Loading…
A curated registry of Model Context Protocol servers, each with an automated security grade from our tool-surface scanner.
Context for the grades below — how inspection, tool poisoning, and the grade-vs-gate split work. Directory letters are Andrax scanner grades (mcpgrade-1.4.0), not Guard runtime scores.
Soft CTA: a grade finds risk on a snapshot; Guard enforces allow/deny/audit on live MCP traffic (mcpgrade-2.0.0). Do not equate the two scores.
Run an MCP server? Paste its remote endpoint — we'll scan it (read-only) and publish a free, reproducible security grade. Genuine MCP servers get listed instantly.
Validates and generates EU e-invoices (UBL 2.1 / EN 16931) through a public, no-signup hosted MCP server.
Structured Japan sports schedules, fixtures, broadcasts, and live updates for AI agents via the Spocal API.
Exact VRAM and KV-cache fit calculations for LLMs on GPUs, multi-GPU rigs, and Macs — read-only MCP access.
Inspects webhook health, investigates delivery failures, configures sources, and replays missed events for Relin's webhook reliability platform.
On-chain crypto compliance tooling covering stablecoin freeze status, token security, wallet screening, and KYT risk verdicts.
Send free and paid faxes to US and Canada from AI agents via MCP.
Fuse Network's MCP server gives AI agents on-chain access to the Fuse blockchain.
Converts files between 50+ formats and runs PDF and image operations for AI agents.
FX protection for SMEs — price guards, live spot and forward rates, and settlement date calculation.