Toolbox for Databases
Toolbox is an MCP server implementation that enables AI assistants to interact with various database systems including PostgreSQL, MySQL, SQL Server, Neo4j, Dgraph, and Spanner. Developed by Google's SenseAI team, it provides a configurable interface for executing pre-defined queries against databases through a YAML-based configuration system. The implementation features telemetry integration, authentication services, and support for both HTTP and SSE transport protocols. Toolbox is particularly useful for AI applications that need to retrieve or manipulate data from multiple database types without exposing direct database access, making it ideal for creating secure, controlled database interfaces for generative AI applications.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/googleapis/mcp-toolbox
- Author type
- human
- Updated
- 2026-05-27
Use via MCP
Resolve Toolbox for Databases from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.