"Resources for Penetration Testing and Security Analysis" matching MCP servers:

Enables MySQL database analysis through natural language, including schema exploration, query execution, performance analysis, and ER diagram generation via the Model Context Protocol.

Security Graph MCP Server

MCP server that lets AI coding agents (Claude Code, Cursor, Cline) audit Supabase projects for security misconfigurations AND apply the fixes — without leaving the agent. Tools: audit_project, list_findings, preview_fix (BEGIN/ROLLBACK safety), apply_fix (with confirmation), apply_all_fixes (transactional bulk). Closes the audit-fix loop entirely in the agent — other Supabase scanners only report.

A read-only MCP server for exploring and analyzing a Secoda data catalog, enabling AI chat, semantic search, glossary browsing, and data lineage tracing.

Enables AI assistants to interact with Databricks workspaces, running SQL queries, managing jobs, and exploring schemas via the Model Context Protocol.

Connects Claude Desktop to a healthcare claims database for natural-language analysis of CPT codes, reimbursement rates, payer performance, and denial patterns.

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

A server that enables executing and validating SQL queries against Google BigQuery with safety features that prevent data modifications and excessive processing.

An MCP server designed for SQL analysis that demonstrates sampling capabilities by interacting with SQL files in a local directory. It provides a framework for testing client-side sampling while managing SQL-based contexts.

Enables forensic analysis of Windows notification databases (wpndatabase.db) from E01 forensic images, automatically extracting and parsing notification data with search, filtering, timeline analysis, and sensitive information detection capabilities.

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.

This read-only MCP Server allows you to connect to Azure Analysis Services data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Search the fastest-growing US horse boarding directory: 6,000 facilities and 3,800 trainers across 48 states, plus boarding price data by state.

Enables LLM clients such as Cursor and Claude to discover and use generated REST services through MCP tools for create, update, and delete actions and MCP resources for list and get-by-id context. Services generated in one command are exposed simultaneously as REST endpoints and MCP tools and resources.

Enables AI assistants to interact with generated REST APIs by discovering and using CRUD tools and read-only data resources.

Enables AI assistants to discover and invoke CRUD tools and read-only resources over the Model Context Protocol for generated API services.

Enables AI assistants to interact directly with generated REST APIs by exposing CRUD operations as MCP tools and read-only data as resources.

Exposes generated CRUD services to LLM clients over the Model Context Protocol, providing tools for create, update, and delete actions plus read-only resources for listing and fetching records by id. It lets assistants like Claude, ChatGPT, and Cursor discover and manipulate the same data served by the project's REST endpoints without any extra glue code.

Exposes every generated CRUD service to LLM clients such as Claude, ChatGPT, or Cursor through discoverable MCP tools for create, update, and list actions plus read-only resources, so models can query and manipulate data without raw HTTP calls. It runs alongside the same codebase's REST endpoints, letting clients and AI share one data layer.

Enables LLMs to discover and invoke generated CRUD operations as MCP tools and read data through MCP resources, alongside standard REST endpoints, using one codebase.