"Security" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Deploy and operate Kubernetes: clusters, stacks, apps, logs, metrics and security, with OAuth.
A2A & MCP Pre-Flight Security: SHA-256 tool schema rug-pull detection and liveness grades.
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
Agent website testing: browser QA, visual regression, Markdown extraction, and security checks.
Sealed order book for non-security agent work: orders rest non-displayed and disclose only as fills.
Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.
Universal executive presentation suite generating editable DrawingML PowerPoint (PPTX), interactive Web decks, Executive KPI Dashboards, Whiteboard Infographics, and vector PDFs with Zero-Retention security.
Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.
Model proof-of-work policy and latency for AI agents. $1 USDC rehearsal; no runtime protection.
ToolYour is a remote MCP harness for AI agents: plan work, run playbooks or solve goals, and verify until checks pass. Primary jobs are ship-gate, SEO audits, and security audits. Developers call the same capabilities through REST; people smoke-check tools in the browser. MCP and REST share one API key and monthly credit quota.
Find and try paid AI agent skills for security, on-chain data, code, markets, research and news.
Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.
Find tools ranked by measured behaviour, read agent reviews, and talk to other people's agents.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
The Google Compute Engine MCP server is a fully-managed Model Context Protocol server that provides tools to manage Google Compute Engine resources through AI agents. It enables capabilities including instance management (creating, starting, stopping, resetting, listing), disk management, handling instance templates and group managers, viewing machine and accelerator types, managing images, and accessing reservation and commitment information. The server operates as a zero-deployment, enterprise-grade endpoint at https://compute.googleapis.com/mcp with built-in IAM-based security.
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
## MarketNow — Agent Skill Marketplace 🔥 ### What is it? MarketNow is an **open MCP skill marketplace** with **13,859 verified skills** for AI agents. Every skill is automatically scanned by **Sentinel** (our security engine) for malware, hardcoded secrets, and license compliance. ### MCP Endpoint
Find best-fit tools for any problem, vetted for prompt-injection risk before your agent trusts them
Threat-intelligence verdicts on a URL, domain or IP before a coding agent connects to it.
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
