Library
88,764 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
-
Designers
MCP serversChecks, prompts and skills for designers working with AI: contrast, a11y, heuristics, critique.
-
injectcheck
MCP serversScan what AI agents read for prompt injection: hidden unicode, comment instructions, exfil, lures.
Source for injectcheck (opens github.com) @reneturcios/injectcheck@0.1.19 -
Aiso
MCP serversInspect AI brand visibility, tracked prompts, competitors, citations and search fan-outs.
-
ctxfw
MCP serversZero-egress AI Agent Firewall: SARA prompt injection defense, AST context pruning & MCP governance.
Source for ctxfw (opens github.com) ctxfw@4.2.1 -
AI Skill Directory
MCP serversSearch and fetch curated AI agent skills, prompts and MCP servers.
-
N0N4 Guardian
MCP serversC2PA sign/verify for AI agents, prompt-injection scanning, and signed M2M custody handoffs.
-
veprompts-mcp-server
MCP serversVePrompts MCP server for 800+ MCP servers, prompt libraries, and AI engineering.
Source for veprompts-mcp-server (opens github.com) veprompts-mcp-server@1.1.2 -
Boardcheck
MCP serversFlags deceptive signals in AI-agent marketplace listings, from fake engagement to prompt injection
Source for Boardcheck (opens github.com) https://github.com/Echolonius/boardcheck/releases/download/v0.8.1/boardcheck-mcp-0.8.1.mcpb@0.8.1 -
AI SEO Tracker
MCP serversTrack brand visibility, citations, prompts & missing sources across ChatGPT, Perplexity, Gemini.
-
YUSA
MCP serversPrompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.
Source for YUSA (opens github.com) https://github.com/yusasecurity/yusa/releases/download/v0.3.6/yusa.mcpb -
GEO Shield
MCP serversDetects hidden AI prompt injection, AI recommendation poisoning, sneaky redirects and hidden spam.
Source for GEO Shield (opens github.com) geo-shield-mcp@0.1.0 -
agentrica
MCP servers56 AI agents for software, design, privacy, security and product work, as MCP prompts.
Source for agentrica (opens github.com) @agentrica/mcp@0.7.1 -
pixellab-pip
SkillsMeet PixelLab Pip: a tiny pup who fetches the right PixelLab workflow. He follows human commands to create, edit, and animate pixel assets, then sniffs out a bigger prompt, scouts for a useful tool, and carries back what happened.
Source for pixellab-pip (opens github.com) git clone https://github.com/Shilo/pixellab-pip.git -
Sharebench
MCP serversSharebench — search & pull AI skills, agents, prompts & playbooks (SKILL.md) into any MCP client
-
Race Calendar F1
MCP serversAnonymous read-only Formula 1 tools, resources, prompts, completion, and interactive dashboard.
-
AIKIZI
MCP serversSearch decoded art styles and their prompts; decode your own images with your account.
-
Sideways
MCP serversUnexpected questions and lateral thinking prompts to break through mental blocks. 86 strategies.
-
SkillsSafe Security Scanner
MCP serversAI skill security scanner. Detects prompt injection, credential theft, ClawHavoc. Free, no signup.
Source for SkillsSafe Security Scanner (opens github.com) skillssafe-mcp@1.0.0 -
Sideways
MCP serversUse Sideways for unexpected questions and lateral thinking prompts to break through mental blocks.
-
branchly
MCP serversConnect your agent to branchly: manage content, prompts, actions, learn from analytics and insights
-
ai-code-scanner
MCP serversScans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
Source for ai-code-scanner (opens github.com) @guardbee/mcp-ai-code-scanner@0.3.2 -
ai-code-scanner
MCP serversScans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
Source for ai-code-scanner (opens github.com) @guardbee/mcp-ai-code-scanner@0.5.1 -
heu-mcp
MCP serversHEU Legal e-signature MCP: manage HEU documents and PDFs, prompt signers, download PDFs.
Source for heu-mcp (opens github.com) heu-mcp@0.5.2 -
Agent Security Scanner
MCP serversScan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.