The quality layer every
AI agent needs
Catch hallucinations. Block injections. Redact PII. Screen sanctions. Guard trades. 26 tools. One platform. Pay per call in SOL.
of AI-generated packages are hallucinated
USENIX 2025
max GDPR fine for a single data breach
GDPR Art. 83
lost by one agent from a single decimal error
Lobstar 2026
Stop your agent from leaking regulated data
Agents write logs, file tickets, call third-party APIs, and store transcripts — and any of those can leak a customer's SSN, a card number, or a medical record. One unguarded egress is a reportable breach. The PII / PHI / PCI Firewall is the deterministic gate your agent calls before text crosses the boundary.
- ✓ Checksum-validated: cards (Luhn), IBANs (ISO-7064), UK NHS (mod-11), SIN — plus SSN, email, phone, IP
- ✓ PASS / FLAG / BLOCK, a redacted copy of the text, and a signed SHA-256 certificate
- ✓ block / flag / audit modes · jurisdiction & type policy · nothing stored, raw values never returned · <20ms
curl -X POST https://agent-toolbox.ai/v1/scan/pii \\
-H "Content-Type: application/json" \\
-d '{
"text": "Patient SSN 219-09-9999, card 4111 1111 1111 1111"
}'{
"verdict": "BLOCK",
"categories": ["PII", "PCI"],
"totalFindings": 2,
"redactedText": "Patient SSN [REDACTED_US_SSN], card [REDACTED_CREDIT_CARD]",
"certificate": "sha256:5f691771..."
}26 tools. Six suites. One platform.
Composable, agent-callable APIs that verify and improve LLM outputs before they cause damage. Click any tool for capabilities and use cases.
Core quality checks
Security, privacy & analysis
Finance protection
Backed by real incidents: Lobstar $440k decimal error · Claude Code $1,446 unauthorized sweep
Compliance & safety
Deterministic, offline gates for regulated workflows — screen before you transact, dose before you advise
Agent, infra & legal
Deterministic guardrails for tool calls, infrastructure changes, and legal work
Data & validation
Deterministic validators for identifiers, structured output, and SQL
Catch it before it runs
Send AI-generated code. Get a verdict in milliseconds.
curl -X POST https://agent-toolbox.ai/v1/validate/imports \\
-H "Content-Type: application/json" \\
-d '{
"language": "python",
"code": "import numpy\\nfrom superlogger import magic_log\\nimport pandas"
}'{
"language": "python",
"valid": [
{ "name": "numpy", "status": "valid", "registry": "pypi" },
{ "name": "pandas", "status": "valid", "registry": "pypi" }
],
"hallucinated": [
{ "name": "superlogger", "status": "hallucinated", "evidence": "Not found on PyPI" }
],
"verdict": "BLOCK",
"totalImports": 3,
"hallucinationRate": 0.33,
"latencyMs": 142
}Works with Claude, Warp, Cursor — any MCP client
Drop agent-toolbox into your MCP config and your agent gets all 26 tools out of the box — import validation, the hallucination firewall, secret & PII scanning, sanctions screening, medication safety, tool-argument validation, IaC risk gating, legal citation checks, token counting, and the full finance protection suite. No SDK, no glue code.
{
"mcpServers": {
"agentoolbox": {
"command": "node",
"args": ["/path/to/agentoolbox/packages/mcp/dist/index.js"]
}
}
}Start free. Pay per call in SOL.
No subscriptions. No invoices. Agents pay autonomously on-chain.
Pay-as-you-go
- /v1/scan/pii new 0.0001 SOL
- /v1/compliance/sanctions new 0.0001 SOL
- /v1/health/rx-check new 0.0002 SOL
- /v1/agent/tool-args new 0.0001 SOL
- /v1/infra/plan/risk new 0.0002 SOL
- /v1/validate/identifier new 0.0001 SOL
- /v1/scan/sql new 0.0001 SOL
- /v1/scan/command new 0.0001 SOL
- /v1/scan/url new 0.0001 SOL
- /v1/verify 0.0002 SOL
- /v1/finance/order/risk 0.0005 SOL
- /v1/validate/imports 0.0001 SOL
1 SOL = 10,000 calls • No subscription • Agents pay autonomously
How to pay →Service Wallet — send SOL here to purchase credits
8qXedRydihKEETqU64UXtG2sYZaUhwR4HBFz4Suu27CV
Use your Solana transaction signature as the Bearer token on your first API call. Credits are verified on-chain instantly. Or query GET /v1/pricing for programmatic discovery.