name defaults to `safeselect--`.

The generated MCP entry is a stdio server scoped to one project and environment:

{
  "mcpServers": {
    "safeselect-myapp-testing": {
      "command": "safeselect",
      "args": ["serve", "--project", "/path/to/myapp", "--environment", "testing"]
    }
  }
}

SafeSelect uses each client's official MCP configuration contract, pins the

absolute repository path, and defaults to user scope. Add `--local` for a

project-scoped entry where the client supports it. See

AI agent integration for exact paths, scopes, and manual

configuration.

Guided MCP Context

Clients that support MCP prompts can invoke `read_only_database_debugging` for a

safe investigation checklist. Clients can also read

`safeselect://guide/read-only-database-debugging` for the same static workflow

and boundary notes. Neither capability exposes database data, credentials, or

write access; use the database tools below for discovery and bounded reads.

Agent Workflow

Agents should use SafeSelect in this order:

1. `database_info`

2. `list_tables` then `describe_table`; inspect `list_table_indexes` or bounded statistics when useful for SQL

3. `list_databases`, `list_collections`, then `discover_document_schema` for NoSQL

4. `select` / `explain`, or the bounded MongoDB read tool that matches the task

5. `check`, `connect`, or `reconnect` when connectivity is stale

Agents must discover relation or collection structure before querying unfamiliar data and use each discovery response's `next_suggestion` instead of guessing column or field names. SQL descriptions are catalog metadata; MongoDB schemas are inferred from a bounded, non-exhaustive sample.

MongoDB query documents must remain complete nested JSON values. Clients that

flatten nested tool arguments can pass `filter`, `projection`, and `sort` as

JSON-encoded object strings and `pipeline` as a JSON-encoded array string.

`redact_fields` also accepts a JSON-encoded string array. Flattened keys are

rejected so a lost filter or redaction can never become a less constrained

fallback.

MongoDB server-side JavaScript is never available: `$where`, `$function`, and

`$accumulator` are rejected recursively in filters, projections, sorts, and

aggregation pipelines before the MongoDB driver receives them. When rejected,

rebuild the request with declarative MQL operators; SafeSelect has no setting

that enables JavaScript.

Query responses include `row_count`, `byte_count`, `elapsed_ms`, and a human-readable `elapsed` value so agents can reason about result size and latency.

Every MCP success and error includes one contextual `next_suggestion`. Agents

should follow that single safe action, never blindly repeat an invalid request,

and stop when the suggestion is terminal. For clients that only show an MCP

error summary, SafeSelect also includes the trusted next suggestion in that

summary without exposing database-derived detail.

Security Model

• Fail closed: security violations terminate the MCP process.
• Read only: SQL allows `SELECT`, `EXPLAIN`, and `WITH`; NoSQL backends allow discovery and read-only document reads.
• No server-side JavaScript: MongoDB `$where`, `$function`, and `$accumulator` are rejected in Rust and again in the Java sidecar.
• Scoped access: schemas, relations, databases, and collections can be allowed or denied.
• Hard limits: row count, result bytes, and timeouts are enforced; MongoDB read commands receive the same timeout as `maxTimeMS`.
• Secret isolation: passwords live in macOS Keychain or environment variables, never in project config.
• Driver verification: JDBC drivers are checked by SHA-256 before use.
• Audit trail: query text is hashed before being recorded; the current session exposes bounded audit metadata through `audit_status` and `audit_recent`.

Deliberate Limits

• SafeSelect does not expose database writes, migrations, administration, or arbitrary command execution.
• PostgreSQL and MongoDB are the supported backends today; broad connector count is not the goal.
• MCP transport is local stdio. SafeSelect is not a remote database gateway.
• MongoDB schema discovery is sampled and bounded, not an exhaustive schema guarantee.
• SafeSelect complements database-native least privilege; it does not replace it.

MCP Tools

When no `.safeselect/` directory exists, `safeselect serve --environment ` enters setup mode automatically and exposes only the setup-safe tools.

> [!IMPORTANT]

> Setup mode does not expose query tools. Agents can help import and validate configuration before any database inspection tools become available.

CLI Essentials

Use `safeselect --help` or a command-specific `--help` for the full CLI.

Uninstall checks both release-installer and Cargo binary locations.

MongoDB Compass imports support SSH-tunneled `mongodb+srv://` connections by resolving

the SRV target and rewriting the local endpoint with the required TLS and direct-connection

options.

Configuration

Global state lives in `~/.config/safeselect/` by default. Project policy lives in `.safeselect/` at the repository root:

/
└── .safeselect/
    ├── project.toml
    └── environments/
        └── .toml

SafeSelect walks upward from the current directory to find `.safeselect/`. Use `--project ` when an agent or script should target a specific repository.

Supported Agents

SafeSelect never silently falls back to a broader scope. In particular,

`--local` for Windsurf fails with a clear correction because Windsurf does not

document a project-scoped MCP configuration.

Build From Source

# Installs makevn through Homebrew or asdf only when it is missing.
./install.sh --install-makevn
"$HOME/.local/bin/safeselect" --version

Requirements: Rust 1.85+ and Java 17+. The bootstrap requires Homebrew or

asdf; otherwise install `makevn` first. `sshpass` is optional for

password-based SSH tunnels. Add `~/.local/bin` to your `PATH` before invoking

`safeselect` without its full path.

Documentation

• Installation guide
• AI agent integration
• On-demand Codex code review
• Security model
• Security Proof
• Security test suite
• Security policy
• Distribution
• Changelog

Release notes are generated from `CHANGELOG.md`.

License

MIT - see LICENSE.