"Information on 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.

This read-only MCP Server allows you to connect to Act-On data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at https://www.cdata.com/solutions/mcp

Retrieves comprehensive patient information including personal details, insurance plans, and employee data through the get_patient tool. Supports Docker Compose deployment and integration with Watson Orchestrate for healthcare data access.

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

Deploys 25 MCP tools for Apache Doris, enabling SQL execution, metadata queries, monitoring, and data governance over HTTPS via AWS Bedrock AgentCore Runtime.

Enables MCP sessions to survive ECS Fargate deployments by using Redis-backed tool state and stateless Streamable HTTP transport.

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.

A testing server that provides CRUD operations on a JSON user database via MCP tools, enabling AI assistants to list, search, add, update, and delete users.

Enables LLMs to retrieve Tokyo Stock Exchange stock information and execute SQL queries on Databricks SQL warehouses, deployed as a Databricks App.

Provides AI agents read-only access to the Autotask Report Data Warehouse for cross-client reporting on finance, contracts, projects, time, and tickets through schema exploration and SQL queries.

Enables AI agents to query Trino and Apache Pinot lakehouses under enforced governance, where every SQL statement is AST-validated, table-allowlisted, priced from the engine's own plan before it runs, and blocked or admitted against scan-byte and intermediate-row budgets. It also grounds agents with schema discovery tools, returns verified results with warnings instead of misleading answers, and records every tool call on an audit trail.

Check 22,000+ devices with open firmware or open protocols (OpenWrt, LineageOS, coreboot, Zigbee2MQTT, Tasmota…) before reverse engineering one; claim a device while you work on it and publish your findings when done.

Guardrail proxy for AI agents on SQL Server. Each statement runs as the caller's own login, a T-SQL parser blocks dangerous statements, and every statement is audited. Local stdio mode or a central Docker service.

Enables AI assistants to execute arbitrary SQL queries on a local SQLite database via a single execute_sql tool.

Enables AI to execute SQL queries (SELECT, DML, DDL) on MySQL/MariaDB databases with strong security: connection credentials never exposed to AI, write queries require user approval, read-only connections enforced, and query results limited to 50 rows.

Enables querying and acting on any Acumatica ERP tenant's contract-based REST API through 8 generic tools, covering all entities with read-only by default safety.

Enables AI agents to inspect tables, estimate bytes/cost, rehearse SQL on 1%→3%→10% samples, predict full-scale results, and only run a query inside a budget across DuckDB, BigQuery, Snowflake and Postgres. Also supports impact/lineage analysis, schema drift detection, key-based data diffs, SQL translation, incremental-model advice and cheap data-quality checks.

Enables querying and updating Markdown frontmatter metadata using DuckDB SQL, with optional semantic search capabilities for finding similar documents based on content.

A read-only MCP server that lets AI search and read both sides of a user's own LINE Desktop chat history on macOS using local database snapshots, without needing a LINE Official Account or altering unread state.

Build on the Flarelink stack — Cloudflare auth (better-auth + KV sessions), D1, and R2 — from AI coding tools. Provides copy-paste code patterns and scaffolding that need no account, plus project-management tools (list/query your projects, D1 databases, and R2 buckets) gated by a Flarelink API key.

Enables AI assistants to query and manage a local Engine DJ library on macOS, including searching tracks by BPM, key, genre, or comments, auditing duplicates and missing files, reading cues and beatgrids, and building playlists or fixing tags when write access is enabled.

Provides a blueprint for building and deploying Python MCP servers on Oracle Cloud Infrastructure, with sample tools for database schema and data retrieval.

Enables Claude to query your local TimeScribe time tracking database read-only, listing projects and returning work, break and scheduled hours per project or day, plus individual entries and the live running timer, without exporting CSVs. All data stays on your machine with no network access.

Enables AI assistants to query and read data on DICOM servers (PACS, VNA, etc.).

Enables MCP clients to search and describe API routes, retrieve people, admissions, academics, and billing records, download exports, and optionally make changes against a school information system, read-only by default.

MCP server for creating day-by-day trip itineraries in SQLite, with a planner agent that uses a Tavily search scout via tool boundaries. Enforces guard rails like rejecting activities on out-of-range days.

Read-only BIM query server for agents: structured, policy-bounded queries on IFC/gbXML models with deterministic cited results.

MCP server enabling text-to-SQL on PostgreSQL databases using a CrewAI multi-agent system. It generates and executes read-only SQL queries from natural language, with security layers against prompt injection.

Enables natural language to SQL queries on MSSQL databases via Claude, with safe SELECT-only execution and schema discovery.

Gives AI clients guarded access to SAP Business One over SAP HANA / MS SQL and the Service Layer OData API. SQL is read-only, enforced on the server; Service Layer is GET-only by default, with opt-in writes that require user approval unless a profile explicitly turns it off.