// SCAN REPORT

Azure AI Agent Service MCP Server

28 tools. 10 can modify or destroy data without limits.

10 write tools that can modify data. Rate limits recommended.

Last updated: 11 Jun 2026

10 can modify or destroy data

18 read-only

28 tools total

Community server · catalogue entry verified 11/06/2026

How to control Azure AI Agent Service MCP Server ↓

TOOL MAP

What Azure AI Agent Service MCP Server exposes to your agents

Read (18) Write / Execute (10) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Azure AI Agent Service MCP Server tools

Execute · High deploy_model_on_ai_services Model deployment on cloud services is an Execute-category action because it runs/triggers infrastructure operations whose effects depend on specified arguments. Execute · High execute_dynamic_swagger_action This tool permits execution of arbitrary API operations from a Swagger specification with agent-controlled parameters. Execute · Medium run_agent_eval This tool executes evaluation logic on agent data based on specified evaluator types. Execute · Medium run_text_eval Despite the empty description reducing confidence, the tool name 'run_text_eval' and its position among execution-oriented siblings (execute_dynamic_swagger_action, agent_query_and_evaluate) indicates it executes evaluat

10 of Azure AI Agent Service MCP Server's 28 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Azure AI Agent Service MCP Server

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. These are the rules we recommend:

Rate limit write operations

{
  "create_azure_ai_services_account": {
    "limits": [
      {
        "counter": "create_azure_ai_services_account_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "fetch_finetuning_status": {
    "limits": [
      {
        "counter": "fetch_finetuning_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Azure AI Agent Service MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON AZURE AI AGENT SERVICE →

Free to start. No card required.

FULL CATALOGUE

All 28 Azure AI Agent Service MCP Server tools

EXECUTE 7 tools

Execute deploy_model_on_ai_services deploy_model_on_ai_services Execute execute_dynamic_swagger_action Execute a dynamically generated tool from the Swagger specification. Args: tool_name: Name of Execute run_agent_eval Run agent evaluation on agent data. Accepts both plain text and JSON strings. Parameters: - evaluator Execute run_text_eval run_text_eval Execute agent_query_and_evaluate Query an agent and evaluate its response in a single operation. Parameters: - agent_id: ID of the age Execute query_default_agent Send a query to the default configured Azure AI Agent. Parameters: - query: Text query to send to the Execute connect_agent Connect to a specific Azure AI Agent and run a query. Parameters: - agent_id: ID of the agent to conn

WRITE 3 tools

Write create_azure_ai_services_account create_azure_ai_services_account Write create_foundry_project create_foundry_project Write update_model_deployment update_model_deployment

READ 18 tools

Read fetch_finetuning_status Fetches the status of a fine-tuning job using Azure OpenAI API. Parameters: - job_id: The ID of the Read format_evaluation_report Format evaluation results into a readable report with metrics and Studio URL. Parameters: - evaluatio Read get_agent_evaluator_requirements Get the required input fields for a specific agent evaluator or all agent evaluators. Parameters: - e Read get_finetuning_job_events MCP-compatible function to retrieve all events for a specific finetuning job. It also returns the billing Read get_finetuning_metrics Retrieves fine-tuning metrics if the job has succeeded. Calls fetch_finetuning_status to confirm job compl Read get_model_details_and_code_samples Retrieves detailed information for a specific model from the Azure AI Foundry catalog. This function is u Read get_model_quotas Get model quotas for a specific Azure location. Args: subscription_id: The ID of the Azure subscr Read get_prototyping_instructions_for_github_and_labs Provides comprehensive instructions and setup guidance for starting to work with models from Azure AI Foundry Read get_text_evaluator_requirements Get the required input fields for a specific text evaluator or all text evaluators. Parameters: - eva Read list_agent_evaluators Returns a list of available agent evaluator names for evaluating agent behaviors. Read list_agents List available agents in the Azure AI Agent Service. Read list_azure_ai_foundry_labs_projects Retrieves a list of state-of-the-art AI models from Microsoft Research available in Azure AI Foundry Labs. Read list_deployments_from_azure_ai_services Retrieves a list of deployments from Azure AI Services. This function is used when a user requests inform Read list_dynamic_swagger_tools list_dynamic_swagger_tools Read list_finetuning_files list_finetuning_files Read list_finetuning_jobs MCP-compatible function to list all finetuning jobs using Azure OpenAI API. Returns: List of d Read list_models_from_model_catalog Retrieves a list of supported models from the Azure AI Foundry catalog. This function is useful when a us Read list_text_evaluators Returns a list of available text evaluator names for evaluating text outputs.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Azure AI Agent Service MCP Server

How do I prevent bulk modifications through Azure AI Agent Service MCP Server? +

The Azure AI Agent Service MCP Server server has 3 write tools including create_azure_ai_services_account, create_foundry_project, update_model_deployment. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Azure AI Agent Service MCP Server.

How many tools does the Azure AI Agent Service MCP Server MCP server expose? +

28 tools across 3 categories: Execute, Read, Write. 18 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Azure AI Agent Service MCP Server? +

Register the Azure AI Agent Service MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Azure AI Agent Service MCP Server tool call.

Deterministic rules across all 28 Azure AI Agent Service MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AZURE AI AGENT SERVICE →

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.