ai-guardrail-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ai-guardrail-mcp scan this text for policy issues: "We guarantee 100% success""
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@mhdd_24/ai-guardrail-mcp
MCP server for Input/output policy validation.
Same architecture as @mhdd_24/sublime-mcp.
Full documentation: docs/WIKI.md
How it works (30 seconds)
You (chat) → MCP client → ai-guardrail-mcp → AI Guardrail APIs / CLIs / local toolsRelated MCP server: sentinel-scan
Prerequisites
Requirement | Notes |
Node.js 18+ | ESM TypeScript MCP server |
Credentials / CLIs | See environment variables below |
Install
Option A — npm (after publish)
npm install -g @mhdd_24/ai-guardrail-mcpOption B — npx
npx @mhdd_24/ai-guardrail-mcpOption C — clone and build
git clone https://github.com/Mhdd-24/AI-Guardrail-MCP.git
cd AI-Guardrail-MCP
npm install
npm run build
node dist/index.jsConfigure Cursor
Edit ~/.cursor/mcp.json:
{
"mcpServers": {
"aiguard": {
"command": "npx",
"args": ["-y", "@mhdd_24/ai-guardrail-mcp"],
"env": {
"_": "optional"
}
}
}
}Local development:
{
"command": "node",
"args": ["/absolute/path/to/AI-Guardrail-MCP/dist/index.js"]
}Environment variables
Variable | Description |
— | No required env |
Tools
Tool | Description |
| Show Input/output policy validation configuration / health. |
| Scan text for policy/safety issues. |
| Generate a test suite outline. |
License
ISC
Available Tools
3 toolsaiguard_scanC
Scan text for policy/safety issues.
Inputs: text (required).
aiguard_statusA
Show Input/output policy validation configuration / health.
Inputs: no named parameters.
aiguard_suiteC
Generate a test suite outline.
Inputs: policy (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The three tools have clearly distinct purposes: status/health checking, text scanning, and test suite generation. There is no overlap or ambiguity between them, making tool selection straightforward.
All tool names follow a uniform aiguard_ prefix pattern with a single lowercase descriptive word. This consistent naming convention makes the tool set predictable and easy to navigate.
Three tools is a compact but reasonable size for a focused guardrail utility. Each tool has a distinct purpose, though the set could potentially be slightly expanded with additional related operations without feeling bloated.
The tools cover health/status, text scanning, and test outline generation, but notable gaps exist—there is no policy management or execution capability for the generated test suite. Specifically, aiguard_suite creates an outline with no way to run it, creating a dead end in the workflow.
Related MCP Connectors
Statically audits MCP tool surfaces for token cost, schema quality, and design issues.
MCP policy creation, quality checks and guarded data handoffs before automated writes.
Scan text, documents, websites, and MCP metadata for prompt injection and sensitive-data risks.
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables users to validate MCP servers, skills, extensions, and packages for schema, security, functional, and semantic quality directly from their MCP client.MIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to scan tool manifests and server configs for prompt injection, tool poisoning, excessive agency, and other OWASP-mapped security issues directly through the scan_mcp_manifest tool.50 npm3MIT
- AlicenseBqualityCmaintenanceEnables scanning text for policy and safety issues, generating test suite outlines, and checking the configuration/health of the evaluation setup.310 npmISC

MCP Security scannerofficial
AlicenseAqualityBmaintenanceEnables users to deterministically audit MCP servers for security issues across manifests, source, runtime responses, multi-call state, identity, and install scripts, and to run an inline gateway that gates tool calls and scans responses before returning them.325 PyPI1Apache 2.0