This release is a pre-release and may not be stable for production use.
mistralai-agentic-security
Summary
Agentic Safety: Agentic Safety Service API
Table of Contents
SDK Installation
The SDK can be installed with uv, pip, or poetry package managers.
uv
uv is a fast Python package installer and resolver, designed as a drop-in replacement for pip and pip-tools. It's recommended for its speed and modern Python tooling capabilities.
uv add git+<UNSET>.git
PIP
PIP is the default package installer for Python, enabling easy installation and management of packages from PyPI via the command line.
pip install git+<UNSET>.git
Poetry
Poetry is a modern tool that simplifies dependency management and package publishing by using a single pyproject.toml file to handle project metadata and dependencies.
poetry add git+<UNSET>.git
Shell and script usage with uv
You can use this SDK in a Python shell with uv and the uvx command that comes with it like so:
uvx --from mistralai-agentic-security python
It's also possible to write a standalone Python script without needing to set up a whole project like so:
#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "mistralai-agentic-security",
# ]
# ///
from mistral.agentic_safety import AgenticSafetyClient
sdk = AgenticSafetyClient(
# SDK arguments
)
# Rest of script here...
Once that is saved to a file, you can run it with uv run script.py where
script.py can be replaced with the actual file name.
IDE Support
PyCharm
Generally, the SDK will work well with most IDEs out of the box. However, when using PyCharm, you can enjoy much better integration with Pydantic by installing an additional plugin.
SDK Example Usage
Example
# Synchronous Example
from mistral.agentic_safety import AgenticSafetyClient, models
with AgenticSafetyClient() as agentic_safety_client:
res = agentic_safety_client.policies.create_policy(name="Block sensitive data", enabled=True, products=[
models.Product.VIBE_WORK,
], rule_ids=[])
# Handle response
print(res)
The same SDK client can also be used to make asynchronous requests by importing asyncio.
# Asynchronous Example
import asyncio
from mistral.agentic_safety import AgenticSafetyClient, models
async def main():
async with AgenticSafetyClient() as agentic_safety_client:
res = await agentic_safety_client.policies.create_policy_async(name="Block sensitive data", enabled=True, products=[
models.Product.VIBE_WORK,
], rule_ids=[])
# Handle response
print(res)
asyncio.run(main())
Authentication
Per-Client Security Schemes
This SDK supports the following security scheme globally:
| Name | Type | Scheme | Environment Variable |
|---|---|---|---|
api_key |
http | HTTP Bearer | MISTRAL_API_KEY |
To authenticate with the API the api_key parameter must be set when initializing the SDK client instance. For example:
from mistral.agentic_safety import AgenticSafetyClient, models
import os
with AgenticSafetyClient(
api_key=os.getenv("MISTRAL_API_KEY", ""),
) as agentic_safety_client:
res = agentic_safety_client.policies.create_policy(name="Block sensitive data", enabled=True, products=[
models.Product.VIBE_WORK,
], rule_ids=[])
# Handle response
print(res)
Available Resources and Operations
Available methods
AgenticSafety
- create_policy - Create Policy
- list_policies - List Policies
- list_policy_authors_editors - List Policy Authors Editors
- batch_get_policies - Batch Get Policies
- count_policies - Count Policies
- get_policy - Get Policy
- update_policy - Update Policy
- delete_policy - Delete Policy
- create_rule - Create Rule
- list_rules - List Rules
- list_rule_authors_editors - List Rule Authors Editors
- batch_get_rules - Batch Get Rules
- count_rules - Count Rules
- get_rule - Get Rule
- update_rule - Update Rule
- delete_rule - Delete Rule
- get_bundle - Get Bundle
- list_alerts - List Alerts
- get_harness_config - Get Harness Config
- make_guardrails_decision - Make Guardrails Decision
Alerts
- list_alerts - List Alerts
Bundles
- get_bundle - Get Bundle
Policies
- create_policy - Create Policy
- list_policies - List Policies
- list_policy_authors_editors - List Policy Authors Editors
- batch_get_policies - Batch Get Policies
- count_policies - Count Policies
- get_policy - Get Policy
- update_policy - Update Policy
- delete_policy - Delete Policy
Rules
- create_rule - Create Rule
- list_rules - List Rules
- list_rule_authors_editors - List Rule Authors Editors
- batch_get_rules - Batch Get Rules
- count_rules - Count Rules
- get_rule - Get Rule
- update_rule - Update Rule
- delete_rule - Delete Rule
Retries
Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.
To change the default retry strategy for a single API call, simply provide a RetryConfig object to the call:
from mistral.agentic_safety import AgenticSafetyClient, models
from mistral.agentic_safety.utils import BackoffStrategy, RetryConfig
with AgenticSafetyClient() as agentic_safety_client:
res = agentic_safety_client.policies.create_policy(name="Block sensitive data", enabled=True, products=[
models.Product.VIBE_WORK,
], rule_ids=[],
RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False))
# Handle response
print(res)
If you'd like to override the default retry strategy for all operations that support retries, you can use the retry_config optional parameter when initializing the SDK:
from mistral.agentic_safety import AgenticSafetyClient, models
from mistral.agentic_safety.utils import BackoffStrategy, RetryConfig
with AgenticSafetyClient(
retry_config=RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False),
) as agentic_safety_client:
res = agentic_safety_client.policies.create_policy(name="Block sensitive data", enabled=True, products=[
models.Product.VIBE_WORK,
], rule_ids=[])
# Handle response
print(res)
Error Handling
SDKError is the base class for all HTTP error responses. It has the following properties:
| Property | Type | Description |
|---|---|---|
err.message |
str |
Error message |
err.status_code |
int |
HTTP response status code eg 404 |
err.headers |
httpx.Headers |
HTTP response headers |
err.body |
str |
HTTP body. Can be empty string if no body is returned. |
err.raw_response |
httpx.Response |
Raw HTTP response |
err.data |
Optional. Some errors may contain structured data. See Error Classes. |
Example
from mistral.agentic_safety import AgenticSafetyClient, errors, models
with AgenticSafetyClient() as agentic_safety_client:
res = None
try:
res = agentic_safety_client.policies.create_policy(name="Block sensitive data", enabled=True, products=[
models.Product.VIBE_WORK,
], rule_ids=[])
# Handle response
print(res)
except errors.SDKError as e:
# The base class for HTTP error responses
print(e.message)
print(e.status_code)
print(e.body)
print(e.headers)
print(e.raw_response)
# Depending on the method different errors may be thrown
if isinstance(e, errors.HTTPValidationError):
print(e.data.detail) # Optional[List[models.ValidationError]]
Error Classes
Primary error:
SDKError: The base class for HTTP error responses.
Less common errors (8)
Network errors:
httpx.RequestError: Base class for request errors.httpx.ConnectError: HTTP client was unable to make a request to a server.httpx.TimeoutException: HTTP request timed out.
Inherit from SDKError:
HTTPValidationError: Validation Error. Status code422. Applicable to 18 of 38 methods.*NotFoundError: 404 body: the requested resource (or filtered set) does not exist. Status code404. Applicable to 9 of 38 methods.*RuleInUseError: 409 body: the rule is still referenced by active policies. Status code409. Applicable to 1 of 38 methods.*ResponseValidationError: Type mismatch between the response data and the expected Pydantic model. Provides access to the Pydantic validation error via thecauseattribute.
* Check the method documentation to see if the error is applicable.
Server Selection
Override Server URL Per-Client
The default server can be overridden globally by passing a URL to the server_url: str optional parameter when initializing the SDK client instance. For example:
from mistral.agentic_safety import AgenticSafetyClient, models
with AgenticSafetyClient(
server_url="https://api.mistral.ai",
) as agentic_safety_client:
res = agentic_safety_client.policies.create_policy(name="Block sensitive data", enabled=True, products=[
models.Product.VIBE_WORK,
], rule_ids=[])
# Handle response
print(res)
Custom HTTP Client
The Python SDK makes API calls using the httpx HTTP library. In order to provide a convenient way to configure timeouts, cookies, proxies, custom headers, and other low-level configuration, you can initialize the SDK client with your own HTTP client instance.
Depending on whether you are using the sync or async version of the SDK, you can pass an instance of HttpClient or AsyncHttpClient respectively, which are Protocol's ensuring that the client has the necessary methods to make API calls.
This allows you to wrap the client with your own custom logic, such as adding custom headers, logging, or error handling, or you can just pass an instance of httpx.Client or httpx.AsyncClient directly.
For example, you could specify a header for every request that this sdk makes as follows:
from mistral.agentic_safety import AgenticSafetyClient
import httpx
http_client = httpx.Client(headers={"x-custom-header": "someValue"})
s = AgenticSafetyClient(client=http_client)
or you could wrap the client with your own custom logic:
from mistral.agentic_safety import AgenticSafetyClient
from mistral.agentic_safety.httpclient import AsyncHttpClient
import httpx
class CustomClient(AsyncHttpClient):
client: AsyncHttpClient
def __init__(self, client: AsyncHttpClient):
self.client = client
async def send(
self,
request: httpx.Request,
*,
stream: bool = False,
auth: Union[
httpx._types.AuthTypes, httpx._client.UseClientDefault, None
] = httpx.USE_CLIENT_DEFAULT,
follow_redirects: Union[
bool, httpx._client.UseClientDefault
] = httpx.USE_CLIENT_DEFAULT,
) -> httpx.Response:
request.headers["Client-Level-Header"] = "added by client"
return await self.client.send(
request, stream=stream, auth=auth, follow_redirects=follow_redirects
)
def build_request(
self,
method: str,
url: httpx._types.URLTypes,
*,
content: Optional[httpx._types.RequestContent] = None,
data: Optional[httpx._types.RequestData] = None,
files: Optional[httpx._types.RequestFiles] = None,
json: Optional[Any] = None,
params: Optional[httpx._types.QueryParamTypes] = None,
headers: Optional[httpx._types.HeaderTypes] = None,
cookies: Optional[httpx._types.CookieTypes] = None,
timeout: Union[
httpx._types.TimeoutTypes, httpx._client.UseClientDefault
] = httpx.USE_CLIENT_DEFAULT,
extensions: Optional[httpx._types.RequestExtensions] = None,
) -> httpx.Request:
return self.client.build_request(
method,
url,
content=content,
data=data,
files=files,
json=json,
params=params,
headers=headers,
cookies=cookies,
timeout=timeout,
extensions=extensions,
)
s = AgenticSafetyClient(async_client=CustomClient(httpx.AsyncClient()))
httpx2 (Pydantic's httpx fork)
httpx2 is Pydantic's maintained fork of httpx. To run this SDK on httpx2, call alias_httpx() at your program's entry point, before importing the SDK, so every import httpx — including the ones inside the SDK — resolves to httpx2:
import httpx2
httpx2.alias_httpx()
from mistral.agentic_safety import AgenticSafetyClient
s = AgenticSafetyClient()
An SDK can also be generated against httpx2 directly, so it depends on the fork instead of httpx, by setting python.httpClientLibrary: httpx2 in gen.yaml.
Resource Management
The AgenticSafetyClient class implements the context manager protocol and registers a finalizer function to close the underlying sync and async HTTPX clients it uses under the hood. This will close HTTP connections, release memory and free up other resources held by the SDK. In short-lived Python programs and notebooks that make a few SDK method calls, resource management may not be a concern. However, in longer-lived programs, it is beneficial to create a single SDK instance via a context manager and reuse it across the application.
from mistral.agentic_safety import AgenticSafetyClient
def main():
with AgenticSafetyClient() as agentic_safety_client:
# Rest of application here...
# Or when using async:
async def amain():
async with AgenticSafetyClient() as agentic_safety_client:
# Rest of application here...
Debugging
You can setup your SDK to emit debug logs for SDK requests and responses.
You can pass your own logger class directly into your SDK.
from mistral.agentic_safety import AgenticSafetyClient
import logging
logging.basicConfig(level=logging.DEBUG)
s = AgenticSafetyClient(debug_logger=logging.getLogger("mistral.agentic_safety"))
You can also enable a default debug logger by setting an environment variable MISTRAL_DEBUG to true.
Metadata
Release files for mistralai-agentic-security 0.1.0a6
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 |
|---|---|---|---|---|
| mistralai_agentic_security-0.1.0a6.tar.gz | 163.0 kB | With provenance | Details for mistralai_agentic_security-0.1.0a6.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mistralai_agentic_security-0.1.0a6-py3-none-any.whl | Python 3 | none | any | Details for mistralai_agentic_security-0.1.0a6-py3-none-any.whl |
Total release size: 437.0 kB
Release files / mistralai_agentic_security-0.1.0a6.tar.gz
| Download URL | mistralai_agentic_security-0.1.0a6.tar.gz |
|---|---|
| Size | 163.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8b28dbacb29352533b1043e0cc43f77ce089e4c68af8f115ebad4572939ac756
|
|
BLAKE2b-256 checksum How to use checksums |
b8650638d2bd307e024c919ce6eab542598419be469479eaa104e790458aae49
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 19, 2026.
Transparency logRelease files / mistralai_agentic_security-0.1.0a6-py3-none-any.whl
| Download URL | mistralai_agentic_security-0.1.0a6-py3-none-any.whl |
|---|---|
| Size | 274.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
36faf230df013fa74ad986b0dd24d641636eeec6892b594507c64c50f88cd22f
|
|
BLAKE2b-256 checksum How to use checksums |
4e50cf009f15f38182baeb59cd45d40a337520b274351ecc1f71db895f694584
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 19, 2026.
Transparency logSecurity for mistralai-agentic-security 0.1.0a6
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.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for mistralai_agentic_security-0.1.0a6.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 19, 2026.
Transparency logA 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.