mcpbeat Sign in

AIShield Security Scanner MCP Server

answering

AIShield Security Scanner is answering right now. Last checked 1 min ago. 32 installs a week from npm. It exposes 10 tools. Last commit 22 Sep 2026.

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

Installs per day peak 257 · avg 10
a month agotoday
Uptime history 48 days of history · worst day 44%
48 days agonow
98.9%
Uptime 24h
90 of 91 checks
10
Tools
read from the server
856 ms
Response time
average over 24h
32
Installs / week
npm and PyPI

What changed 7

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 28 August 2026. No other catalogue keeps this.

19 Sep 2 tool descriptions were rewritten aishield_digest, aishield_scan
19 Sep a tool appeared aishield_digest
16 Sep a tool description was rewritten aishield_scan
28 Aug a tool appeared aishield_vertical_risk
28 Aug a tool description was rewritten aishield_scan
28 Aug a tool changed version

What the code does

We read the source, 9 h ago · tools taken from the live server · rules 3dff92dd89df

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

        (r"\brm\s+(-rf|-r)\b", "rm -rf — 可删除文件/目录"),
Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Builds a file path from a variable api/server.py:717
            asset_path = os.path.join(BASE, "static", rel)
      "answer": "AIShield's sandbox-hardening rules detect a mounted docker.sock, the --privileged flag, host network, PID, and IPC namespaces, cap_add set to ALL, seccomp set to unconfined, --user 0, and Kubernetes hostPath mounts.",
In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

Builds a database query by concatenation .github/workflows/project-digest.yml:297
      - name: Create or update digest Issue
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch AIShield Security Scanner and you get told the day something new turns up.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

run in your terminal
claude mcp add aishield --transport http https://aishield.tools/api/v1/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "aishield": {
      "url": "https://aishield.tools/api/v1/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.aishield]
url = "https://aishield.tools/api/v1/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "aishield": {
      "url": "https://aishield.tools/api/v1/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "aishield": {
      "url": "https://aishield.tools/api/v1/mcp"
    }
  }
}

Available tools 10

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

aishield
aishield_banned_words
Chinese banned words detection — 6 platform rules
aishield_digest
Compact trust digest (aishield-digest/v1) — a few hundred bytes plus a content fingerprint, so an agent can answer 'can I trust this?' every turn without re-pulling the full report. Accepts {configs} (static analysis only), {scan_result}, or {source_url}. The returned `risk` is never lighter than the worst finding actually present (a config with high findings is never labelled 'safe'), and no plaintext credential is ever echoed back.
aishield_guardrail
Pre-install safety check — pass/block verdict
aishield_handshake
MCP handshake verification — analyze MCP config, detect npx auto-install, sensitive env vars, oversized tool descriptions, and attempt HTTP handshake
aishield_prompt_check
Prompt injection detection — Chinese + English
aishield_rug_pull
Rug pull detection — check if a tool has removed security code or added suspicious changes in recent commits
aishield_scan
OWASP MCP Top 10 aligned security scan — 235 rules, 5-dimension scoring
aishield_vertical_risk
Vertical-industry risk scan — detect high-risk claims for finance/medical/gov sectors (unlicensed diagnosis, illegal medical device, financial over-promise, etc.)
agent
agent_quick_scan
Agent-First quick scan — scan a tool by name and description, no source URL required
agent_register
Agent-First one-click onboarding — register as an Agent, get DID + API Key + quick start guide in a single call

Endpoints

URLTransportStateLatencyChecked
https://aishield.tools/api/v1/mcp streamable-http answering 868 ms 1 min ago

Alternatives to AIShield Security Scanner

same job, measured the same way
Mcpshield
by mcpshield-dev

Security scanner for MCP servers - detects tool poisoning and injection

27 installs/wk local only
C
MCP Safeguard
by cognivators

MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.

125 installs/wk local only
Mund — MCP Security Scanner
by tyox-all

Scan for prompt injection, secrets, PII, and vet MCP servers before installation

35 installs/wk local only
Sentinel Scan
by ventrova

MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.

56 installs/wk local only
mcp-armor
by studiomeyer

Security sidecar for MCP servers: 11 read-only control-plane tools for prompt-injection checks.

local only
MCP Shield
by sophiacave

Security scanner for MCP servers. SSRF, path traversal, injection, auth, secrets. Grade A-F.

32 installs/wk local only
Shadowgate MCP
by josephibra

Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.

answering
TrustScan
by entradox

Security scanner for MCP servers and skills: Unicode injection, patterns, secrets.

4 tools answering

AIShield Security Scanner — questions

Answers built from our own checks of this server.

What can AIShield Security Scanner do?
It exposes 10 tools, read directly from the server on our last check. Among them: agent_quick_scan, agent_register, aishield_banned_words, aishield_digest, aishield_guardrail, aishield_handshake and 4 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
What is AIShield Security Scanner mostly used for?
Its tools cluster around aishield and agent. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is AIShield Security Scanner working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 90 of 91 checks got a reply (98.9%), average response time 856 ms. The bar chart above shows every period we have measured.
How do I connect AIShield Security Scanner?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does AIShield Security Scanner need an API key?
No. AIShield Security Scanner completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 10 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is AIShield Security Scanner?
It answers our handshake in 856 ms on average, which is faster than 14% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use AIShield Security Scanner?
The npm package aishield-mcp-server was installed 32 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is AIShield Security Scanner open source?
Yes — it is published under the MIT licence, written in Python, 2 stars on GitHub and 6 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.