azure-ai-contentsafety
Microsoft Azure AI Content Safety Client Library for Python
Decision gist · record as of 2026-08-14
Yes, if you need content moderation and are already using Azure. The package is stable (1.0.0), actively maintained, has no known vulnerabilities, and integrates cleanly with Azure authentication patterns. However, you must have an Azure subscription and Content Safety resource; the client library alone does not provide moderation—it calls a cloud service. Evaluate Azure's pricing and API quotas for your use case before committing.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires an active Azure AI Content Safety resource and API key or Entra ID credentials; the service is cloud-hosted and cannot be used offline.
- Low install friction with a pure-Python wheel distribution.
- Actively maintained as of 2026-08-14 with no known vulnerabilities.
License · maintenance · safety
MIT License (permissive) — MIT License permits unrestricted use, modification, and distribution with minimal restrictions, making it suitable for both open-source and commercial projects.
last release 2023-12-12 (976 days) · last repo commit 2026-08-14 · 5,588 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,053,001 downloads/mo, #4,437 on PyPI
Alternatives
Verify before relying
pip install azure-ai-contentsafety
from azure.core.credentials import AzureKeyCredential
from azure.ai.contentsafety import ContentSafetyClient
endpoint = "https://<subdomain>.cognitiveservices.azure.com/"
credential = AzureKeyCredential("<api_key>")
client = ContentSafetyClient(endpoint, credential)
result = client.analyze_text(text="sample text to analyze")- Whether the service requires an active Azure subscription and incurs per-request costs beyond the client library itself.
- Performance characteristics and latency expectations for text and image analysis at scale.
- Whether custom blocklists persist across sessions or require reinitialization.
What it is and what it does
This package is a Python client for Azure AI Content Safety, a cloud-hosted service that classifies text and images for harmful content. It provides two main clients—ContentSafetyClient for analyzing content and BlocklistClient for managing custom term blocklists—and wraps REST calls to Azure's moderation APIs. The service recognizes four harm categories (hate, sexual, violence, self-harm) and returns severity ratings on a 0–7 scale; text supports full granularity while images return mapped levels (0, 2, 4, 6).
You authenticate using either an API key or Microsoft Entra ID credentials, then call analyze methods to scan text or image URLs. The package handles request serialization and response parsing, abstracting away HTTP details. It's designed for applications that need to filter user-generated or AI-generated content at scale—e.g., moderation workflows, safety compliance, or content filtering in multi-tenant platforms. The blocklist APIs let you supplement the default classifiers with domain-specific terms, useful when the built-in categories don't capture your use case.
Use it for
- Moderate user-generated comments or posts in social platforms or forums before publishing.
- Screen AI-generated text or images for harmful output in chatbot or generative AI applications.
- Build compliance workflows that flag content for manual review based on severity thresholds.
- Create custom blocklists for industry-specific harmful terms (e.g., medical misinformation, financial scams).
- Analyze bulk content archives to identify and categorize harmful material across historical data.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need content moderation and are already using Azure.
The package is stable (1.0.0), actively maintained, has no known vulnerabilities, and integrates cleanly with Azure authentication patterns. However, you must have an Azure subscription and Content Safety resource; the client library alone does not provide moderation—it calls a cloud service. Evaluate Azure's pricing and API quotas for your use case before committing.
Install
azure-ai-contentsafety on PyPI
Before you install
Low install friction with a pure-Python wheel distribution. Actively maintained as of 2026-08-14 with no known vulnerabilities. Depends on three stable, widely-used packages: azure-core, isodate, and typing-extensions.
Requires an active Azure AI Content Safety resource and API key or Entra ID credentials; the service is cloud-hosted and cannot be used offline.
License in practice
MIT License permits unrestricted use, modification, and distribution with minimal restrictions, making it suitable for both open-source and commercial projects.
Quickstart
pip install azure-ai-contentsafety
from azure.core.credentials import AzureKeyCredential
from azure.ai.contentsafety import ContentSafetyClient
endpoint = "https://<subdomain>.cognitiveservices.azure.com/"
credential = AzureKeyCredential("<api_key>")
client = ContentSafetyClient(endpoint, credential)
result = client.analyze_text(text="sample text to analyze")Verify before relying
- Whether the service requires an active Azure subscription and incurs per-request costs beyond the client library itself.
- Performance characteristics and latency expectations for text and image analysis at scale.
- Whether custom blocklists persist across sessions or require reinitialization.
Package facts
| License | MIT License permissive |
| Python support | Supports the current Python release >=3.7 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 3 packagesisodateazure-coretyping-extensions |
| Maintenance | Actively maintained 976 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 1,053,001 / month, #4,437 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableLicense :: OSI Approved :: MIT LicenseProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.7Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9 |
Evidence: azure_ai_contentsafety-1.0.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “content moderation api”
- azure-ai-contentsafetyDetects harmful content in text and images by classifying them across…
- google-cloud-visionProvides a Python client library for Google Cloud Vision API,…
- datarobot-moderationsEnforces content moderation on LLM prompts and responses using…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also azure-ai-textanalytics · azure-ai-documentintelligence · azure-ai-vision-imageanalysis · azure-ai-formrecognizer · azure-ai-language-questionanswering · azure-ai-evaluation · azure-ai-inference · azure-ai-translation-text · azure-ai-language-conversations · detoxify