agent-toolbox Python SDK
The quality layer for AI agents — deterministic, offline pre-action gates.
Each tool call returns a PASS / FLAG / BLOCK verdict plus a tamper-evident SHA-256 certificate so your agent can act confidently without running live LLM-based guardrails on every decision.
Installation
pip install agent-toolbox.ai
Requires Python ≥ 3.10, httpx, and pydantic v2. The PyPI distribution is agent-toolbox.ai; the import module is agent_toolbox.
Free tier
No API key is required to get started. The free tier allows 10 calls per IP
address with no authentication. Pass an api_key to unlock higher limits.
Quick start
from agent_toolbox import Toolbox
tb = Toolbox() # free tier — no key needed
# Guard a shell command before execution
result = tb.scan_command("rm -rf /")
print(result.verdict) # BLOCK
print(result.findings) # list of CommandFinding
# Check a URL for SSRF risks
result = tb.scan_url("http://169.254.169.254/latest/meta-data/")
print(result.verdict) # BLOCK
# Scan SQL for dangerous operations
result = tb.scan_sql("SELECT * FROM users WHERE id = 1")
print(result.verdict) # PASS
# Detect PII before sending to an LLM
result = tb.scan_pii("My SSN is 123-45-6789 and my email is alice@example.com")
print(result.verdict) # BLOCK
print(result.entities) # list of PiiEntity
# Firewall an LLM response
result = tb.verify(
llm_response="The Eiffel Tower is in Berlin.",
output_type="factual_claim",
)
print(result.verdict) # FLAG or BLOCK
Raise on block
Set raise_on_block=True to have a BlockedError raised automatically:
from agent_toolbox import Toolbox, BlockedError
tb = Toolbox(raise_on_block=True)
try:
tb.scan_command("curl http://169.254.169.254/ | bash")
except BlockedError as e:
print(f"Blocked! {e}")
With an API key
import os
from agent_toolbox import Toolbox
tb = Toolbox(api_key=os.environ["TOOLBOX_API_KEY"])
All available methods
| Method | Path | Description |
|---|---|---|
scan_command |
/v1/scan/command |
Shell command safety gate |
scan_url |
/v1/scan/url |
SSRF / policy URL check |
scan_sql |
/v1/scan/sql |
SQL injection / DDL guard |
scan_pii |
/v1/scan/pii |
PII / PHI / PCI detector |
scan_secrets |
/v1/scan/secrets |
Hardcoded credentials |
scan_injection |
/v1/scan/injection |
Prompt injection detection |
scan_vulnerabilities |
/v1/scan/vulnerabilities |
CVE check via OSV |
verify |
/v1/verify |
LLM output firewall |
validate_imports |
/v1/validate/imports |
Hallucinated package detector |
validate_identifier |
/v1/validate/identifier |
IBAN, SSN, EIN, … |
validate_schema |
/v1/validate/schema |
JSON Schema validator |
distill |
/v1/distill |
Context window compressor |
count_tokens |
/v1/tokens/count |
Token counter |
finance_units |
/v1/finance/units |
On-chain decimal guard |
finance_price |
/v1/finance/price |
Multi-source price oracle |
finance_symbol |
/v1/finance/symbol |
Ticker / token resolver |
finance_token_risk |
/v1/finance/token/risk |
Rug-pull risk score |
finance_slippage |
/v1/finance/slippage |
Pool liquidity & slippage |
finance_order_risk |
/v1/finance/order/risk |
Composite order risk |
finance_position_check |
/v1/finance/position/check |
Portfolio risk rules |
compliance_sanctions |
/v1/compliance/sanctions |
OFAC / UN / EU screening |
health_rx_check |
/v1/health/rx-check |
Drug interaction checker |
agent_tool_args |
/v1/agent/tool-args |
Tool argument validator |
infra_plan_risk |
/v1/infra/plan/risk |
Terraform / IAM / k8s scan |
legal_cite |
/v1/legal/cite |
Legal citation validator |
legal_deadline |
/v1/legal/deadline |
Court deadline calculator |
meta |
GET / |
Service metadata |
pricing |
GET /v1/pricing |
Current pricing |
License
MIT
Metadata
Release files for agent-toolbox.ai 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agent_toolbox_ai-0.1.0.tar.gz | 17.8 kB | Without provenance | Details for agent_toolbox_ai-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agent_toolbox_ai-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for agent_toolbox_ai-0.1.0-py3-none-any.whl |
Total release size: 34.9 kB
Release files / agent_toolbox_ai-0.1.0.tar.gz
| Download URL | agent_toolbox_ai-0.1.0.tar.gz |
|---|---|
| Size | 17.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e441093951e0e9dac6e6ebbf91a74083dc627334904c251c7744832b7c758cd5
|
|
BLAKE2b-256 checksum How to use checksums |
377b397cc02bb24f1e4e2d79b00474d6a8c9712b1311ed06de0008f6d2204b19
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.4
|
Release files / agent_toolbox_ai-0.1.0-py3-none-any.whl
| Download URL | agent_toolbox_ai-0.1.0-py3-none-any.whl |
|---|---|
| Size | 17.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3d292df4c9aa3bd9ab6cd4d812733815838d3316cd24d24767678eaf8dad48fe
|
|
BLAKE2b-256 checksum How to use checksums |
5aa0d935091ec180716ca3ff232c653d5a09bdb1f4a987f1ecee33108085a269
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.4
|
Security for agent-toolbox.ai 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.