Agent Threat Protection
Defending agents from injection, poisoned tools and leaks. As of 2026-11-21, 473 indexed products match this subcategory (138 with full profiles); 213 were published in the last 90 days, against 115 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, iFixAi leads, holding 24% of the stars of the 398 products here with their own repository. The most common form is MCP servers (90% of indexed products).
SubcategorySegment label: Lagging the catalogue DER
Segment statistics
Whole catalogue (all 473 indexed products, not only profiled ones). Calculated 2026-11-21.
Lagging the catalogue. Mid-sized for its level, with launches growing more slowly than the catalogue’s. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.103, attention is spread as if across about 10 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 424 | 89.6% | 93 |
| Infrastructure | 14 | 3.0% | 14 |
| Agent skills | 11 | 2.3% | 11 |
| Plugins | 7 | 1.5% | 5 |
| Libraries | 6 | 1.3% | 6 |
| Rules packs | 3 | 0.63% | 1 |
| Frameworks | 3 | 0.63% | 3 |
| Developer tools | 2 | 0.42% | 2 |
| Agent projects | 2 | 0.42% | 2 |
| AI APIs | 1 | 0.21% | 1 |
4 capabilities
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Prompt Injection DefenseDetecting and blocking prompt injection and jailbreaks. | 193 | 58 | 89 | Crowded, slowing |
| Data Loss PreventionDetecting and redacting sensitive data. | 89 | 20 | 44 | Lagging the catalogue |
| Secrets ManagementStoring and injecting credentials safely. | 57 | 14 | 26 | Lagging the catalogue |
| MCP Server ScanningAuditing MCP servers for malicious or risky tools. | 47 | 13 | 22 | Lagging the catalogue |
Top 40 products by GitHub stars
Search the directoryProfiled products only (138 of 473), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | iFixAiIndependent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds. | Infrastructure | ifixai-ai | 47k | 1d ago | Apache-2.0 | ||
| 2 | infisicalInfisical is the open-source platform for securing secrets, certificates, access, and AI Agents. | Agent project | Infisical | 31k | today | — | ||
| 3 | mcp-for-beginnersThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration. | MCP server | microsoft | 18k | today | MIT | ||
| 4 | OmniGetDesktop toolbox for coding agents: downloads, files, pages, ports, chats and cleanup, in OmniGet | MCP server | tonhowtf | 15k | 1d ago | GPL-3.0 | ||
| 5 | garakLLM vulnerability scanner that probes models and apps for jailbreaks, prompt injection, data leakage and toxicity. | Developer tool | NVIDIA | 10k | 3d ago | Apache-2.0 | ||
| 6 | AI-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. | Infrastructure | Tencent | 7.6k | 1d ago | Apache-2.0 | ||
| 7 | NeMo GuardrailsToolkit for adding programmable rails (topic control, jailbreak and content safety checks) to LLM apps using the Colang language. | Library | NVIDIA | 7.5k | 2d ago | Apache-2.0 | ||
| 8 | bla🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQLite, GGUF/Safetensors & Android DEX against AI reverse-engineering agents (REA). | MCP server | qybaihe | 6.4k | today | MIT | ||
| 9 | GiskardTesting library that scans LLM agents and RAG apps for hallucination, prompt injection and harmful-content vulnerabilities and generates test suites. | Library | Giskard | 6.0k | 1d ago | Apache-2.0 | ||
| 10 | Handsy AILet AI agents see and operate a real iPhone via an ESP32-S3 USB HID + AirPlay. No jailbreak. | MCP server | onehumanbeing | 5.2k | today | MIT | ||
| 11 | nonoagent runtime security - zero trust, zero setup, zero latency agent sandboxing | Agent project | nolabs-ai | 5.1k | 1d ago | Apache-2.0 | ||
| 12 | AI-Engineer-HeadquartersA collection of scientific methods, processes, algorithms, and systems to build stories & models. | Infrastructure | hemansnation | 3.8k | 24d ago | — | ||
| 13 | Snyk Agent ScanScanner that inspects installed MCP servers and agent configs for tool poisoning, prompt injection and toxic flows. | Developer tool | Snyk (Invariant Labs) | 3.3k | 2d ago | Apache-2.0 | ||
| 14 | bionic-gptBionic is sovereign Agentic AI for the enterprise — Runs on-premise and can securely work with your sensitive data and systems. | Infrastructure | bionic-gpt | 2.4k | 4d ago | Apache-2.0 | ||
| 15 | uptrainUpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them. | Infrastructure | uptrain-ai | 2.4k | 2y ago | Apache-2.0 | ||
| 16 | toolhiveToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers. | MCP server | stacklok | 2.3k | today | Apache-2.0 | ||
| 17 | ADRADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber. | MCP server | uber | 2.1k | 1d ago | Apache-2.0 | ||
| 18 | AISafetyHotAI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP. | MCP server | wuyoscar | 2.1k | today | — | ||
| 19 | agentic_securityAgentic LLM Vulnerability Scanner / AI red teaming kit 🧪 | Framework | msoedov | 2.0k | 2d ago | Apache-2.0 | ||
| 20 | Docker MCP GatewayGateway that runs MCP servers in isolated containers and exposes them through one endpoint, with secrets management and call interception. | Infrastructure | Docker | 1.6k | 2d ago | MIT | ||
| 21 | FuzzyAIA powerful tool for automated LLM fuzzing. It is designed to help developers and security researchers identify and mitigate potential jailbreaks in their LLM APIs. | Infrastructure | cyberark | 1.6k | 9mo ago | Apache-2.0 | ||
| 22 | HOL GuardLocal-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server. | MCP server | hashgraph-online | 1.1k | today | Apache-2.0 | ||
| 23 | agentic-radarA security scanner for your LLM agentic workflows | MCP server | splx-ai | 1.1k | 8d ago | Apache-2.0 | ||
| 24 | skylosDead code, security, secrets detection and code quality for Python, TypeScript, Go. | MCP server | duriantaco | 951 | today | Apache-2.0 | ||
| 25 | ThinkWatchSelf-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs. | Infrastructure | ThinkWatchProject | 817 | today | — | ||
| 26 | AnythingMCPMCP gateway and company brain: 957 connectors (SAP, ERP, SQL), file search, memory and skills. | MCP server | HelpCode-ai | 815 | today | AGPL-3.0 | ||
| 27 | Tracekit MCP gatewayMCP gateway you deploy: a Tracekit signer decides and signs each call; agents send each run's token. | MCP server | Cygnux-Labs | 760 | today | MIT | ||
| 28 | VestigeCausal Proof Engine for AI agents: signed log, zero vectors, failures traced to their cause. | MCP server | samvallad33 | 662 | 1d ago | AGPL-3.0 | ||
| 29 | Claude-Code-CyberSecurity-Skill22 production-quality Claude Code Skills for cybersecurity professionals , covering offensive security, defensive operations, reverse engineering, threat hunting, threat intelligence, purple team / adversary emulation, CSOC automation, AI/LLM security, mobile, OT/ICS, GRC, software supply chain security, and more. | Agent skill | Masriyan | 591 | 1mo ago | — | ||
| 30 | agent-opforOpen-source adversary emulation for AI agents and MCP servers. | MCP server | KeyValueSoftwareSystems | 588 | 18d ago | — | ||
| 31 | Emilia ProtocolExact-action approval for consequential agent actions: request, track, and verify signed receipts. | MCP server | emiliaprotocol | 525 | 5d ago | Apache-2.0 | ||
| 32 | blitzstrikeBlitz Strike — a universal MCP security-audit toolbelt. Reconnaissance at speed. Analysis in depth. Validation before report. | MCP server | shinthink | 523 | 17d ago | MIT | ||
| 33 | vigil-llm⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs | Infrastructure | deadbits | 511 | 2y ago | Apache-2.0 | ||
| 34 | lunarlunar.dev: Agent native MCP Gateway for governance and security | MCP server | TheLunarCompany | 509 | today | MIT | ||
| 35 | AutoHarnessAutoHarness: Automated Harness Engineering for AI Agents | Framework | aiming-lab | 470 | 7mo ago | MIT | ||
| 36 | AgentHoundOffensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack. | MCP server | adithyan-ak | 466 | 8d ago | Apache-2.0 | ||
| 37 | outputaiOutput.ai workflow development toolkit for Claude Code. Adds 5 specialist agents (planner, builder, debugger, prompt writer, quality reviewer), 40+ slash-command skills covering scaffolding, debugging, evaluation, and credential management, plus a SessionStart hook that auto-loads Output SDK conventions so Claude understands the framework before the first prompt. | Plugin | growthxai | 445 | today | Apache-2.0 | ||
| 38 | mcp-gatewayA plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents. | MCP server | lasso-security | 403 | 10mo ago | MIT | ||
| 39 | claude-code-organizerOrganize Claude Code memories, skills, MCP servers, commands, agents, rules via drag-and-drop. | MCP server | mcpware | 395 | today | MIT | ||
| 40 | cross-code-organizerCross-Code Organizer (formerly Claude Code Organizer): cross-harness config dashboard for Claude Code, Codex CLI, MCP servers, skills, memories, agents, sessions, security scanning, context budget, and backups. | MCP server | mcpware | 395 | today | MIT |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| GitHub | 5 | 1.1% |
| PostgreSQL | 5 | 1.1% |
| YouTube | 4 | 0.8% |
| Gmail | 3 | 0.6% |
| MySQL | 3 | 0.6% |
| AWS | 2 | 0.4% |
| Android | 2 | 0.4% |
| Google Cloud | 2 | 0.4% |
| Slack | 2 | 0.4% |
| Azure | 1 | 0.2% |
| Google Drive | 1 | 0.2% |
| GraphQL | 1 | 0.2% |
| Kubernetes | 1 | 0.2% |
| Obsidian | 1 | 0.2% |
| Outlook | 1 | 0.2% |
Launches per month
New Agent Threat Protection products per monthSRC
Whole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-12 | 2 |
| 2025-02 | 1 |
| 2025-03 | 2 |
| 2025-04 | 3 |
| 2025-05 | 1 |
| 2025-06 | 1 |
| 2025-10 | 2 |
| 2025-11 | 4 |
| 2025-12 | 1 |
| 2026-01 | 7 |
| 2026-02 | 18 |
| 2026-03 | 24 |
| 2026-04 | 32 |
| 2026-05 | 28 |
| 2026-06 | 29 |
| 2026-07 | 43 |
| 2026-08 | 43 |
| 2026-09 | 52 |
| 2026-10 | 83 |
| 2026-11 | 68 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
No scored opportunity here
Capability gaps are only scored inside subcategories with at least 20 indexed products, and only the top 80 are kept. None falls under this node.
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .