3399 Model Context Protocol servers — searchable, rated, ready to install.
Draw40 is an independent diagram workspace with an interactive MCP Apps canvas. OAuth sign-in.
CVE, KEV, MITRE ATT&CK, CWE and detection graph for AI agents; every link names its source.
Local MCP server for architectural decisions, traceability, and non-authoritative proposals.
Backtest trading ideas and inspect strategies, trades and results. OAuth; invite-only beta.
Signup-free lyric editing: upload authorized audio, change words, preview, and download.
Check how visible a website is in ChatGPT, Claude and Gemini answers, and start a new scan.
Sourced prop-firm daily-loss and max-drawdown rules and a drawdown-room checker. Read-only, no auth.
Verified, reproduced behavior of public HTTP APIs: spec gaps, errors, pagination, auth.
Rental property tools for agents: turnover cost estimates and security deposit rules by US state.
Find and run AI workflows from the Edgaze marketplace in your agent. Sign in with OAuth.
Free agent evidence: 6 guides, 2 distinct MCP connectors; optional paid local checks. No authority.
Scans MCP tool definitions for hidden instructions and confused-deputy sinks
Triage cubic AI code review findings, start PR reviews, and read wikis, scans, and team learnings.
Sourcery security findings: MCP server, CLI, and fix-prompt builder over the Sourcery API.
Singapore HSA registered therapeutic products — the Health Sciences Authority's official 'Listing…
Keyless MCP server for PyPI: Python package versions, summaries, authors, requirements, release...
Spaceti workplace analytics: occupancy, environment, bookings, sensors. Read-only, OAuth 2.1 login.
Agent trading tools: candles, copy-trading, hire a strategy for your Robinhood vault, pay on chain
Check public MCP reachability, protocol handshake, auth and tool schemas before connecting.
Free no-auth tools for Spain: validate IBAN, EU VAT check (VIES), Modelo 303 sums, Veri*factu dates.
Turn a prompt and a link into a branded, print-ready QR code that always scans.
Agent bridge. Host-readable; anyone with the link can read and reply. Not for secrets.
Open-source governance for MCP agents: useful autonomy without unlimited authority
Secret scanning for AI agents: rules and entropy find candidates, a model decides which are real.
POST /mcp