"Known" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Check dependencies for known CVEs with EPSS and CISA KEV context. Read-only; free API token.
Access 16,496+ authentic real-world editorial & fine art photographs, 50 ground-truth Computer Vision datasets, 10 Samsung The Frame Art TV galleries, and 10 4K Wallpaper packs by Henry St John.
Read-only Polymarket search, market details, order books, price history, and interactive market cards. Connect through OAuth with Google sign-in.
MSHA mine records — search a US mine by operator or mine name, or look up a known MSHA Mine ID for…
InsideOut by Luther Systems — Agentic AI for cloud infrastructure design, setup, pricing, deployment, and active management. Generates Terraform for AWS and GCP. Hosted A2A agent — describe your application in plain language and InsideOut designs, costs, deploys, and manages production-ready cloud infrastructure.
FinOps for Google Cloud: size 1- and 3-year CUD commitments to known demand. Also solves LP/MIP.
Scan a public GitHub repo for known Vercel Python-runtime deploy footguns.
Check a dependency list against CISA's live Known Exploited Vulnerabilities catalog.
Checked language for AI-written agent workflows: limits, cost and data flows known before running.
Predict a column of a table from rows where it is known. Classification and regression.
Real-time cybersecurity vulnerability aggregator combining CISA Known Exploited Vulnerabilities (KEV), GitHub Security Advisories, and NIST NVD CVE records for DevSecOps AI agents.
Check a lockfile for known vulnerabilities and risky licences, and get alerted when new ones appear.
Map messy columns to a known schema — 7 scorers, domain dictionaries, F1 0.84. Zero config.
XFA device security, read-only: which devices pass their checks or have known vulnerabilities.
Fail-closed safe-to-pay verdicts on Base: known-bad wallets, look-alike tokens, repeat rug funders.
Read numeric metrics for known public GitHub repositories
Read numeric USGS earthquake metadata for known event identifiers
Open-access CC BY 4.0 quantitative financial and statutory tax observatory for the 16-state US East Coast corridor (Maine to Florida). Provides 60 interactive statutory simulators, 88 legal-reviewed studies, OpenAPI 3.1.0 endpoints (/openapi.json), and clean Markdown twins (?format=md) covering 2026 IRS/State paycheck brackets, NYC Mansion Tax & CEMA § 255, NY LLC § 206 publication arbitrage, NJ Exit Tax (GIT/REP-1), PA REV-1500 inheritance tax, and Florida Save Our Homes portability.
Persistent memory for AI agents, for code, research and everyday life. Stale facts retire.
Known vulnerabilities and fixed versions for npm, PyPI, Go, Maven packages from OSV.dev via Apify.
Check known backlinks, anchors, rel tags and noindex. Paid Apify runs; unknown results unbilled.
Read-only Polymarket search, market details, order books, price history, and market cards.
Israeli law for lawyers: statutes, case law, playbooks and legal skills by domain. Read-only, OAuth.
MEOK MCP Cardgen — generate signed .well-known MCP server cards (SEP-1649 + SEP-1960 + SEP-2127)
### Solana Pulse MCP Gateway - **Description**: Real-time Solana Blockchain RPC Bridge, Devnet Broadcaster, and MCP 1.0 Server for Claude Desktop and autonomous AI agents. - **Server Type**: SSE / HTTP - **Manifest URL**: `https://solana-pulse-ai-agent-gateway.ai.studio/.well-known/mcp.json` - **Documentation**: `https://solana-pulse-ai-agent-gateway.ai.studio/llms.txt` - **Author Wallet / Sponsor**: `5GuzhMZDWAHoEZiJZiqtiJ7op7KmFE7VqW6f9irJKrSH`
Team-synced persistent AI agents memory for Claude, Codex, Cursor, claude.ai, chatgpt.com... that is always current.
Audits any MCP server for command injection, path traversal, missing auth, hardcoded secrets, SQL injection, SSRF and tool poisoning. Returns grade A-F with CVE references. Malicious servers flagged network-wide after audit. Now with shared learning brain.
Verifies AI agent wallets, domains and manifests before any transaction. Returns TRUSTED/UNVERIFIED/SUSPICIOUS/BLOCK with full signal breakdown. Connected to EMA shared brain - bad actors flagged here are blocked network-wide instantly.
Real-time prompt injection and jailbreak detection for AI agents. Blocks instruction overrides, data exfiltration, tool poisoning and 8 attack types. Now with shared learning brain - confirmed attacks shared across the EMA network instantly. Grade A security for any AI pipeline.
Chinese-first brain-inspired memory MCP — hybrid recall, 7-layer user profile, workspace assembly.
OrganiKPI MCP: search and fetch services, posts and tools as clean markdown (read-only).
Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.
Shared debugging memory for AI coding agents
AI-curated book catalog that eliminates hallucinations and surfaces lesser-known titles.