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/insights/references/tool-contract.md

Agent Insights MCP Contract

Discover agent_insights_get through the Azure MCP foundry tool. It resolves the named agent's existing monitor and returns one unchanged page of generated insights. It does not generate fresh findings.

Inputs

| Parameter | Required | Meaning | |-----------|----------|---------| | projectEndpoint | Yes | Foundry project URL: https://<account>.services.ai.azure.com/api/projects/<project>; use the actual endpoint for the target cloud, not a portal URL | | agentName | Yes | Exact agent name, not a monitor ID or name:version | | category | No | Supported category filter; omit unless requested | | severity | No | Supported severity filter, for example low, medium, high | | status | No | active, resolved, or ignored; open is invalid | | includeDetails | No | Expanded evidence/remediation; service default false, workflow default true | | order | No | Creation-time order: asc or desc; default desc | | after | No | Previous page's last_id when has_more is true | | limit | No | Page size 1-100; service default 20, workflow default 100 |

Use only schema-supported parameters. Do not translate a request for fresh analysis into this retrieval call.

// Azure MCP router; use the host's discovered name for the foundry tool.
foundry({
  intent: "Read generated agent insights with evidence",
  command: "agent_insights_get",
  parameters: {
    projectEndpoint: "https://<account>.services.ai.azure.com/api/projects/<project>",
    agentName: "<agent-name>",
    includeDetails: true,
    order: "desc",
    limit: 100
  }
});

For a directly exposed agent_insights_get tool, pass the inputs without the router wrapper. For subsequent pages, add after and retain the other inputs. Honor requested filters and total-result limits as described in the workflow.

Output

Pagination fields are snake_case:

{
  "data": [
    {
      "id": "insight_example",
      "agent_name": "example-agent",
      "agent_version": "1",
      "title": "Handle tool failures",
      "category": "quality",
      "severity": "high",
      "status": "active",
      "description": "A generated finding."
    }
  ],
  "first_id": "insight_example",
  "last_id": "insight_example",
  "has_more": true
}

This abbreviated example omits details. With includeDetails: true, inspect available details.highlighted_traces, details.linked_traces, and details.recommended_actions.proposed_fix. Preserve returned trace IDs and evidence; do not manufacture missing fields. Proposed fixes are recommendations, not permission to modify code or prompts.

Errors

| Result | Required handling | |--------|-------------------| | Successful empty data, has_more: false | Report no matching generated insights; do not infer health | | No monitor found | Explain that an existing monitor is required; do not create one | | Tool unavailable | Stop and report MCP availability/discovery failure | | Invalid argument/filter | Show the actionable error and correct only supported inputs; do not silently drop filters | | Authentication/authorization failure | Report the failure; do not change permissions | | Backend/network failure | Report failure, or explicitly partial results if earlier pages succeeded | | Malformed page or missing/repeated continuation cursor | Stop; mark retrieval incomplete rather than looping or returning false success |