Microsoft AI Foundry integration

Action security for Microsoft AI Foundry.

Enforce policy around Foundry application tools and workflow boundaries.

Get the Python SDK on PyPITry the local demoRead the documentation

Get the package and source.

Connect the execution boundary.

Attach wrappers to the application’s run, workflow or tool boundaries as documented. This does not intercept every action inside a managed cloud service.

An example to test

A cloud agent selects a profile-export tool with an unexpected destination. Evaluate those final arguments in the application-owned handler.

Illustrative workflow, not a customer deployment or a measured result.

Before connecting live policy

  1. Identify the handler that actually performs the side effect.
  2. Provide trusted identity, purpose and final action arguments.
  3. Configure the tenant’s assigned runtime and keep API credentials server-side.
  4. Test allowed, blocked and unavailable paths before production.

Integration example

Adapt this existing SDK pattern to your application. Names such as the agent, handler and session refer to your own objects. Follow the package documentation for compatible versions and complete setup.

# Install Microsoft AI Foundry support.
python -m pip install "agenticdome-python-sdk[foundry]"

from agenticdome_sdk.microsoft_ai_foundry import AgenticDomeMicrosoftAIFoundryFirewall

firewall = AgenticDomeMicrosoftAIFoundryFirewall()
secure_tool = firewall.secure_tool(tool_name="customer.profile.export")(export_profile)

agenticdome-demo --framework foundry --scenario metadata_exfil

Python demo commands evaluate fixed inputs against a bundled local policy; they do not instantiate the selected framework or prove a live integration. The TypeScript client and OpenClaw runtime plugin need their documented tenant configuration.

Read the integration researchUnderstand runtime verification

See the decision before the action.

Try a local scenario, then bring your workflow to a deployment review. Start with one agent and one tool, and see exactly where the action can be stopped.

Try the local demo Book a deployment review