5442 Model Context Protocol servers — searchable, rated, ready to install.
Send PDFs for e-signature by email and SMS code. Check signing status. No document storage.
What changed in your stack since the model's cutoff, error fixes, and security-scanned skills/MCPs
Public patent search with ranked candidates, source links and coverage context. Developer beta.
Verify Attest agreements, stamp codes, receipts, proofs and SHA-256 fingerprints, with no sign-in.
Can an AI agent use this software? Levels from real agent test drives: sign-up, keys, use, pay.
Provision an OpenCode workbench and MCP stack on any Linux box, local or over SSH.
Build and run data workflows, analyses, reports and dashboards. Inspect and verify every step.
Free SEO check of any website, AI crawler access test, and the full Audit SEO Records.
Lints whether a paid API's 402 response speaks the x402 protocol correctly.
Send WhatsApp messages from your own numbers, read and answer chats, and send sign-in codes.
Publish static websites to a live URL from chat. Write HTML/CSS/JS, get a hosted site and edit link.
MIC — ISO 10383 Market Identifier Code decoder (fleet #3261)
Keep Claude Code and Codex off each other's files: hook-enforced path leases, presence, messages.
Create branded short links and QR codes, and pull click analytics by country, device and referrer.
Search EU public tenders from TED and national portals by CPV code, country, buyer or value.
Language flashcards in your AI assistant: build decks, edit cards and review what's due in the chat.
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
Published software research from SaaS Think Tank. Current MCP edition: app-builder findings.
Zillow homes for sale, for rent or recently sold by US ZIP code: price, Zestimate, beds, baths.
Read versioned developer documentation with original source links using five public MCP tools.
Web access for AI agents: URL to Markdown, link metadata, screenshots, links and images of any URL.
Build platform-ready carousels from an outline.
Independent AI model test scores on 5 tasks: inbox, scheduling, receipts, finance, support replies.
Scans agent code for untrusted input poisoning persistent cross-session memory
POST /mcp