AI Agent Infrastructure

The quality layer every
AI agent needs

Catch hallucinated packages. Block bad outputs. Cut token waste. Before your agent breaks production.

Read the docs View on GitHub

API Online · <200ms avg

19.7%

of AI-generated packages are hallucinated

USENIX 2025

68%

of multi-agent pipelines contain hallucinations

IBM 2026

<200ms

average firewall check latency

Three checks. One firewall.

Composable, agent-callable services that verify and improve LLM outputs before they cause damage.

Package Validator

19.7% of AI-generated imports don't exist. We check every one against PyPI, npm, crates.io, and Go — in under 200ms.

POST /v1/validate/imports

Hallucination Firewall

Returns PASS, FLAG, or BLOCK for any LLM output. Catches bad packages, dead URLs, malformed citations, and numeric contradictions. Every verdict is SHA-256 certified.

POST /v1/verify

Context Distiller

Trim bloated agent context windows to a token budget. Keep the system prompt, deduplicate, and slice from newest to oldest. Up to 80% compression.

POST /v1/distill

Catch it before it runs

Send AI-generated code. Get a verdict in milliseconds.

request.sh

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"
  }'

response.json

BLOCK

{
  "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
}

PASS FLAG BLOCK

Model Context Protocol

Works with Claude, Warp, Cursor — any MCP client

Drop agent-toolbox into your MCP config and your agent gets three quality tools out of the box. No SDK, no glue code.

validate_imports verify_output distill_context

claude_desktop_config.json

{
  "mcpServers": {
    "agentoolbox": {
      "command": "node",
      "args": ["/path/to/agentoolbox/packages/mcp/dist/index.js"]
    }
  }
}

Start free. Scale on-chain.

Pay per call in SOL when you're ready.

Free

$0 / forever

✓ 10 calls
✓ No auth needed
✓ All endpoints

Get started

Coming soon

Pro

SOL / per call

✓ SOL micropayments
✓ Per-call pricing
✓ Priority queue
✓ SLA

The quality layer every AI agent needs