ZBS Index What actually exists in applied AI, with the source next to it

mcp server

AIShield Security Scanner

Scans MCP servers for tool poisoning, prompt injection and supply chain risks.

Description as published by the maintainer. Source

  • version 4.2.1
  • active
  • security

active — Registry entry last updated 2026-08-05. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

8 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

agent_quick_scan(tool_name, source_url, tool_description)
Agent-First quick scan — scan a tool by name and description, no source URL required Required: tool_name, tool_description.
agent_register(owner, agent_name, capabilities)
Agent-First one-click onboarding — register as an Agent, get DID + API Key + quick start guide in a single call Required: agent_name.
aishield_banned_words(text, platform)
Chinese banned words detection — 6 platform rules Required: text.
aishield_guardrail(auto_block, source_url)
Pre-install safety check — pass/block verdict Required: source_url.
aishield_handshake(source_url)
MCP handshake verification — analyze MCP config, detect npx auto-install, sensitive env vars, oversized tool descriptions, and attempt HTTP handshake Required: source_url.
aishield_prompt_check(prompt)
Prompt injection detection — Chinese + English Required: prompt.
aishield_rug_pull(source_url)
Rug pull detection — check if a tool has removed security code or added suspicious changes in recent commits Required: source_url.
aishield_scan(name, tool_type, source_url)
OWASP MCP Top 10 aligned security scan — 133 rules, 5-dimension scoring Required: source_url.

Last successful function declaration observed on . Source: https://aishield.tools/api/v1/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://aishield.tools/api/v1/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
Latest published version 4.2.1 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-08-05 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-08-05 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
mcp tools declared 8 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe aishield.tools
mcp endpoint status ok The server listed 8 functions when asked. as of probe aishield.tools

Where to get it

Also from lm203688

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. Tools declared by the MCP server at https://aishield.tools/api/v1/mcp — aishield.tools, observed , trust tier 1.
  2. Official MCP Registry — Model Context Protocol, observed , trust tier 1.