"An overview of penetration testing (pentest)" matching MCP servers:

A read-only MCP server for bounded table discovery, deterministic profiling, and maintained-library statistical testing (Welch's t-test and two-proportion z-test) using SQLite, pandas, SciPy, and statsmodels.

Enables interaction with Databricks workspaces using On-Behalf-Of authentication to test connectivity, retrieve user information, and perform operations on behalf of authenticated users.

MCP server for sandboxed, read-only SQL queries on CSV/Parquet/JSON files via DuckDB, limited to a specified directory.

Enables managing employee records by providing tools to list directories, retrieve detailed profiles, and search for staff by department. It integrates with Claude Desktop to allow users to interact with employee data through natural language commands.

Enables integration with financial transaction data through REST APIs, PostgreSQL databases, and document storage systems. Demonstrates agentic AI capabilities by connecting to Alpha Vantage API and managing financial data through natural language interactions.

Enables AI agents to run deterministic database intelligence tasks including natural-language-to-SQL synthesis, AST SQL auditing and optimization, schema migration diffing, SQL transpilation, index and normalization advice, PII scrubbing, fixture generation, connection-pool sizing, isolation-hazard auditing, and ORM model compilation over Streamable HTTP or stdio.

Enables AI agents to safely query and explore Apache Impala clusters with read-only SQL, metadata, statistics, cluster overview, and analysis prompt templates.

This local MCP server is deprecated and no longer receives updates. Use the Fibery remote MCP server instead https://developers.fibery.com/guides/mcp/overview

Enables read-only access to GA4 accounts and properties via tools that list properties, fetch settings and metadata, and run standard, realtime, and one-call overview reports. It is stateless and takes a Google access token on every request, letting one deployment serve many accounts behind an auth proxy.

Enables AI agents to share a local SQLite memory for authorized pentest intelligence, letting them record, retrieve, and work with vulnerabilities, assets, snapshots, and related findings through stdio MCP tools.

Provides secure access to VA's VistA electronic health record system, enabling AI applications to retrieve and summarize patient medical records for clinical staff.

Enables LLM agents to answer questions about Austrian passenger car registrations from an SQLite database, with tools for market overview, brand trends, brand rankings, and top models.

Enables natural-language sales queries against a SQLite database, generating and executing read-only SQL through a secure MCP server with table listing, schema description, and query execution.

An employee-analytics MCP server backed by SQLite that provides hand-written SQL queries for common analytics tasks like salary ranking and department statistics. It self-seeds sample data, enabling immediate testing of GROUP BY, window functions, NULL handling, and subqueries.

An MCP server that provides targeted PostgreSQL schema access to AI agents, retrieving only relevant tables for a question and enforcing read-only access through multiple layers.

An MCP server that provides a USDA-accurate food database with deterministic macro math, enabling tools like list_foods, get_food, calculate_macros, filter_by_diet, build_meal, and list_available_tags. It allows Claude to look up nutrition facts and solve for exact macro targets offline, without AI or network.

SchemaBrain is an MCP server that sits between AI agents (Claude, Cursor, Windsurf) and your SQL database as a read-only trust + intelligence layer. The agent never writes SQL — 12 tools compile it from definitions you control, PII and secret categories are refused before the query runs, and every call lands in a tamper-evident (SHA-256-chained) audit log. Postgres today.

Give your AI agent the entire China A-share market: 55 datasets of prices, financials, capital flows, corporate events and futures/options, stored locally and queryable with read-only SQL. Built point-in-time with delisted stocks kept, so backtests don't lie — no account, no API key.

Enables natural language querying of SQL databases by allowing the agent to explore schema, write SQL, and self-correct errors. It integrates with MCP-compatible assistants like Claude Desktop or Cursor.

An MCP server that gives models semantic context about a data warehouse, including table meaning, units, lineage, and health, to reduce guessing.