Enables AI agents and LLM clients to inspect sandboxed files, run read-only SQL queries, and fetch public web content through guarded MCP tools with deterministic path, SQL, SSRF, timeout, and PII protections.
Provides secure read-only SQL access to PostgreSQL and ClickHouse databases with built-in safety features like read-only enforcement, timeouts, and managed result files.
Enables secure, read-only PostgreSQL queries, sandboxed file reads within a confined directory tree, and host CPU, memory, and disk metrics over stdio. It exposes these capabilities through narrowly scoped tools with strict validation and fail-closed guardrails.
Enables read-only access to explicitly approved local and remote filesystems, including inspecting Git repositories and querying SQLite and DuckDB databases, with root administration kept separate from MCP.