dolthub/dolt
Dolt is a SQL database with Git-like version control capabilities, enabling users to manage, version, and collaborate on data and schemas as easily as code in Git repositories.
ergut/mcp-bigquery-server
BigQuery MCP Server gives an MCP client read-only access to a Google BigQuery warehouse, so questions asked in natural language are answered from the data without the user writing SQL by hand. The read-only guarantee is enforced rather than advisory: only SELECT statements are accepted and every query is validated by the BigQuery dry-run planner before it executes, which rejects INSERT, UPDATE, DELETE, DROP, TRUNCATE, MERGE and EXPORT DATA. Beyond running queries, the server lets an assistant explore dataset schemas and reach both tables and materialized views, labelling each resource so the two are distinguishable. Cost is bounded by a configurable limit on bytes billed, set in config.json or with the --maximum-bytes-billed flag. The second focus is keeping sensitive columns out of the model conversation. The README argues that BigQuery IAM controls who can reach the data while field restrictions control what an agent surfaces into an LLM response, and that these are different boundaries because query results leave the network when they are sent to a model provider. A preventedFields list blocks named columns per table, and when a query touches one the agent is told how to reformulate it using aggregates or an EXCEPT clause so it stays useful without exposing individual records. An optional scanner walks every dataset looking for columns matching sensitive patterns such as names, emails, national identifiers, medical records and API keys, and adds what it finds to the restricted list, so newly added tables are covered on the next run; the patterns are configurable to match local naming conventions. The README documents a simple mode run straight from npx for non-sensitive projects and a protected mode driven by config.json for PHI, PII and regulated environments. Authentication uses either gcloud application default credentials or a service account key file, and Node.js 14 or newer is required.
https://github.com/ergut/mcp-bigquery-server
Also in Databases
t8y2/dbx
DBX is a lightweight, cross-platform database client supporting over 70 databases, featuring a built-in AI assistant, MCP Server, and available as desktop, Docker, or CLI.
Canner/WrenAI
Open-source generative BI engine that exposes governed text-to-SQL, a semantic layer and dashboard generation to AI agents through an MCP server and CLI across more than twenty data sources.
googleapis/mcp-toolbox
MCP Toolbox for Databases is an open-source Model Context Protocol (MCP) server that connects AI agents, IDEs, and applications directly to enterprise databases, offering both pre-built and custom ...
makenotion/notion-mcp-server
The Notion MCP Server is an official MCP server implementation that enables secure, programmatic interaction with Notion content through MCP commands, optimized for AI agents and supporting multiple deployment options.
bytebase/dbhub
DBHub is a universal database gateway implementing the Model Context Protocol (MCP) server interface, enabling MCP clients to connect to and explore multiple database systems including MySQL, PostgreSQL, Oracle, SQL Server, MariaDB, and SQLite.
crystaldba/postgres-mcp
Postgres MCP Pro is an open-source Model Context Protocol server for PostgreSQL that provides advanced database health monitoring, index tuning, query plan analysis, and safe SQL execution to support AI agents and developers throughout the application lifecycle.
supabase-community/supabase-mcp
Supabase MCP Server connects Supabase projects to AI assistants using the Model Context Protocol, enabling LLMs to manage and query Supabase resources.