Retrieves a list of supported models from the Azure AI Foundry catalog. This function is useful when a user requests a list of available Foundry models or Foundry Labs projects. It fetches models based on optional filters like whether the model supports free playground usage, the publisher name, ...
AI agents call list_models_from_model_catalog to retrieve information from Azure AI Agent Service MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs only a query/list operation against the Azure AI Foundry model catalog. It returns metadata about available models with optional filtering parameters (free playground availability, publisher, license type). There are no side effects, no data modification, no code execution, and no resource creation or destruction. This is a straightforward Read operation with minimal risk.
From the tool's definition Tool 'retrieves a list of supported models' and 'fetches models based on optional filters' - pure data retrieval with no modification, creation, deletion, or execution capabilities.
Documented attack patterns abuse exactly the kind of access list_models_from_model_catalog gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Azure AI Agent Service MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_models_from_model_catalog:
{
"version": "1",
"default": "deny",
"tools": {
"list_models_from_model_catalog": {}
}
}list_models_from_model_catalog is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieves a list of supported models from the Azure AI Foundry catalog. This function is useful when a user requests a list of available Foundry models or Foundry Labs projects. It fetches models based on optional filters like whether the model supports free playground usage, the publisher name, and the license type. The function will return the list of models with useful fields. Parameters: ctx (Context): The context of the current session. Contains metadata about the request and session. search_for_free_playground (bool, optional): If True, filters models to include only those that can be used for free by users for prototyping. If False, all models will be included regardless of free playground support. Defaults to False. publisher_name (str, optional): A filter to specify the publisher of the models to retrieve. If provided, only models from this publisher will be returned. Defaults to an empty string, meaning no filter is applied. license_name (str, optional): A filter to specify the license type of the models to retrieve. If provided, only models with this license will be returned. Defaults to an empty string, meaning no filter is applied. Returns: str: A JSON-encoded string containing the list of models and their metadata. The list will include model names, inference model names, summaries, and the total count of models retrieved. Usage: Use this function when users inquire about available models from the Azure AI Foundry catalog. It can also be used when filtering models by free playground usage, publisher name, or license type. If user didn't specify free playground or ask for models that support GitHub token, always explain that by default it will show the all the models but some of them would support free playground. Explain to the user that if they want to find models suitable for prototyping and free to use with support for free playground, they can look for models that supports free playground, or look for models that they can use with GitHub token. It is categorised as a Read tool in the Azure AI Agent Service MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Azure AI Agent Service MCP Server MCP server in PolicyLayer and add a rule for list_models_from_model_catalog: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Azure AI Agent Service MCP Server. Nothing to install.
list_models_from_model_catalog is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_models_from_model_catalog rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_models_from_model_catalog. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_models_from_model_catalog is provided by the Azure AI Agent Service MCP Server MCP server (microsoft-foundry/mcp-foundry). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Azure AI Agent Service MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
28 Azure AI Agent Service MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.