Loading source
Pulling the file list, source metadata, and syntax-aware rendering for this listing.
Source from repo
Deploy, evaluate, and manage AI agents end-to-end on Microsoft Azure AI Foundry
Files
Skill
Size
Entrypoint
Format
Open file
Syntax-highlighted preview of this file as included in the skill package.
foundry-agent/create/create-prompt.md
1# Create Prompt Agent23Create and manage prompt agents in Azure Foundry Agent Service using MCP tools or Python SDK. For hosted agents (container-based), see [create-hosted.md](create-hosted.md).45## Quick Reference67| Property | Value |8|----------|-------|9| **Agent Type** | Prompt (`kind: "prompt"`) |10| **Primary Tool** | Foundry MCP server (`foundry_agents_*`) |11| **Fallback SDK** | `azure-ai-projects` v2.x preview |12| **Auth** | `DefaultAzureCredential` / `az login` |1314## Workflow1516```17User Request (create/list/get/update/delete agent)18│19▼20Step 1: Resolve project context (endpoint + credentials)21│22▼23Step 2: Try MCP tool for the operation24│ ├─ ✅ MCP available → Execute via MCP tool → Done25│ └─ ❌ MCP unavailable → Continue to Step 326│27▼28Step 3: Fall back to SDK29│ Read references/sdk-operations.md for code30│31▼32Step 4: Execute and confirm result33```3435### Step 1: Resolve Project Context3637The user needs a Foundry project endpoint. Check for:38391. `PROJECT_ENDPOINT` environment variable402. Ask the user for their project endpoint413. Use `foundry_resource_get` MCP tool to discover it4243Endpoint format: `https://<resource>.services.ai.azure.com/api/projects/<project>`4445### Step 2: Create Agent (MCP — Preferred)4647For a **prompt agent**:48- Provide: agent name, model deployment name, instructions49- Optional: tools (code interpreter, file search, function calling, web search, Bing grounding, memory)5051For a **workflow**:52- Workflows are created in the Foundry portal visual builder53- Use MCP to create the individual agents that participate in the workflow54- Direct the user to the Foundry portal for workflow assembly5556### Step 3: SDK Fallback5758If MCP tools are unavailable, use the `azure-ai-projects` SDK:59- See [SDK Operations](references/sdk-operations.md) for create, list, update, delete code samples60- See [Agent Tools](references/agent-tools.md) for adding tools to agents6162### Step 4: Add Tools (Optional)6364> ⚠️ **MANDATORY:** Before configuring any tool, **read its reference documentation** linked below to understand prerequisites, required parameters, and setup steps. Do not attempt to add a tool without first reviewing its reference.6566| Tool Category | Reference |67|---------------|-----------|68| Code Interpreter, Function Calling | [Simple Tools](references/agent-tools.md) |69| File Search (requires vector store) | [File Search](references/tool-file-search.md) |70| Web Search (default, no setup needed) | [Web Search](references/tool-web-search.md) |71| Bing Grounding (explicit request only) | [Bing Grounding](references/tool-bing-grounding.md) |72| Azure AI Search (private data) | [Azure AI Search](references/tool-azure-ai-search.md) |73| MCP Servers | [MCP Tool](references/tool-mcp.md) |74| Memory (persistent across sessions) | [Memory](references/tool-memory.md) |75| Connections (for tools that need them) | [Project Connections](../../project/connections.md) |7677> ⚠️ **Web Search Default:** Use `WebSearchPreviewTool` for web search. Only use `BingGroundingAgentTool` when the user explicitly requests Bing Grounding.7879## Error Handling8081| Error | Cause | Resolution |82|-------|-------|------------|83| Agent creation fails | Missing model deployment | Deploy a model first via `foundry_models_deploy` or portal |84| MCP tool not found | MCP server not running | Fall back to SDK — see [SDK Operations](references/sdk-operations.md) |85| Permission denied | Insufficient RBAC | Need `Foundry User` role on the project |86| Agent name conflict | Name already exists | Use a unique name or update the existing agent |87| Tool not available | Tool not configured for project | Verify tool prerequisites (e.g., Bing resource for grounding) |88| SDK version mismatch | Using 1.x instead of 2.x | Install `azure-ai-projects --pre` for v2.x preview |89| Tenant mismatch | MCP token tenant differs from resource tenant | Fall back to SDK — `DefaultAzureCredential` resolves the correct tenant |90