"Red" matching MCP servers:

Provides access to Atomic Red Team tests, enabling search, validation, and execution of atomic tests via natural language.

Enables structured robustness and security testing by scanning text for policy/safety issues and generating test suite outlines.

Enables querying Red Hat security data including CSAF advisories, CVEs, and OVAL streams through natural language.

MCP server for Speakeasy — Windows API emulation for binary analysis. It runs a .exe in a Wine-like sandbox and returns a structured API trace.

Privacy layer for healthcare AI agents. Pseudonymises patient identifiers (NHS numbers, names, dates of birth, addresses; UK and US) into labelled tokens locally before text reaches an agent, then restores the originals afterwards, keeping the token map out of agent context.

Enables AI agents to permanently remove personally identifiable information from PDF documents, returning redacted files with the sensitive text deleted rather than merely covered. Supports scanned documents, multiple languages, entity types, and optional human review.

MCP server for detecting publisher telemetry pipeline leaks in binary artifacts by scanning for sensitive strings like Sentry DSNs, Slack tokens, and AWS keys.

Enables secure, governed interaction with DMTF Redfish-compliant BMCs (iDRAC, iLO, etc.) via MCP, with read-only default and write operations gated behind explicit write-mode elevation and dry-run confirmations.

An MCP server that redacts PII/PHI from text before it ever reaches an LLM — self-hosted, fail-closed, and HIPAA-aware.

Sanitizes text and files by removing PII, secrets, and custom patterns locally before sending to LLMs, with optional reverse-scrubbing.

A secure email gateway MCP server that protects AI agents from prompt injection attacks by scanning emails for malicious instructions before they reach the agent.

MCP server for angr — symbolic execution + CFG + reaching-definitions.

Provides a local-first MCP server for multi-format document redaction, enabling detection of sensitive content, physical removal from PDFs, DOCX, XLSX, PPTX, and text files, and forensic audit with zero network calls.

Enables safe, read-only interaction with Redis databases via cursor-based tools for retrieving keys, hashes, lists, sets, and sorted sets, backed by ACL DRYRUN-verified privilege checks.

Detects and redacts sensitive personal information such as names, emails, phone numbers, ID numbers, and locations in text before it is processed by AI agents, using configurable mask, hash, or remove strategies.

MCP server for FreeIPA / Red Hat IdM — user, group, host, DNS, HBAC, and sudo management via the Model Context Protocol.

Provides AI governance controls as MCP tools for safety screening, risk classification, and red teaming of AI systems, returning structured governance reports.

Converts natural language security requirements into validated Cerbos YAML policies with automated testing and red-team analysis, enabling AI governance with zero-trust guardrails for tool calls, data access, and compliance frameworks.

Provides redacted access to a private local knowledgebase for coding agents, allowing them to inspect files while hiding sensitive names and identifiers.

Enables red-team and blue-team security workflows on BlackArch Linux by wrapping local tools like nmap, gobuster, nikto, and hydra as MCP tools, with scope-gating that prevents unauthorized scanning against any target not explicitly listed in a local scope.yaml file.