$ loading_
Connect to multiple databases to explore schemas and run SQL queries.
This tool claims to provide database exploration and SQL execution for PostgreSQL, ClickHouse, and MySQL, which makes it a typical MCP tool that runs local service/code and accesses database data; overall it merits caution. No separate cloud API key or explicit third-party egress endpoint is stated, but supply-chain trust is limited due to low community adoption, no declared license, and unknown maintenance status.
The material states there are no extra keys/environment variables, but connecting to PostgreSQL, ClickHouse, and MySQL typically still requires database credentials in practice. If supplied via config or connection strings, those secrets are sensitive and may be exposed through misconfiguration or logging.
No fixed remote endpoint is declared, and there is no stated transfer to unrelated third parties. However, its database exploration and SQL execution functionality inherently means it will communicate with target database hosts and may transmit query contents and results.
The system flags executes-code, and the description says it operates as an MCP server over stdio or HTTP API, which implies running a local service process and handling external requests. This is standard for such tools, and no extra high-risk system privilege request is stated in the material.
Its core capability is database exploration and SQL execution, so it can access schema and data in connected databases, with the actual scope determined by the database account privileges. If used with a highly privileged account, it could read, modify, or delete data. The material does not show unrelated excessive access such as filesystem access.
A public open-source repository is available for inspection, which lowers risk. However, the source is a third-party registry, the GitHub repo has 0 stars, no declared license, and unknown maintenance status, so community and governance signals are weak; code and dependencies should be reviewed before use.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Multi-DB MCP Server" yet — see the docs or source repo.
Connect to the PostgreSQL database, list all schemas, table names, and key columns for each table, then present them in a hierarchical structure.
A clear database structure overview including schemas, tables, and columns.
Run the following SQL in ClickHouse and summarize the key findings: daily order volume and revenue trends for the last 30 days.
A result table plus a brief analysis of trends and anomalies.
Connect to MySQL and PostgreSQL, check whether record counts for the same user_id match in the user tables, and list sample differences.
A data consistency report with mismatch counts and sample discrepancies.
Connect to multiple databases to query, inspect schemas, and access remotely via SSH.
Query and manage multiple databases with read-only access and schema inspection.
Connect to PostgreSQL via MCP for queries, schema inspection, and database changes.
Connect LLM apps to query and manage multiple databases through one tool.
Query PostgreSQL, inspect tables, and explore schemas through MCP clients.
Connect AI assistants to PostgreSQL for secure querying, management, and analysis.