Security

Citepath public MCP server for LLM readiness audits and public scan results.

Security-first, self-hosted email archive with search, cited answers, and sending for AI agents.

200+ audits on AI visibility: AIO, AEO, GEO scores, site issues, competitor gaps and scan history.

Control Sonos from any MCP client. No bridge hardware; connects over OAuth — no API key to paste.

Check how visible a website is in ChatGPT, Claude and Gemini answers, and start a new scan.

Convert uploaded speech or singing with your saved HanoLab voices, using OAuth and credit quotes.

AI-matched AU mattress catalogue: 16 retailers, live AUD prices, agent-attributed leads. No auth.

Create, publish and measure SparkleTree marketing campaigns from an AI client. OAuth 2.1 with PKCE.

Technical SEO, passive security and page-delivery audits with evidence and suggested fixes.

AI agent messaging with durable inboxes, contacts and tasks. Connect through MCP with OAuth.

Audit Dockerfiles for root users, baked-in secrets, curl-pipe-shell and unpinned base images.

Hosted AI agent memory that learns from outcomes, with shared rooms, in Claude, Cursor and ChatGPT.

Score agent manifests, generate CI workflows, and pull Clarx scan findings into your IDE.

Open Korean e-Gov and finance sites in a clean, disposable Windows Sandbox with security programs.

MCP server for Yandex Direct API: campaigns, ads, keywords, bids, reports. Click.ru or OAuth.

Generate, edit and track dynamic (editable) QR codes with scan analytics. Hosted MCP and REST API.

Unofficial Partner Center REST API knowledge & codegen assistant (scenarios, auth, errors).

Positive-security for apps, APIs, LLMs and edge, plus fraud scoring and identity/AML screening.

Inspect an MCP server for common security risks before you install it. Offline, zero telemetry.

Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client

PostgreSQL security for AI agents: CVEs, yanked releases, exploits, and upgrade paths

Safety checks an agent runs before it acts: package malware, destructive command, secret leak.

Security grades (A-F) for MCP servers. Check one before you install or trust it. mcpgrade.dev

Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.