// MCP TOOL REFERENCE

connect_agent

ServerAzure AI Agent Service MCP Server
CategoryExecute

WHAT IT DOES

What connect_agent does on Azure AI Agent Service MCP Server

AI agents invoke connect_agent to trigger actions in Azure AI Agent Service MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

THE RISK

High Risk

Why connect_agent needs a policy

This tool actively connects to an external Azure AI Agent and executes a query against it, triggering real-time processing by an external AI system. The effects depend on the query arguments passed and the agent's capabilities (which may include Azure AI Search, Bing Web Grounding, and other tools).

From the tool's definition Connect to a specific Azure AI Agent and run a query

Documented attack patterns abuse exactly the kind of access connect_agent gives an agent:

POLICY

How to control connect_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 connect_agent:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "connect_agent": {
      "limits": [
        {
          "counter": "connect_agent_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

connect_agent stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Azure AI Agent Service MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Azure AI Agent Service MCP Server 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: Execute run_agent_eval Run agent evaluation on agent data. Accepts both plain text and JSON strings. Paramet Execute run_text_eval run_text_eval Execute agent_query_and_evaluate Query an agent and evaluate its response in a single operation. Parameters: - age Execute query_default_agent Send a query to the default configured Azure AI Agent. Parameters: - query: Text Write create_azure_ai_services_account create_azure_ai_services_account Write create_foundry_project create_foundry_project

All 28 Azure AI Agent Service MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Azure AI Agent Service MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about connect_agent

What does the connect_agent tool do? +

Connect to a specific Azure AI Agent and run a query. Parameters: - agent_id: ID of the agent to connect to - query: Text query to send to the agent Returns a dict with the agent's response and thread/run IDs for potential evaluation. It is categorised as a Execute tool in the Azure AI Agent Service MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on connect_agent? +

Register the Azure AI Agent Service MCP Server MCP server in PolicyLayer and add a rule for connect_agent: 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.

What risk level is connect_agent? +

connect_agent is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit connect_agent? +

Yes. Add a rate_limit block to the connect_agent 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.

How do I block connect_agent completely? +

Set action: deny in the PolicyLayer policy for connect_agent. 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.

What MCP server provides connect_agent? +

connect_agent 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.

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

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.

CHECK YOUR STACK →

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.