3236 Model Context Protocol servers — searchable, rated, ready to install.
Read-only Bicycle Guide registry: published guides, homes, taxonomy, capability spine. No auth.
MCP server for AlienVault OTX: pulses, indicators. Free key.
Read-only Bicycle Guide registry: published guides, homes, taxonomy, capability spine. No auth.
CVE, KEV, MITRE ATT&CK, CWE and detection graph for AI agents; every link names its source.
Audits AI-built websites for France and Belgium: cookies, GDPR, legal pages, exposed keys, security.
Shared Markdown memory that every AI assistant can read and write. Hosted in the EU.
Audit, rank-track and analyze SEO for sites via an authenticated MCP server.
Read PDFs locally: text, pages, metadata, scan detection, layout, permissions, render, OCR.
中国大陆寿险/分红产品数据:利益演示、保费现价测算、行业指标与竞品对比、需求转介;免费每日 30 次,OAuth 2.1 授权,无需 Key
Read-only Cedar ARMS railroad data via Cedar login for authorized carriers.
Scan a live web page for WCAG 2.1/2.2 AA issues with axe-core: score, grade, failing rules.
Coding & security oracle grounded in 1855 real books. Cited answers via MCP.
Fail-closed MCP adapter for untrusted model output over a local Tkach runtime.
LovedOne Soft: clients, visits, notes, invoices, scheduling. API key or OAuth care_circle:write.
Query OSV.dev for known vulnerabilities by package and version, and scan lockfiles in batch.
Free no-storage MCP that checks A2A Agent Card connection readiness for authorized targets.
Three-layer firewall for MCP: content, egress and action policy. Proxy or server.
Create dynamic QR codes and re-point ones already printed, with bot-filtered scan analytics.
US carrier vetting on FMCSA data: authority, insurance, safety, identity links. Pay per call (x402)
Store speed, web-app security checks, automation ROI, checklists and guides from 7IT Solutions.
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
eBay MCP — Browse + Taxonomy APIs via client_credentials OAuth
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
POST /mcp