3236 Model Context Protocol servers — searchable, rated, ready to install.
AI security firewall & DLP proxy protecting API keys and blocking destructive commands.
Personal context and preferences for AI via OAuth-approved profile sections and taste data.
Pickup orders at Japanese restaurants for AI agents: find stores, read menus, place orders. No auth.
License plate lookup for AI agents: plate messages and ALPR history via PlateQuery. OAuth 2.1.
Real-device ad verification: malvertising and cloaking scans, AI policies, alerts, webhooks.
Turn a prompt and a link into a branded, print-ready QR code that always scans.
Scans code, IaC and AI-agent config for security problems. Read-only — nothing can be edited.
Invoice PDFs, scans and photos to Excel, with the math checked: fields, line items and totals.
ny-authority-debt — New York public authority debt issuance. Fleet #1001.
Agent bridge. Host-readable; anyone with the link can read and reply. Not for secrets.
Static AST security scanner detecting command injection, leaked secrets, and SSRF in MCP tools.
Cobalt Intelligence MCP — US Secretary-of-State business registration, UCC liens, and TIN/EIN…
Governed external-environment scanning: signal harvest, Field Intel Reports, per-signal lineage.
Author PDF templates and generate documents from them.
Agent trading tools: candles, copy-trading, hire a strategy for your Robinhood vault, pay on chain
Triage cubic AI code review findings, start PR reviews, and read wikis, scans, and team learnings.
Send and read one-time encrypted secrets with local encryption.
Browse, inspect, and retrieve installable React and Next.js interaction effects from Hyperiux Vault.
Daily photo game: you see a secret word, show it in photos, and your AI guesses it.
Reference integrity for AI agents. Scans and verifies links, imports, assets, deps.
Finds the 12 author-side privacy duties your plugin PHP breaks, with the article and the fix on ever
Grade a site's security headers with fixes and a badge; read logs or code for the defender.
Sourcery security findings: MCP server, CLI, and fix-prompt builder over the Sourcery API.
Read-only macOS disk analysis with bounded scans, size queries, and extension breakdowns.
POST /mcp