$ loading_
Safely explore and analyze data across multiple databases with read-only access.
This MCP tool appears relatively low risk overall: it is open-source, MIT-licensed, and declares no extra secrets or remote endpoints. However, it does execute local code and access database data, and its low community adoption and unknown maintenance status warrant some caution.
The materials explicitly state that no keys or environment variables are required, and there is no indication of API tokens or third-party credentials. However, real database connectivity may still rely on connection strings or host-side DB credentials, which cannot be fully verified due to missing documentation.
Although no fixed remote endpoint is declared, its stated function is to connect to PostgreSQL, MySQL, and ClickHouse databases for read-only analysis, which implies network connections to user-configured database hosts and transfer of query/result data. This is within its normal function, and there is no evidence of exfiltration to unrelated third parties.
The system checks indicate that this tool executes code/local processes. For an MCP tool this is a normal capability, but it still means the server implementation runs on the host machine. The materials do not show requests for high-risk system privileges unrelated to database access.
The tool is described as providing read-only exploratory analysis over databases, so its primary access scope should be read-only data within configured databases. There is no indication of local sensitive file access or write operations, but the lack of a README means the read-only constraint cannot be independently verified at the implementation level.
There is a public GitHub repository and the project is MIT-licensed, making the source in principle auditable—this is a meaningful risk-reducing factor. However, it comes from a third-party registry, has 0 stars, and has unknown maintenance status, so trust and evidence of ongoing upkeep are limited; review the code and dependencies before using it in sensitive environments.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "db-connect-mcp" yet — see the docs or source repo.
Connect to PostgreSQL, MySQL, and ClickHouse, list sales-related databases, tables, and columns, and summarize their differences.
A schema inventory of relevant tables across databases plus a summary of field and naming differences.
Run a read-only exploratory analysis on the orders table: count records, summarize time distribution, major status ratios, and detect obvious outliers or missing values.
A summary with key statistics, distribution overview, anomaly flags, and suggested next analysis steps.
Query the last 30 days of order counts and revenue from PostgreSQL and ClickHouse, aggregate by week, and compare whether the results match.
A weekly metric comparison between the two databases, highlighting periods with possible discrepancies.
Connect to PostgreSQL and MySQL, run SQL, and manage database transactions.
Query and manage multiple databases with read-only access and schema inspection.
Connect to major databases via MCP to run SQL queries and commands.
Query databases in natural language and auto-generate and execute SQL.
Safely query and inspect PostgreSQL databases without enabling risky write operations by default.
Run read-only MySQL queries and list datasources through MCP.