AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

microsoft-foundry

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent, managed harness agent, Copilot harness, voice agent, create/update/invoke/evaluate agent, add tool to agent, agent insights, batch/continuous eval, continuous monitoring, agent CI/CD, optimize/improve prompt, optimize agent instructions, Agent Optimizer, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

Original source
microsoft
License
MIT
Pinned revision
3f5b461b2314e01c400564051e92469114c5b68f

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

This skill also requires local files or dependencies. Remote reading alone may not be enough.

Ask your assistant

Use Agentic Memory skills to read microsoft--microsoft-foundry at revision 3f5b461b2314e01c400564051e92469114c5b68f, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 151

foundry-agent/create/references/tools/managed-harness-agent/tool-mcp.md

MCP

Connect a Managed Harness Agent directly to a remote MCP server.

Public server:

tools:
  - type: mcp
    server_label: learn
    server_url: https://learn.microsoft.com/api/mcp
    require_approval: always

Authenticated server:

tools:
  - type: mcp
    server_label: internal
    server_url: https://tools.example.com/mcp
    project_connection_id: <connection-name-or-id>
    require_approval: always
    allowed_tools:
      - search

server_label and server_url are required. Keep require_approval: always unless the user explicitly trusts the server. Use allowed_tools to restrict exposure.

Use a connection supplied by the user or already referenced by the Agent. Create one only when explicitly requested. Select the matching azd connection flow:

Follow only the connection-creation and validation sections; do not create a Toolbox unless explicitly requested.

Agent Service requires a remotely reachable MCP endpoint. Do not place literal credentials in headers or azure.yaml.

A generic MCP URL remains a generic MCP workflow. Do not infer that it is a Foundry Toolbox or automatically create a Toolbox connection merely because its URL contains /toolboxes/. When the user explicitly requests a Foundry Toolbox, follow Toolbox.