"AMD" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Deterministic runtime enforcement of step order for AI agents: ALLOW/DENY before a step runs.
Neuronto ARD Registry: one search across every public ARD registry + 200,000+ verified MCP tools
Free agent identity and signed US supplier-payment decisions. Inspect first; verify portable proof.
What a domain publishes for AI agents: ai-catalog.json, llms.txt, agents.md, robots.txt rules. Free.
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Find best-fit tools for any problem, vetted for prompt-injection risk before your agent trusts them
Five pay-per-result web intelligence tools for AI agents, hosted on Apify: tech stack detection (7,600+ technologies from HTML, headers and DNS), company profile from a domain (logo, socials, ATS + open jobs, email setup; no personal data), sitemap extraction and new-page monitoring, URL status and indexability checks, and official EU fuel prices (FR/ES/IT). Auth: Apify OAuth or API token; x402 agentic payments supported. Docs: https://github.com/moha-tah/web-intelligence-mcp
Third-party signed reads of how an AI agent behaved: drift, vows, and the town it works in.
Webhook capture and replay, delivery pipes, and signed multi-agent rooms. No signup to start.
Search and fetch skills from your org's Skills and Agents catalog. Bearer token required.
The bridge from K2 agents through Wrangler to your master AI - safe, approval-gated Cloudflare ops.
A registry of 5,900+ peer-authored skills any MCP agent can search and load on demand.
9 remote MCP servers on Cloudflare Workers for AI agents. Free tier + Pro API keys.
Search and load from 138 production agent personas and skills. search_catalog, preview_product, and recommend_products browse the line; get_free_skill loads any product's complete free gateway skill; premium tools unlock full personas, skills, and themed kits by license.
Inventory and audit your agent fleet over MCP: audit_mcp_config returns risk-ranked findings with a 0-100 posture score, scope_check ranks tool-manifest blast radius, audit_skill_file and injection_scan screen untrusted skill files and text, and inventory_report builds a governance inventory with risk tiers. All analysis is deterministic and local to the request.
