[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69B3YKJ8HA5H9C06HD2FKFN":3,"skill-same:01M69B3YKJ8HA5H9C06HD2FKFN":93},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M69B3YKJ8HA5H9C06HD2FKFN","entra-agent-id",null,"Microsoft Entra Agent ID (preview) for creating OAuth2-capable AI agent identities via Microsoft Graph beta API.\nCovers Agent Identity Blueprints, BlueprintPrincipals, Agent Identities, required permissions, sponsors, and Workload Identity Federation.\nIncludes Microsoft Entra SDK for AgentID (containerized sidecar) for polyglot agent authentication (Docker\u002FKubernetes), 3P agent integration, autonomous and interactive agent patterns.\nTriggers: \"agent identity\", \"agent id\", \"Agent Identity Blueprint\", \"BlueprintPrincipal\", \"entra agent\", \"agent identity provisioning\", \"Graph agent identity\", \"entra sidecar\", \"agent id sidecar\", \"auth sidecar\", \"3P agent\", \"third-party agent identity\", \"polyglot agent auth\".","microsoft\u002Fskills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69AJYYW4E1RMSYCQDJ4FJSH",3202,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fentra-agent-id\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,9,47,48,49],"agent id","id","entra agent id","graph","for","preview","microsoft graph","patterns","Blueprint","autonomous","api","federation","beta","docker","permissions","agent identity","authentication","workload","identity","auth","ai agent","sdk","kubernetes","2026-11-10 10:12:30",false,"---\nname: entra-agent-id\ndescription: |\n  Microsoft Entra Agent ID (preview) for creating OAuth2-capable AI agent identities via Microsoft Graph beta API.\n  Covers Agent Identity Blueprints, BlueprintPrincipals, Agent Identities, required permissions, sponsors, and Workload Identity Federation.\n  Includes Microsoft Entra SDK for AgentID (containerized sidecar) for polyglot agent authentication (Docker\u002FKubernetes), 3P agent integration, autonomous and interactive agent patterns.\n  Triggers: \"agent identity\", \"agent id\", \"Agent Identity Blueprint\", \"BlueprintPrincipal\", \"entra agent\", \"agent identity provisioning\", \"Graph agent identity\", \"entra sidecar\", \"agent id sidecar\", \"auth sidecar\", \"3P agent\", \"third-party agent identity\", \"polyglot agent auth\".\n---\n\n# Microsoft Entra Agent ID\n\nCreate and manage OAuth2-capable identities for AI agents using Microsoft Graph beta API.\n\n> **Preview API** — All Agent Identity endpoints are under `\u002Fbeta` only. Not available in `\u002Fv1.0`.\n\n## Before You Start\n\nSearch `microsoft-docs` MCP for the latest Agent ID documentation:\n- Query: \"Microsoft Entra agent identity setup\"\n- Verify: API parameters match current preview behavior\n\n## Conceptual Model\n\n```\nAgent Identity Blueprint (application)        ← one per agent type\u002Fproject\n  └── BlueprintPrincipal (service principal)   ← MUST be created explicitly\n        ├── Agent Identity (SP): agent-1       ← one per agent instance\n        ├── Agent Identity (SP): agent-2\n        └── Agent Identity (SP): agent-3\n```\n\n## Prerequisites\n\n### PowerShell (recommended for interactive setup)\n\n```powershell\n# Requires PowerShell 7+\nInstall-Module Microsoft.Graph.Beta.Applications -Scope CurrentUser -Force\n```\n\n### Python (for programmatic provisioning)\n\n```bash\npip install azure-identity requests\n```\n\n### Required Entra Roles\n\nOne of: **Agent Identity Developer**, **Agent Identity Administrator**, or **Application Administrator**.\n\n## Environment Variables\n\n```bash\nAZURE_TENANT_ID=\u003Cyour-tenant-id>\nAZURE_CLIENT_ID=\u003Capp-registration-client-id>\nAZURE_CLIENT_SECRET=\u003Capp-registration-secret>\n```\n\n## Authentication\n\n> **⚠️ `DefaultAzureCredential` is NOT supported.** Azure CLI tokens contain\n> `Directory.AccessAsUser.All`, which Agent Identity APIs explicitly reject (403).\n> You MUST use a dedicated app registration with `client_credentials` flow or\n> connect via `Connect-MgGraph` with explicit delegated scopes.\n\n### PowerShell (delegated permissions)\n\n```powershell\nConnect-MgGraph -Scopes @(\n    \"AgentIdentityBlueprint.Create\",\n    \"AgentIdentityBlueprint.ReadWrite.All\",\n    \"AgentIdentityBlueprintPrincipal.Create\",\n    \"User.Read\"\n)\nSet-MgRequestContext -ApiVersion beta\n\n$currentUser = (Get-MgContext).Account\n$userId = (Get-MgUser -UserId $currentUser).Id\n```\n\n### Python (application permissions)\n\n```python\nimport os\nimport requests\nfrom azure.identity import ClientSecretCredential\n\ncredential = ClientSecretCredential(\n    tenant_id=os.environ[\"AZURE_TENANT_ID\"],\n    client_id=os.environ[\"AZURE_CLIENT_ID\"],\n    client_secret=os.environ[\"AZURE_CLIENT_SECRET\"],\n)\ntoken = credential.get_token(\"https:\u002F\u002Fgraph.microsoft.com\u002F.default\")\n\nGRAPH = \"https:\u002F\u002Fgraph.microsoft.com\u002Fbeta\"\nheaders = {\n    \"Authorization\": f\"Bearer {token.token}\",\n    \"Content-Type\": \"application\u002Fjson\",\n    \"OData-Version\": \"4.0\",  # Required for all Agent Identity API calls\n}\n```\n\n## Core Workflow\n\n### Step 1: Create Agent Identity Blueprint\n\nSponsors are required and **must be User objects** — ServicePrincipals and Groups are rejected.\n\n```python\nimport subprocess\n\n# Get sponsor user ID (client_credentials has no user context, so use az CLI)\nresult = subprocess.run(\n    [\"az\", \"ad\", \"signed-in-user\", \"show\", \"--query\", \"id\", \"-o\", \"tsv\"],\n    capture_output=True, text=True, check=True,\n)\nuser_id = result.stdout.strip()\n\nblueprint_body = {\n    \"@odata.type\": \"Microsoft.Graph.AgentIdentityBlueprint\",\n    \"displayName\": \"My Agent Blueprint\",\n    \"sponsors@odata.bind\": [\n        f\"https:\u002F\u002Fgraph.microsoft.com\u002Fbeta\u002Fusers\u002F{user_id}\"\n    ],\n}\nresp = requests.post(f\"{GRAPH}\u002Fapplications\", headers=headers, json=blueprint_body)\nresp.raise_for_status()\n\nblueprint = resp.json()\napp_id = blueprint[\"appId\"]\nblueprint_obj_id = blueprint[\"id\"]\n```\n\n### Step 2: Create BlueprintPrincipal\n\n> **This step is mandatory.** Creating a Blueprint does NOT auto-create its\n> service principal. Without this, Agent Identity creation fails with:\n> `400: The Agent Blueprint Principal for the Agent Blueprint does not exist.`\n\n```python\nsp_body = {\n    \"@odata.type\": \"Microsoft.Graph.AgentIdentityBlueprintPrincipal\",\n    \"appId\": app_id,\n}\nresp = requests.post(f\"{GRAPH}\u002FservicePrincipals\", headers=headers, json=sp_body)\nresp.raise_for_status()\n```\n\nIf implementing idempotent scripts, check for and create the BlueprintPrincipal\neven when the Blueprint already exists (a previous run may have created the Blueprint\nbut crashed before creating the SP).\n\n### Step 3: Create Agent Identities\n\n```python\nagent_body = {\n    \"@odata.type\": \"Microsoft.Graph.AgentIdentity\",\n    \"displayName\": \"my-agent-instance-1\",\n    \"agentIdentityBlueprintId\": app_id,\n    \"sponsors@odata.bind\": [\n        f\"https:\u002F\u002Fgraph.microsoft.com\u002Fbeta\u002Fusers\u002F{user_id}\"\n    ],\n}\nresp = requests.post(f\"{GRAPH}\u002FservicePrincipals\", headers=headers, json=agent_body)\nresp.raise_for_status()\nagent = resp.json()\n```\n\n## API Reference\n\n| Operation | Method | Endpoint | OData Type |\n|-----------|--------|----------|------------|\n| Create Blueprint | `POST` | `\u002Fapplications` | `Microsoft.Graph.AgentIdentityBlueprint` |\n| Create BlueprintPrincipal | `POST` | `\u002FservicePrincipals` | `Microsoft.Graph.AgentIdentityBlueprintPrincipal` |\n| Create Agent Identity | `POST` | `\u002FservicePrincipals` | `Microsoft.Graph.AgentIdentity` |\n| List Agent Identities | `GET` | `\u002FservicePrincipals?$filter=...` | — |\n| Delete Agent Identity | `DELETE` | `\u002FservicePrincipals\u002F{id}` | — |\n| Delete Blueprint | `DELETE` | `\u002Fapplications\u002F{id}` | — |\n\nAll endpoints use base URL: `https:\u002F\u002Fgraph.microsoft.com\u002Fbeta`\n\n## Required Permissions\n\n| Permission | Purpose |\n|-----------|---------|\n| `Application.ReadWrite.All` | Blueprint CRUD (application objects) |\n| `AgentIdentityBlueprint.Create` | Create new Blueprints |\n| `AgentIdentityBlueprint.ReadWrite.All` | Read\u002Fupdate Blueprints |\n| `AgentIdentityBlueprintPrincipal.Create` | Create BlueprintPrincipals |\n| `AgentIdentity.Create.All` | Create Agent Identities |\n| `AgentIdentity.ReadWrite.All` | Read\u002Fupdate Agent Identities |\n\nThere are **18 Agent Identity-specific** Graph application permissions. Discover all:\n```bash\naz ad sp show --id 00000003-0000-0000-c000-000000000000 \\\n  --query \"appRoles[?contains(value, 'AgentIdentity')].{id:id, value:value}\" -o json\n```\n\nGrant admin consent (required for application permissions):\n```bash\naz ad app permission admin-consent --id \u003Cclient-id>\n```\n\n> Admin consent may fail with 404 if the service principal hasn't replicated. Retry with 10–40s backoff.\n\n## Cleanup\n\n```python\n# Delete Agent Identity\nrequests.delete(f\"{GRAPH}\u002FservicePrincipals\u002F{agent['id']}\", headers=headers)\n\n# Delete BlueprintPrincipal (get SP ID first)\nsps = requests.get(\n    f\"{GRAPH}\u002FservicePrincipals?$filter=appId eq '{app_id}'\",\n    headers=headers,\n).json()\nfor sp in sps.get(\"value\", []):\n    requests.delete(f\"{GRAPH}\u002FservicePrincipals\u002F{sp['id']}\", headers=headers)\n\n# Delete Blueprint\nrequests.delete(f\"{GRAPH}\u002Fapplications\u002F{blueprint_obj_id}\", headers=headers)\n```\n\n## Best Practices\n\n1. **Always create BlueprintPrincipal after Blueprint** — not auto-created; implement idempotent checks on both\n2. **Use User objects as sponsors** — ServicePrincipals and Groups are rejected\n3. **Handle permission propagation delays** — after admin consent, wait 30–120s; retry with backoff on 403\n4. **Include `OData-Version: 4.0` header** on every Graph request\n5. **Use Workload Identity Federation for production auth** — for local dev, use a client secret on the Blueprint (see [references\u002Foauth2-token-flow.md](references\u002Foauth2-token-flow.md))\n6. **Set `identifierUris` on Blueprint** before using OAuth2 scoping (`api:\u002F\u002F{app-id}`)\n7. **Never use Azure CLI tokens** for API calls — they contain `Directory.AccessAsUser.All` which is hard-rejected\n8. **Check for existing resources** before creating — implement idempotent provisioning\n\n## References\n\n| File | Contents |\n|------|----------|\n| [references\u002Foauth2-token-flow.md](references\u002Foauth2-token-flow.md) | Production (Managed Identity + WIF) and local dev (client secret) token flows |\n| [references\u002Fknown-limitations.md](references\u002Fknown-limitations.md) | 29 known issues organized by category (from official preview known-issues page) |\n| [references\u002Fsdk-sidecar.md](references\u002Fsdk-sidecar.md) | Microsoft Entra SDK for AgentID — endpoints, 3P agent patterns, Docker\u002FK8s deployment, security |\n\n### External Links\n\n| Resource | URL |\n|----------|-----|\n| Official Setup Guide | https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fentra\u002Fagent-id\u002Fidentity-platform\u002Fagent-id-setup-instructions |\n| AI-Guided Setup | https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fentra\u002Fagent-id\u002Fidentity-platform\u002Fagent-id-ai-guided-setup |\n| Microsoft Entra SDK for AgentID — Overview | https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fentra\u002Fmsidweb\u002Fagent-id-sdk\u002Foverview |\n| Microsoft Entra SDK for AgentID — Endpoints | https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fentra\u002Fmsidweb\u002Fagent-id-sdk\u002Fendpoints |\n","# Microsoft Entra Agent ID\n\nCreate and manage OAuth2-capable identities for AI agents using Microsoft Graph beta API.\n\n> **Preview API** — All Agent Identity endpoints are under `\u002Fbeta` only. Not available in `\u002Fv1.0`.\n\n## Before You Start\n\nSearch `microsoft-docs` MCP for the latest Agent ID documentation:\n- Query: \"Microsoft Entra agent identity setup\"\n- Verify: API parameters match current preview behavior\n\n## Conceptual Model\n\n```\nAgent Identity Blueprint (application)        ← one per agent type\u002Fproject\n  └── BlueprintPrincipal (service principal)   ← MUST be created explicitly\n        ├── Agent Identity (SP): agent-1       ← one per agent instance\n        ├── Agent Identity (SP): agent-2\n        └── Agent Identity (SP): agent-3\n```\n\n## Prerequisites\n\n### PowerShell (recommended for interactive setup)\n\n```powershell\n# Requires PowerShell 7+\nInstall-Module Microsoft.Graph.Beta.Applications -Scope CurrentUser -Force\n```\n\n### Python (for programmatic provisioning)\n\n```bash\npip install azure-identity requests\n```\n\n### Required Entra Roles\n\nOne of: **Agent Identity Developer**, **Agent Identity Administrator**, or **Application Administrator**.\n\n## Environment Variables\n\n```bash\nAZURE_TENANT_ID=\u003Cyour-tenant-id>\nAZURE_CLIENT_ID=\u003Capp-registration-client-id>\nAZURE_CLIENT_SECRET=\u003Capp-registration-secret>\n```\n\n## Authentication\n\n> **⚠️ `DefaultAzureCredential` is NOT supported.** Azure CLI tokens contain\n> `Directory.AccessAsUser.All`, which Agent Identity APIs explicitly reject (403).\n> You MUST use a dedicated app registration with `client_credentials` flow or\n> connect via `Connect-MgGraph` with explicit delegated scopes.\n\n### PowerShell (delegated permissions)\n\n```powershell\nConnect-MgGraph -Scopes @(\n    \"AgentIdentityBlueprint.Create\",\n    \"AgentIdentityBlueprint.ReadWrite.All\",\n    \"AgentIdentityBlueprintPrincipal.Create\",\n    \"User.Read\"\n)\nSet-MgRequestContext -ApiVersion beta\n\n$currentUser = (Get-MgContext).Account\n$userId = (Get-MgUser -UserId $currentUser).Id\n```\n\n### Python (application permissions)\n\n```python\nimport os\nimport requests\nfrom azure.identity import ClientSecretCredential\n\ncredential = ClientSecretCredential(\n    tenant_id=os.environ[\"AZURE_TENANT_ID\"],\n    client_id=os.environ[\"AZURE_CLIENT_ID\"],\n    client_secret=os.environ[\"AZURE_CLIENT_SECRET\"],\n)\ntoken = credential.get_token(\"https:\u002F\u002Fgraph.microsoft.com\u002F.default\")\n\nGRAPH = \"https:\u002F\u002Fgraph.microsoft.com\u002Fbeta\"\nheaders = {\n    \"Authorization\": f\"Bearer {token.token}\",\n    \"Content-Type\": \"application\u002Fjson\",\n    \"OData-Version\": \"4.0\",  # Required for all Agent Identity API calls\n}\n```\n\n## Core Workflow\n\n### Step 1: Create Agent Identity Blueprint\n\nSponsors are required and **must be User objects** — ServicePrincipals and Groups are rejected.\n\n```python\nimport subprocess\n\n# Get sponsor user ID (client_credentials has no user context, so use az CLI)\nresult = subprocess.run(\n    [\"az\", \"ad\", \"signed-in-user\", \"show\", \"--query\", \"id\", \"-o\", \"tsv\"],\n    capture_output=True, text=True, check=True,\n)\nuser_id = result.stdout.strip()\n\nblueprint_body = {\n    \"@odata.type\": \"Microsoft.Graph.AgentIdentityBlueprint\",\n    \"displayName\": \"My Agent Blueprint\",\n    \"sponsors@odata.bind\": [\n        f\"https:\u002F\u002Fgraph.microsoft.com\u002Fbeta\u002Fusers\u002F{user_id}\"\n    ],\n}\nresp = requests.post(f\"{GRAPH}\u002Fapplications\", headers=headers, json=blueprint_body)\nresp.raise_for_status()\n\nblueprint = resp.json()\napp_id = blueprint[\"appId\"]\nblueprint_obj_id = blueprint[\"id\"]\n```\n\n### Step 2: Create BlueprintPrincipal\n\n> **This step is mandatory.** Creating a Blueprint does NOT auto-create its\n> service principal. Without this, Agent Identity creation fails with:\n> `400: The Agent Blueprint Principal for the Agent Blueprint does not exist.`\n\n```python\nsp_body = {\n    \"@odata.type\": \"Microsoft.Graph.AgentIdentityBlueprintPrincipal\",\n    \"appId\": app_id,\n}\nresp = requests.post(f\"{GRAPH}\u002FservicePrincipals\", headers=headers, json=sp_body)\nresp.raise_for_status()\n```\n\nIf implementing idempotent scripts, check for and create the BlueprintPrincipal\neven when the Blueprint already exists (a previous run may have created the Blueprint\nbut crashed before creating the SP).\n\n### Step 3: Create Agent Identities\n\n```python\nagent_body = {\n    \"@odata.type\": \"Microsoft.Graph.AgentIdentity\",\n    \"displayName\": \"my-agent-instance-1\",\n    \"agentIdentityBlueprintId\": app_id,\n    \"sponsors@odata.bind\": [\n        f\"https:\u002F\u002Fgraph.microsoft.com\u002Fbeta\u002Fusers\u002F{user_id}\"\n    ],\n}\nresp = requests.post(f\"{GRAPH}\u002FservicePrincipals\", headers=headers, json=agent_body)\nresp.raise_for_status()\nagent = resp.json()\n```\n\n## API Reference\n\n| Operation | Method | Endpoint | OData Type |\n|-----------|--------|----------|------------|\n| Create Blueprint | `POST` | `\u002Fapplications` | `Microsoft.Graph.AgentIdentityBlueprint` |\n| Create BlueprintPrincipal | `POST` | `\u002FservicePrincipals` | `Microsoft.Graph.AgentIdentityBlueprintPrincipal` |\n| Create Agent Identity | `POST` | `\u002FservicePrincipals` | `Microsoft.Graph.AgentIdentity` |\n| List Agent Identities | `GET` | `\u002FservicePrincipals?$filter=...` | — |\n| Delete Agent Identity | `DELETE` | `\u002FservicePrincipals\u002F{id}` | — |\n| Delete Blueprint | `DELETE` | `\u002Fapplications\u002F{id}` | — |\n\nAll endpoints use base URL: `https:\u002F\u002Fgraph.microsoft.com\u002Fbeta`\n\n## Required Permissions\n\n| Permission | Purpose |\n|-----------|---------|\n| `Application.ReadWrite.All` | Blueprint CRUD (application objects) |\n| `AgentIdentityBlueprint.Create` | Create new Blueprints |\n| `AgentIdentityBlueprint.ReadWrite.All` | Read\u002Fupdate Blueprints |\n| `AgentIdentityBlueprintPrincipal.Create` | Create BlueprintPrincipals |\n| `AgentIdentity.Create.All` | Create Agent Identities |\n| `AgentIdentity.ReadWrite.All` | Read\u002Fupdate Agent Identities |\n\nThere are **18 Agent Identity-specific** Graph application permissions. Discover all:\n```bash\naz ad sp show --id 00000003-0000-0000-c000-000000000000 \\\n  --query \"appRoles[?contains(value, 'AgentIdentity')].{id:id, value:value}\" -o json\n```\n\nGrant admin consent (required for application permissions):\n```bash\naz ad app permission admin-consent --id \u003Cclient-id>\n```\n\n> Admin consent may fail with 404 if the service principal hasn't replicated. Retry with 10–40s backoff.\n\n## Cleanup\n\n```python\n# Delete Agent Identity\nrequests.delete(f\"{GRAPH}\u002FservicePrincipals\u002F{agent['id']}\", headers=headers)\n\n# Delete BlueprintPrincipal (get SP ID first)\nsps = requests.get(\n    f\"{GRAPH}\u002FservicePrincipals?$filter=appId eq '{app_id}'\",\n    headers=headers,\n).json()\nfor sp in sps.get(\"value\", []):\n    requests.delete(f\"{GRAPH}\u002FservicePrincipals\u002F{sp['id']}\", headers=headers)\n\n# Delete Blueprint\nrequests.delete(f\"{GRAPH}\u002Fapplications\u002F{blueprint_obj_id}\", headers=headers)\n```\n\n## Best Practices\n\n1. **Always create BlueprintPrincipal after Blueprint** — not auto-created; implement idempotent checks on both\n2. **Use User objects as sponsors** — ServicePrincipals and Groups are rejected\n3. **Handle permission propagation delays** — after admin consent, wait 30–120s; retry with backoff on 403\n4. **Include `OData-Version: 4.0` header** on every Graph request\n5. **Use Workload Identity Federation for production auth** — for local dev, use a client secret on the Blueprint (see [references\u002Foauth2-token-flow.md](references\u002Foauth2-token-flow.md))\n6. **Set `identifierUris` on Blueprint** before using OAuth2 scoping (`api:\u002F\u002F{app-id}`)\n7. **Never use Azure CLI tokens** for API calls — they contain `Directory.AccessAsUser.All` which is hard-rejected\n8. **Check for existing resources** before creating — implement idempotent provisioning\n\n## References\n\n| File | Contents |\n|------|----------|\n| [references\u002Foauth2-token-flow.md](references\u002Foauth2-token-flow.md) | Production (Managed Identity + WIF) and local dev (client secret) token flows |\n| [references\u002Fknown-limitations.md](references\u002Fknown-limitations.md) | 29 known issues organized by category (from official preview known-issues page) |\n| [references\u002Fsdk-sidecar.md](references\u002Fsdk-sidecar.md) | Microsoft Entra SDK for AgentID — endpoints, 3P agent patterns, Docker\u002FK8s deployment, security |\n\n### External Links\n\n| Resource | URL |\n|----------|-----|\n| Official Setup Guide | https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fentra\u002Fagent-id\u002Fidentity-platform\u002Fagent-id-setup-instructions |\n| AI-Guided Setup | https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fentra\u002Fagent-id\u002Fidentity-platform\u002Fagent-id-ai-guided-setup |\n| Microsoft Entra SDK for AgentID — Overview | https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fentra\u002Fmsidweb\u002Fagent-id-sdk\u002Foverview |\n| Microsoft Entra SDK for AgentID — Endpoints | https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fentra\u002Fmsidweb\u002Fagent-id-sdk\u002Fendpoints |\n",{"name":5,"description":7},"main","3f5b461b2314e01c400564051e92469114c5b68f",".github\u002Fskills\u002Fentra-agent-id",368,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","https:\u002F\u002Fmicrosoft.github.io\u002Fskills\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 02:08:41",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add microsoft\u002Fskills --skill entra-agent-id",{"tool":71,"command":72},"bunx","bunx skills add microsoft\u002Fskills --skill entra-agent-id",{"tool":74,"command":75},"pnpm","pnpm dlx skills add microsoft\u002Fskills --skill entra-agent-id","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fentra-agent-id\u002FSKILL.md",true,[79,85,89],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fknown-limitations.md","REFERENCE","参考文档",4890,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fentra-agent-id\u002Freferences\u002Fknown-limitations.md",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Foauth2-token-flow.md",5000,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fentra-agent-id\u002Freferences\u002Foauth2-token-flow.md",{"path":90,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fsdk-sidecar.md",13326,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fentra-agent-id\u002Freferences\u002Fsdk-sidecar.md",[94,119,156,183,203,241],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":101,"publishedAt":50},"01M69B4JCRQV5SPXAFCKXQRV0H","skill-creator","Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fskill-creator\u002FSKILL.md",[100],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[102,103,104,9,105,106,107,108,109,110,111,112,113,114,115,31,116,117,118],"skill creator","creator","coding agents","foundry","microsoft foundry","ai coding agents","azure","services","coding","guide","use","ai coding","with","sdks","Existing","when","new",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":135,"publishedAt":50},"01M69B4FD57V1MYKRWAJJECTZ7","podcast-generation","Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fpodcast-generation\u002FSKILL.md",[125,128,131,134],{"categoryNo":126,"categoryName":127,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":129,"categoryName":130,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":132,"categoryName":133,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[136,137,138,139,140,141,142,108,143,144,145,37,146,147,148,149,150,151,152,153,154,117,155],"podcast generation","podcast","generation","frontend","python","react","realtime","azure openai","generate","streaming","Audio","stack","text","model","fastapi","creation","python fastapi","narrative","features","fastapi backend",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":163,"publishedAt":50},"01M69B4CYPM5SESY5ZWEFDXEQZ","microsoft-docs","Understand Microsoft technologies by querying official documentation. Use whenever the user asks how something works, wants tutorials, needs configuration options, limits, quotas, or best practices for any Microsoft technology (Azure, .NET, M365, Windows, Power Platform, etc.)—even if they don't mention \"docs.\" If the question is about understanding a concept rather than writing code, this is the right skill.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmicrosoft-docs\u002FSKILL.md",[162],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[164,9,165,166,167,168,169,170,171,172,173,108,174,175,176,112,177,68,178,179,180,181,182,31],"docs","microsoft docs","MCP","writing","cli","mcp server","windows","power platform","official","documentation","learn","best practices","question","power","back","technology","platform","learn mcp","concept",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":190,"publishedAt":50},"01M69B49C3YPD1ZJ3NC0HPCY58","mcp-builder","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP), Node\u002FTypeScript (MCP SDK), or C#\u002F.NET (Microsoft MCP SDK).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmcp-builder\u002FSKILL.md",[189],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[166,191,192,193,140,194,48,195,9,196,197,149,198,199,111,112,200,201,202,114,31,117],"mcp builder","builder","typescript","llms","model context protocol","fastmcp","Tools","node","context","integrate","mcp sdk","building mcp servers",{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":221,"publishedAt":50},"01M69B467A7CDMFQ0T6Q0ZA12Q","kql","KQL language expertise for writing correct, efficient Kusto Query Language queries. Covers syntax gotchas, join patterns, dynamic types, datetime pitfalls, regex patterns, serialization, memory management, result-size discipline, and advanced functions (geo, vector, graph). USE THIS SKILL whenever writing, debugging, or reviewing KQL queries — even simple ones — because the gotchas section prevents the most common errors that waste tool calls and cause expensive retry cascades. Trigger on: KQL, Kusto, ADX, Azure Data Explorer, Fabric Real-Time Intelligence, EventHouse, Log Analytics, log analysis, data exploration, time series, anomaly detection, summarize, where clause, join, extend, project, let statement, parse operator, extract function, any mention of pipe-forward query syntax.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fkql\u002FSKILL.md",[209,212,213,218],{"categoryNo":210,"categoryName":211,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":214,"categoryName":215,"taxonomyType":216,"taxonomyTypeDesc":217},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",{"categoryNo":219,"categoryName":220,"taxonomyType":216,"taxonomyTypeDesc":217},"01JBSEEDCAT000000000000036","内容创作者",[205,167,222,223,224,108,225,226,227,228,229,230,231,232,233,234,235,236,237,31,238,239,240],"summarize","memory","analytics","vector","time series","tool","discipline","log","geo","exploration","pipe","time","project","regex","join","datetime","section","anomaly","parse",{"skillNo":242,"name":243,"nameZh":6,"description":244,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":245,"categories":246,"keywords":247,"publishedAt":50},"01M69B44HJQ7897EZ7NE7DWQX3","github-issue-creator","Convert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error messages, or informal descriptions and wants a structured GitHub issue. Supports images\u002FGIFs for visual evidence.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fgithub-issue-creator\u002FSKILL.md",[],[248,249,250,251,103,252,253,254,255,256,257,258,112,259,260,261,262,263,264,31,117],"github","github issue creator","github issue","issue","issue creator","screenshots","notes","logs","error messages","messages","convert","evidence","reports","images","info","visual","error"]