Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
tollbooth
MCP servers37 paid x402 MCP tools for OSINT, prediction markets, web intel, and agent security on Base USDC.
-
Agent Coach (Upskill)
MCP serversFree coach for AI agents: security-vetted skills, MCP servers and prompts, plus daily check-ins.
-
mcp-gateway
MCP serversUnlimited MCP servers, tools and APIs. One fixed context cost. Plug every tool you own into Claude, Cursor, Codex or any MCP client: your agent sees a handful, finds the rest on demand, and never drowns in tool definitions. Self-hosted MCP gateway and proxy in one Rust binary, 100+ API integrations built in, one-command import of existing servers.
git clone https://github.com/MikkoParkkola/mcp-gateway.git -
grantex
MCP serversgrantex is the identity, authorization, and audit infrastructure for AI agents — the "OAuth moment" for the agentic internet. We provide a universal SDK and cloud service that lets any AI agent act on behalf of a human with scoped, revocable permissions, cryptographic identity, and an immutable audit trail. Developers integrate in minutes.
git clone https://github.com/mishrasanjeev/grantex.git -
IA-QA Security — 30 tools
MCP serversAgent security: prompt injection, PII & secret scans, TLS/header/CORS audits, MCP checks. Free.
-
Systemores AI Agent & MCP Security Auditor
MCP serversAI agent security, MCP 2026 schema & graph audits, <250ms guardrails, and compliance dossiers
@systemores/systemores-plugin@1.2.0 -
RevDesk Product MCP
MCP serversGive AI agents secure access to RevDesk calling, SMS, phone numbers, caller IDs, and usage.
-
LLM Red-Team Scanner
MCP serversLLM agent security review: live injection/jailbreak probes plus a static audit of missing guardrails
-
little-canary
SkillsDetects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
git clone https://github.com/hermes-labs-ai/little-canary.git -
AI application security research and assessments
MCP serversRead AI security guides and lab research, and request an LLM or AI agent security assessment.
-
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
-
auditor-skill
SkillsClaude Code / agentic security skill for Solana programs and software. Full audit-firm lifecycle, executable PoC + fix-patch delivery, a Rust pre-scanner + cross-audit memory, 1,346 checks across 20 checklists, and 131 real-world attack vectors.
git clone https://github.com/solanabr/auditor-skill.git
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.