AgentSidekick

Red Teaming

Adversarial testing for safety and robustness. As of 2026-11-21, 28 indexed products offer it (21 with full profiles), in 5 forms: 15 MCP servers, 7 Infrastructure, 3 Developer tools, 2 Libraries. 8 were published in the last 90 days, against 5 in the 90 days before. promptfoo has the most GitHub stars, 44% of the total across 28 products with their own repository.

CapabilitySegment label: Thin DERScored as an opportunity

Available as

All in the directory

Profiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.

MCP servers 15 indexed · 8 profiled

Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms

Red Teaming: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1AISafetyHotAI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.wuyoscar2.1ktoday
2agentic-radarA security scanner for your LLM agentic workflowssplx-ai1.1k8d ago
3agent-opforOpen-source adversary emulation for AI agents and MCP servers. KeyValueSoftwareSystems58818d ago
4vulnerable-mcp-servers-labA collection of servers which are deliberately vulnerable to learn Pentesting MCP Servers.appsecco28411mo ago
5pgwardenGive AI assistants access to Postgres with per-user permissions and human approval for writes.B0yko22today
6MultimeterScaffold, validate, format, and run YAML .mmt API tests. Do not invent syntax.mshobeyri141d ago
7grok-mcpUse xAI Grok as a peer reviewer + PR gate from Claude Code, Cursor, Cline and any MCP host.howardpen9113mo ago
8RogueGPTStore and retrieve controlled AI news stimuli with generation metadata for misinformation researchaloth814d ago

Infrastructure 7 indexed · 7 profiled

No compatibility evidence is collected for this form.

Red Teaming: Infrastructure by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1AI-Infra-GuardA full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.Tencent7.6k1d ago
2rhesisThe collaboration layer for teams building AI agents. Test, simulate, and trace your agents, while domain experts annotate behavior and engineers improve the agent from what they find.rhesis-ai4051d ago
3OpenARTOpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.AI45Lab2771d ago
4dodoguardDodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Tencent ADP, ByteDance HiAgent, and more. dodoguardai2751mo ago
5aludelPhoenix-native LLM evaluation, prompt testing, model comparison, red teaming, and observability for Elixircristianodabc414d ago
6consoleOpen-source, self-hosted AI gateway and control plane: OpenAI-compatible LLM routing, RAG, an MCP hub, guardrails and agent tracing for multi-tenant teams.Cognipeer281d ago
7ai-evaluation-toolsThe comprehensive list of AI evaluation tools: 300+ open-source and commercial LLM evaluation frameworks, platforms, benchmarks, observability, red teaming, and guardrails — for LLMs, RAG, and AI agents.aglio-lab163mo ago

Developer tools 3 indexed · 3 profiled

No compatibility evidence is collected for this form.

Red Teaming: Developer tools by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1promptfooCLI and library for declarative prompt/model test suites, side-by-side comparisons and automated red-teaming of LLM apps and agents.OpenAI (Promptfoo)28ktoday
2garakLLM vulnerability scanner that probes models and apps for jailbreaks, prompt injection, data leakage and toxicity.NVIDIA10k3d ago
3PyRITPython Risk Identification Tool for automated red-teaming of generative AI systems with attack orchestrators and scorers.microsoft5.0ktoday

Libraries 2 indexed · 2 profiled

No compatibility evidence is collected for this form.

Red Teaming: Libraries by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1red-team-blue-team-agent-fabricAI agent security harness, adversarial testing: 661 executable tests in the v4.31.1 release, across MCP, A2A, x402/L402, decision governance, benchmark integrity, human-in-the-loop, skill supply chain. Five target shapes: a verdict must be able to be wrong AND to be right. OWASP Agentic v1.1 T1-T17, AIUC-1 crosswalk (2026-10-15), NIST AI 800-2.msaleme34today
2ziranZIRAN finds the vulnerabilities in AI agents that come from tools combining, not from any single prompt. Graph-based tool chain discovery, execution-level side-effect detection, multi-phase campaigns.taoq-ai123d ago

Frameworks 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

Red Teaming: Frameworks by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1agentic_securityAgentic LLM Vulnerability Scanner / AI red teaming kit 🧪msoedov2.0k2d ago

Which platforms these forms can reach

All platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Platforms publishers name

PlatformProfiled products naming it
Claude Code1
Cline1
Cursor1

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

IntegrationProducts Share
PostgreSQL13.6%
n8n13.6%

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
red teaming20
adversarial testing4
safety testing0
garak1
promptfoo3
vulnerability probing0

Segment statistics

Whole catalogue (28 indexed products). Calculated 2026-11-21.

28DERIndexed products21 with full profiles
8DERLaunched, last 90 days5 in the 90 days before
18DERMomentum vs catalogue50 = same pace as the catalogue
44%DERLargest project's share of starsAcross 28 products with their own repository
0.249DERConcentration (HHI)About 4 equal-sized projects’ worth; moderately concentrated
38SRCMedian starsPer product with its own repository
82%DEROpen sourceMarked open source; unknown counts as not

Thin. Among the smallest 30% of capabilities, and launches are not outpacing the catalogue. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.249 means stars are spread as if across about 4 equally popular projects — moderately concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.

Scored as an opportunity

Score breakdown

Coverage gap: Red Teaming: score 58.1 HEU, competition High, confidence Low. Only 28 indexed products match "Red Teaming", against 507 in Agent Evaluation overall.

Limits

  • Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
  • Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
  • Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
  • Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.

Page data last updated .