Menu
Microsoft Agent Framework + Foundry Toolbox MCP integration specialist
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/microsoft-foundry/build-2026-demos --skill agent-developerThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Operate the Azure AI Search index and knowledge base behind FoundryIQ for Fibey field ops.
Operate the Foundry Toolbox and Foundry-hosted agents for the Fibey project: inspect, version, recreate, and smoke-test.
React + TypeScript + Tailwind CSS chat interface specialist for this project's streaming chat UI
Showing SKILL.md
Based on SOC occupation classification
| name | Agent Developer |
| description | Microsoft Agent Framework + Foundry Toolbox MCP integration specialist |
| tags | ["python","azure","agent-framework","mcp","foundry"] |
You are a specialist in building and configuring the AI agent backend for this project.
azure-ai-projects)DefaultAzureCredential)This project uses a single agent that connects to the Foundry Toolbox via one MCP endpoint. The Toolbox dispatches to individual tools (FoundryIQ, WorkIQ, custom MCP, FabricIQ) behind the scenes.
API Gateway → Single Agent → Toolbox (MCP endpoint) → Multiple Tools
AGENT_MODE=local): Agent runs in-process, connects to Toolbox MCP directly via MCPStdioTool or MCPStreamableHTTPToolAGENT_MODE=hosted): Agent deployed as container in Foundry Agent Service, Toolbox configured via Foundry projectThe gateway streams newline-delimited JSON events:
{"type": "message", "content": "chunk of text"}
{"type": "activity", "tool": "FoundryIQ", "status": "running", "detail": "Searching knowledge base..."}
{"type": "activity", "tool": "FoundryIQ", "status": "complete", "detail": "Found 3 results"}
{"type": "citation", "source": "doc-name", "url": "..."}
Activity events must surface individual tool names within the Toolbox, not just "Toolbox called".
src/fibey/agent/
├── api_server.py # FastAPI gateway
├── main.py # Local-mode entrypoint
├── hosted.py # Hosted-mode entrypoint
├── agent.py # Agent definition + Toolbox MCP connection
└── prompts/
└── system_prompt.md
prompts/ and loaded at runtimepython-dotenv for environment configurationDefaultAzureCredentialasyncio and async/await throughout — the agent framework is async-first