Skip to main content
Pre-release

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

Alerts

Bundles

Policies

Rules

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:

Inherit from SDKError:

  • HTTPValidationError: Validation Error. Status code 422. Applicable to 18 of 38 methods.*
  • NotFoundError: 404 body: the requested resource (or filtered set) does not exist. Status code 404. Applicable to 9 of 38 methods.*
  • RuleInUseError: 409 body: the rule is still referenced by active policies. Status code 409. 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 the cause attribute.

* 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)

Source distribution for mistralai-agentic-security 0.1.0a6
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)

Table of built distributions (wheels) for mistralai-agentic-security 0.1.0a6
File Interpreter ABI Platform Actions
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 log

Release 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 log

Security 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.

Select from 2 files

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 log

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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page