"Red" matching MCP servers:

Enables automated adversarial safety probing and jailbreak fuzzing of AI systems through MCP, returning structured execution telemetry and output dossiers.

MCP server that converts file contents into compact, line-numbered PNG images for vision models to read, reducing token usage by roughly 7x for large files.

An MCP server that exposes tools for sub-agent style reasoning across multiple LLM providers, enabling delegation of prompts to various models and running critique loops, debates, red-teaming, and answer ranking.

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

Converts text or markdown into Xiaohongshu (Little Red Book) style image cards with AI cover generation, supporting multiple themes and aspect ratios.

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

Exposes Microsoft's PyRIT AI red-teaming framework as structured tools for MCP-compatible agents, enabling authorized AI security assessments through engagements, targets, attacks, scoring, and reporting.

Provides 40 MCP tools for searching and retrieving content from six major platforms (Douyin, Xiaohongshu, WeChat, Bilibili, Toutiao, TikTok) along with AI search and image/video generation via RedFoxHub's API.

Enables coding agents to make offline, zero-cost decisions using schema-safe Choice/Score/Noul primitives, a confidence gatekeeper, planning, adversarial red-teaming, research, and RLVR-based self-improvement via 21 MCP tools.

Enables movie and TV recommendation workflows, including title resolution, evidence tracking, candidate retrieval from MovieLens and TMDB, and recording of recommendation runs and reactions.

A stdio MCP server that enables agents without native vision to ask an OpenAI-compatible vision model to describe, OCR, or extract structured data from images via a single tool.

Minimal MCP server for Kimi-compatible image analysis, allowing local images to be sent as inline base64 to any compatible endpoint.

Provides AI assistants with direct access to Red Hat OpenShift AI observability data, enabling querying of Prometheus metrics, Alertmanager alerts, Loki logs, Grafana dashboards, and Kubernetes cluster state to troubleshoot vLLM inference workloads.

Generates dating profile bios with embedded red flags using the StupidAPIs.

An MCP server that enables AI agents to interact with Red Hat OpenShift AI environments, providing tools for project management, workbench operations, model serving, and more.

Enables AI coding agents to perform end-to-end medical image analysis locally, from inspecting CT/MRI/X-ray studies and running containerized segmentation models like MedSAM2, TotalSegmentator, and HD-BET to refining masks, measuring volumes, and writing reports. It pairs preset or custom guideline protocols with a code-customizable viewer that renders images back to agents as annotated PNGs and to humans as interactive HTML.

MCP server that exposes an AI decompiler via an OpenAI-compatible API, enabling decompilation, explanation, and variable renaming of disassembly for binary analysis.

Enables AI agents to manage a homelab by providing tools for Docker, Ollama, and system monitoring through the Model Context Protocol.

Enables automated LLM red teaming by submitting asynchronous test runs, retrieving aggregated metrics, and accessing artifacts.

Provides a read-only MCP server to access ChatGPT conversation history via a local browser process. Allows AI clients to list, get, and search conversations from the authenticated user's ChatGPT account.