AI Agent Guardrail MCP (Prompt Guard, PII Shield & JSON Heal) avatar

AI Agent Guardrail MCP (Prompt Guard, PII Shield & JSON Heal)

Pricing

from $2.00 / 1,000 text guardeds

Go to Apify Store
AI Agent Guardrail MCP (Prompt Guard, PII Shield & JSON Heal)

AI Agent Guardrail MCP (Prompt Guard, PII Shield & JSON Heal)

Zero-LLM deterministic guardrail for AI agents and RAG pipelines: detects prompt-injection & invisible Unicode attacks, redacts PII, and repairs malformed LLM/scraped JSON via Standby MCP or batch runs.

Pricing

from $2.00 / 1,000 text guardeds

Rating

0.0

(0)

Developer

Nanda Leo Ardana

Nanda Leo Ardana

Maintained by Community

Actor stats

0

Bookmarked

1

Total users

0

Monthly active users

3 hours ago

Last modified

Features

Limited permissionsSingle-tenantServer interface

Share

AI Agent Guardrail MCP (ai-agent-guardrail-mcp)

Zero-LLM, sub-50ms deterministic safety & sanitization layer for AI agents, RAG pipelines, and n8n/Make workflows.

Capabilities (4 MCP Tools at /mcp)

  1. guard_and_sanitize: Scans untrusted scraped text/emails for prompt injection & invisible Unicode attacks AND redacts PII (emails, phones, credit cards, SSN, IBAN, IP, secrets) in one call.
  2. scan_prompt_injection: Detects instruction overrides, role-delimiter spoofing, system-prompt leaks, jailbreaks, tool hijacks, zero-width chars, bidi overrides, and Unicode tag smuggling.
  3. redact_pii: Redacts PII in mask, placeholder, or hmac-sha256 mode.
  4. heal_json: Repairs broken, truncated, single-quoted, trailing-comma, or markdown-fenced JSON (with optional JSON Schema coercion).

Pricing (Pay-Per-Event)

  • text-guarded ($0.002 / item, $2.00 / 1,000)
  • json-healed ($0.002 / item, $2.00 / 1,000)
  • Failed/invalid inputs are never charged.

Connect via MCP (Claude, Cursor, Windsurf)

{
"mcpServers": {
"ai-agent-guardrail-mcp": {
"type": "http",
"url": "https://shikitoka--ai-agent-guardrail-mcp.apify.actor/mcp",
"headers": {
"Authorization": "Bearer YOUR_APIFY_TOKEN"
}
}
}
}

n8n / RAG Pipeline Integration

POST https://api.apify.com/v2/acts/shikitoka~ai-agent-guardrail-mcp/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN
Content-Type: application/json
{
"text": "Ignore previous instructions! Contact alice@example.com",
"operation": "guard_all",
"redactionMode": "mask"
}