3236 Model Context Protocol servers — searchable, rated, ready to install.
Scan a page for content planted to hijack an AI browsing/shopping agent before it acts on the page.
Audit MCP servers for tool poisoning and shadowing. Scan a remote server by URL or paste its tools.
Doppler API: projects, configs, secrets listing and download. Needs service or personal token.
Security reviews, threat models over a repo or website, and remediation tracking, in your editor.
Free, no auth. Daily CN AI infra: LLM prices, index, trends, GPU, estimators, agents, PC, funding.
Guard Core security MCP: SecurityConfig validation, docs search, live threat detection.
Citepath public MCP server for LLM readiness audits and public scan results.
Read-only Bicycle Guide registry: published guides, homes, taxonomy, capability spine. No auth.
AI-answer-engine visibility scans for local businesses, as agent tools
Free no-storage MCP that checks A2A Agent Card connection readiness for authorized targets.
Document AI and headless DMS: OCR, IDP, search, workflows, signatures. EU-hosted, OAuth 2.1.
Connect AI assistants to the Rubrik Security Cloud GraphQL API to discover, query, and automate.
Check text for leaked credentials before an agent writes or commits it. Runs locally.
Backend for AI agents: one batched tool over ~668 actions (hosting, storage, auth, payments).
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Commerce preflights, agent run mandates, D365 authorization, and offer checks; no external writes.
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
MCP elicitation anti-patterns: secrets in forms, third-party authorize URLs, credentials in URLs
Read-only Bicycle Guide registry: published guides, homes, taxonomy, capability spine. No auth.
Read PDFs locally: text, pages, metadata, scan detection, layout, permissions, render, OCR.
Audits AI-built websites for France and Belgium: cookies, GDPR, legal pages, exposed keys, security.
Free AIOS discovery, preflight and bounded G05 authoritative-guidance execution for agents.
Shared Markdown memory that every AI assistant can read and write. Hosted in the EU.
Fail-closed MCP adapter for untrusted model output over a local Tkach runtime.
POST /mcp