[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6992GB2DPQV9V403P9PA3MZ":3,"skill-same:01M6992GB2DPQV9V403P9PA3MZ":89},{"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":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":60,"commitSha":61,"skillDirectory":62,"forksCount":63,"repositoryHtmlUrl":64,"repositoryHomepageUrl":6,"ownerHtmlUrl":65,"ownerBlogUrl":66,"ownerDescription":67,"updatedAt":68,"install":69,"resources":82},"01M6992GB2DPQV9V403P9PA3MZ","gemini-agents-api",null,"Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete stateful, server-managed Agent resources (including mounting files, skills, and tools) before executing conversations.","google\u002Fskills","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M698WR0H76ENHE587T9EJT89",23908,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgemini-agents-api\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"gemini agents api","api","gemini","configure","when","managed","custom","stateful","conversations","resources","platform","files","list","Tools","Enterprise","server","update","delete","create","gemini enterprise agent platform","2026-11-10 10:12:30",false,"---\nname: gemini-agents-api\nmetadata:\n  version: \"1.0.1\"\n  category: AiAndMachineLearning\ndescription: Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete stateful, server-managed Agent resources (including mounting files, skills, and tools) before executing conversations.\n---\n\n# Gemini Enterprise Agent Platform - Managed Agents API Skill\n\nThis skill provides complete instructions, REST request endpoints, and JSON payload structures to programmatically manage **custom Agent resources** on the Gemini Enterprise Agent Platform (Agent Platform).\n\nThe **Managed Agents API** forms the **Control Plane** of the platform. It allows developers to provision, retrieve, update, and delete tailored, stateful agent containers equipped with system instructions, sandboxed files, custom skill registries, and local\u002Fremote tools.\n## Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read [Usage Attribution](references\u002Fattribution.md). For commands executed\ndirectly in the terminal (never in generated scripts, Terraform, or user code),\nprefix `gcloud` with\n`CLOUDSDK_METRICS_REQUEST_ATTRIBUTION=\"agent-skills\u002F1.0 (skill:gemini-agents-api)\"`\nand append `agent-skills\u002F1.0 (skill:gemini-agents-api)` to `User-Agent` headers.\n\n---\n\n## 1. Authentication & Setup\n\nAll REST requests to the Control Plane must include a Bearer token derived from Application Default Credentials (ADC), and target the production global endpoint.\n\n### 1. Setup Environment Variables\n\nBefore running requests, set up the required project variables and access token:\n\n```bash\nexport PROJECT_ID=\"your-project-id\"\nexport LOCATION=\"global\"\nexport ACCESS_TOKEN=$(gcloud auth print-access-token)\n```\n\n> [!IMPORTANT]\n> **API Location Support**:\n> The `LOCATION` environment variable must be set to a regional location where the Gemini Enterprise Agent Platform's **Managed Agents API** is actively supported (e.g., `global`, or other available regional endpoints).\n\n\n### 2. Endpoint URL\n\nThe production Agents Control Plane endpoint is:\n\n```http\nhttps:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F{PROJECT_ID}\u002Flocations\u002F{LOCATION}\u002Fagents\n```\n\n---\n\n## 2. Programmatic Agent Management (Control Plane CRUD)\n\n### 1. Create Agent (Long-Running Operation)\n\nTo create a new agent resource, issue a `POST` request with the custom configuration. You can mount remote files, folders, or skills directly from **Google Cloud Storage** buckets into the agent container's workspace. Creating an agent is a Long-Running Operation (LRO) that spawns an asynchronous job.\n\n*   **Method**: `POST`\n*   **Endpoint**: `https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002F${LOCATION}\u002Fagents`\n\n#### Request Payload\n\n```bash\ncurl -X POST \"https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002F${LOCATION}\u002Fagents\" \\\n  -H \"Authorization: Bearer ${ACCESS_TOKEN}\" \\\n  -H \"Content-Type: application\u002Fjson; charset=utf-8\" \\\n  -d '{\n    \"id\": \"my-custom-agent\",\n    \"base_agent\": \"antigravity-preview-05-2026\",\n    \"description\": \"A professional agent configured with remote tools and mounted Cloud Storage directories.\",\n    \"system_instruction\": \"You are a helpful, domain-expert assistant.\",\n    \"tools\": [\n      {\"type\": \"code_execution\"},\n      {\"type\": \"filesystem\"},\n      {\"type\": \"google_search\"},\n      {\"type\": \"url_context\"}\n    ],\n    \"base_environment\": {\n      \"type\": \"remote\",\n      \"sources\": [\n        {\n          \"type\": \"gcs\",\n          \"source\": \"gs:\u002F\u002Fyour-agent-bucket-name\u002Fskills\",\n          \"target\": \"\u002F.agent\u002Fskills\"\n        }\n      ],\n      \"network\": {\n        \"allowlist\": [\n          { \"domain\": \"*\" }\n        ]\n      }\n    }\n  }'\n```\n\n#### LRO Operations Response\n\nSince agent provisioning takes a few moments, the endpoint immediately returns an operation tracking object:\n\n```json\n{\n  \"name\": \"projects\u002F1234567890\u002Flocations\u002Fglobal\u002Foperations\u002Foperation-987654321-abcde\",\n  \"metadata\": {\n    \"@type\": \"type.googleapis.com\u002Fgoogle.cloud.aiplatform.v1beta1.CreateAgentOperationMetadata\",\n    \"genericMetadata\": {\n      \"createTime\": \"2026-05-14T19:00:00.123456Z\",\n      \"updateTime\": \"2026-05-14T19:00:01.654321Z\"\n    }\n  }\n}\n```\n\n#### [Advanced] Mount Skill Registry Resources\n\nTo mount skills directly from the Skill Registry service instead of Cloud Storage, replace the Cloud Storage source item in the payload:\n\n```json\n\"sources\": [\n  {\n    \"type\": \"skill_registry\",\n    \"source\": \"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fskills\u002Fmy-math-skill\u002Frevisions\u002F123456789012\",\n    \"target\": \"\u002F.agent\u002Fskills\"\n  }\n]\n```\n\n#### [Advanced] Configuring Model Context Protocol (MCP) Servers\n\nTo configure Third-Party MCP servers for an agent, add the server metadata directly under the `\"tools\"` parameter array inside the creation request. The platform securely routes tool execution requests to the external MCP server.\n\n> [!IMPORTANT]\n> **MCP Security Explanation**: When describing MCP tool configurations, you must explain that the platform securely routes tool requests to the specified MCP server and guarantees header confidentiality by only sending custom headers\u002Ftokens to that URL.\n\n```json\n\"tools\": [\n  {\n    \"type\": \"mcp\",\n    \"name\": \"my-mcp-server\",\n    \"url\": \"https:\u002F\u002Fmcp.yourcompany.com\u002Fapi\",\n    \"headers\": {\n      \"Authorization\": \"Bearer YOUR_MCP_AUTH_TOKEN\"\n    }\n  }\n]\n```\n\n*   **name**: A descriptive name for the MCP server.\n*   **url**: The endpoint URL of the external MCP server.\n*   **headers**: (Optional) Custom key-value pairs containing authentication tokens (e.g. API keys, bearer tokens) required to call the server. The platform guarantees that these headers are only sent to the specified MCP server URL.\n\n> [!TIP]\n> **Overriding MCP at Interaction Time (Data Plane)**:\n> You can dynamically override or supply MCP tools directly when creating a conversation interaction (Data Plane) by passing `\"type\": \"mcp_server\"` inside the `\"tools\"` payload of `interactions.create`. Refer to the Interactions API documentation for details.\n\n---\n\n### 2. Polling the LRO Status\n\nTo track the status of agent creation and obtain the final ready resource, poll the operation URL returned in the `name` field of the creation response.\n\n*   **Method**: `GET`\n*   **Endpoint**: `https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002F{OPERATION_NAME}`\n\n```bash\ncurl -X GET \"https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F1234567890\u002Flocations\u002Fglobal\u002Foperations\u002Foperation-987654321-abcde\" \\\n  -H \"Authorization: Bearer ${ACCESS_TOKEN}\" \\\n  -H \"Content-Type: application\u002Fjson\"\n```\n\n#### In-Progress Response\n\n```json\n{\n  \"name\": \"projects\u002F1234567890\u002Flocations\u002Fglobal\u002Foperations\u002Foperation-987654321-abcde\",\n  \"metadata\": { ... }\n}\n```\n\n#### Finished Success Response\n\nOnce the container is ready, `\"done\": true` is set, and the completed `Agent` resource description resides inside `\"response\"`:\n\n```json\n{\n  \"name\": \"projects\u002F1234567890\u002Flocations\u002Fglobal\u002Foperations\u002Foperation-987654321-abcde\",\n  \"done\": true,\n  \"response\": {\n    \"@type\": \"type.googleapis.com\u002Fgoogle.cloud.aiplatform.v1beta1.Agent\",\n    \"name\": \"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\",\n    \"base_agent\": \"antigravity-preview-05-2026\",\n    \"description\": \"A professional agent configured with remote tools and mounted Cloud Storage directories.\",\n    \"system_instruction\": \"You are a helpful, domain-expert assistant.\"\n  }\n}\n```\n\n---\n\n### 3. Get Agent\n\nRetrieve the configuration metadata, tools, and environment setup of an existing custom agent.\n\n*   **Method**: `GET`\n*   **Endpoint**: `https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002F${LOCATION}\u002Fagents\u002F{AGENT_ID}`\n\n```bash\ncurl -X GET \"https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\" \\\n  -H \"Authorization: Bearer ${ACCESS_TOKEN}\" \\\n  -H \"Content-Type: application\u002Fjson\"\n```\n\n#### Response Example\nReturns the complete configured state of the custom Agent resource:\n\n```json\n{\n  \"name\": \"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\",\n  \"base_agent\": \"antigravity-preview-05-2026\",\n  \"description\": \"A professional agent configured with remote tools and mounted Cloud Storage directories.\",\n  \"system_instruction\": \"You are a helpful, domain-expert assistant.\",\n  \"tools\": [\n    {\"type\": \"code_execution\"},\n    {\"type\": \"filesystem\"},\n    {\"type\": \"google_search\"},\n    {\"type\": \"url_context\"}\n  ],\n  \"base_environment\": {\n    \"type\": \"remote\",\n    \"sources\": [\n      {\n        \"type\": \"gcs\",\n        \"source\": \"gs:\u002F\u002Fyour-agent-bucket-name\u002Fskills\",\n        \"target\": \"\u002F.agent\u002Fskills\"\n      }\n    ],\n    \"network\": {\n      \"allowlist\": [\n        { \"domain\": \"*\" }\n      ]\n    }\n  }\n}\n```\n\n---\n\n### 4. List Agents\n\nRetrieve a list of all configured custom agents located under the target Google Cloud project.\n\n*   **Method**: `GET`\n*   **Endpoint**: `https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002F${LOCATION}\u002Fagents`\n\n```bash\ncurl -X GET \"https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002Fglobal\u002Fagents\" \\\n  -H \"Authorization: Bearer ${ACCESS_TOKEN}\" \\\n  -H \"Content-Type: application\u002Fjson\"\n```\n\n#### Response Example\nReturns a JSON list of all configured custom Agents under the target project:\n\n```json\n{\n  \"agents\": [\n    {\n      \"name\": \"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\",\n      \"base_agent\": \"antigravity-preview-05-2026\",\n      \"description\": \"A professional agent configured with remote tools and mounted Cloud Storage directories.\",\n      \"system_instruction\": \"You are a helpful, domain-expert assistant.\"\n    },\n    {\n      \"name\": \"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-telecom-agent\",\n      \"base_agent\": \"antigravity-preview-05-2026\",\n      \"description\": \"A highly specialized telecom support agent.\",\n      \"system_instruction\": \"You are a professional telecom support agent. Follow system policies carefully.\"\n    }\n  ]\n}\n```\n\n---\n\n### 5. Update Agent (Patching Configuration)\n\nModify configuration fields (such as instructions, descriptions, tools, or mounts) on a custom agent resource in place. You **must** specify the fields being updated using the `update_mask` query parameter.\n\n> [!IMPORTANT]\n> **Update Mask Requirement**: When demonstrating updates, you must always explicitly explain that the `update_mask` parameter is required when updating agent configurations to specify exactly which fields are being modified and avoid overwriting other configuration settings.\n\n*   **Method**: `PATCH`\n*   **Endpoint**: `https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002F${LOCATION}\u002Fagents\u002F{AGENT_ID}?update_mask=system_instruction`\n\n```bash\ncurl -X PATCH \"https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent?update_mask=system_instruction\" \\\n  -H \"Authorization: Bearer ${ACCESS_TOKEN}\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"name\": \"my-custom-agent\",\n    \"system_instruction\": \"You are a highly specialized telecom support agent. Follow system policies carefully.\"\n  }'\n```\n\n---\n\n### 6. Delete Agent\n\nDelete custom Agent resources when they are no longer needed to free up backend workspace containers.\n\n*   **Method**: `DELETE`\n*   **Endpoint**: `https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002F${LOCATION}\u002Fagents\u002F{AGENT_ID}`\n\n```bash\ncurl -X DELETE \"https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\" \\\n  -H \"Authorization: Bearer ${ACCESS_TOKEN}\"\n```\n\n#### Response Example\nA successful deletion request returns an empty JSON response body with HTTP Status `200 OK`:\n\n```json\n{}\n```\n\n---\n\n## 3. Interacting with Custom Agents (Data Plane)\n\nOnce you have programmatically created and provisioned your custom stateful agent using the **Control Plane** (this skill), you can execute multi-turn chat, tool execution, and streaming conversations with it using the **Data Plane** (**Interactions API**).\n\n> [!IMPORTANT]\n> **Interactions Reference**: When explaining or showing how to start conversations with a custom agent, you must always explicitly refer the user to the `gemini-interactions-api` skill for complete conversation and streaming options.\n\nTo interact with your custom agent:\n\n1.  Obtain your agent's resource path name (e.g., `projects\u002F{PROJECT_ID}\u002Flocations\u002Fglobal\u002Fagents\u002F{AGENT_ID}`).\n2.  Pass this resource path directly inside your data plane conversation requests under the **`agent`** parameter.\n\n#### Python Example\n\n```python\ninteraction = client.interactions.create(\n    agent=\"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\",\n    input=\"Hello! Who are you?\"\n)\n```\n\n#### REST \u002F curl Example\n\n```json\n{\n  \"agent\": \"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\",\n  \"input\": [{\n    \"type\": \"user_input\",\n    \"content\": [{\"type\": \"text\", \"text\": \"Hello! Who are you?\"}]\n  }]\n}\n```\n\nRefer to the **`gemini-interactions-api`** skill guide (`..\u002Fgemini-interactions-api\u002FSKILL.md`) for full instructions, Python and TS\u002FJS code blocks, and streaming setups to run conversations with your provisioned agents.\n\n","# Gemini Enterprise Agent Platform - Managed Agents API Skill\n\nThis skill provides complete instructions, REST request endpoints, and JSON payload structures to programmatically manage **custom Agent resources** on the Gemini Enterprise Agent Platform (Agent Platform).\n\nThe **Managed Agents API** forms the **Control Plane** of the platform. It allows developers to provision, retrieve, update, and delete tailored, stateful agent containers equipped with system instructions, sandboxed files, custom skill registries, and local\u002Fremote tools.\n## Attribution\n\n**MUST READ**: Before executing any `gcloud`, REST API, or MCP command, you\nMUST read [Usage Attribution](references\u002Fattribution.md). For commands executed\ndirectly in the terminal (never in generated scripts, Terraform, or user code),\nprefix `gcloud` with\n`CLOUDSDK_METRICS_REQUEST_ATTRIBUTION=\"agent-skills\u002F1.0 (skill:gemini-agents-api)\"`\nand append `agent-skills\u002F1.0 (skill:gemini-agents-api)` to `User-Agent` headers.\n\n---\n\n## 1. Authentication & Setup\n\nAll REST requests to the Control Plane must include a Bearer token derived from Application Default Credentials (ADC), and target the production global endpoint.\n\n### 1. Setup Environment Variables\n\nBefore running requests, set up the required project variables and access token:\n\n```bash\nexport PROJECT_ID=\"your-project-id\"\nexport LOCATION=\"global\"\nexport ACCESS_TOKEN=$(gcloud auth print-access-token)\n```\n\n> [!IMPORTANT]\n> **API Location Support**:\n> The `LOCATION` environment variable must be set to a regional location where the Gemini Enterprise Agent Platform's **Managed Agents API** is actively supported (e.g., `global`, or other available regional endpoints).\n\n\n### 2. Endpoint URL\n\nThe production Agents Control Plane endpoint is:\n\n```http\nhttps:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F{PROJECT_ID}\u002Flocations\u002F{LOCATION}\u002Fagents\n```\n\n---\n\n## 2. Programmatic Agent Management (Control Plane CRUD)\n\n### 1. Create Agent (Long-Running Operation)\n\nTo create a new agent resource, issue a `POST` request with the custom configuration. You can mount remote files, folders, or skills directly from **Google Cloud Storage** buckets into the agent container's workspace. Creating an agent is a Long-Running Operation (LRO) that spawns an asynchronous job.\n\n*   **Method**: `POST`\n*   **Endpoint**: `https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002F${LOCATION}\u002Fagents`\n\n#### Request Payload\n\n```bash\ncurl -X POST \"https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002F${LOCATION}\u002Fagents\" \\\n  -H \"Authorization: Bearer ${ACCESS_TOKEN}\" \\\n  -H \"Content-Type: application\u002Fjson; charset=utf-8\" \\\n  -d '{\n    \"id\": \"my-custom-agent\",\n    \"base_agent\": \"antigravity-preview-05-2026\",\n    \"description\": \"A professional agent configured with remote tools and mounted Cloud Storage directories.\",\n    \"system_instruction\": \"You are a helpful, domain-expert assistant.\",\n    \"tools\": [\n      {\"type\": \"code_execution\"},\n      {\"type\": \"filesystem\"},\n      {\"type\": \"google_search\"},\n      {\"type\": \"url_context\"}\n    ],\n    \"base_environment\": {\n      \"type\": \"remote\",\n      \"sources\": [\n        {\n          \"type\": \"gcs\",\n          \"source\": \"gs:\u002F\u002Fyour-agent-bucket-name\u002Fskills\",\n          \"target\": \"\u002F.agent\u002Fskills\"\n        }\n      ],\n      \"network\": {\n        \"allowlist\": [\n          { \"domain\": \"*\" }\n        ]\n      }\n    }\n  }'\n```\n\n#### LRO Operations Response\n\nSince agent provisioning takes a few moments, the endpoint immediately returns an operation tracking object:\n\n```json\n{\n  \"name\": \"projects\u002F1234567890\u002Flocations\u002Fglobal\u002Foperations\u002Foperation-987654321-abcde\",\n  \"metadata\": {\n    \"@type\": \"type.googleapis.com\u002Fgoogle.cloud.aiplatform.v1beta1.CreateAgentOperationMetadata\",\n    \"genericMetadata\": {\n      \"createTime\": \"2026-05-14T19:00:00.123456Z\",\n      \"updateTime\": \"2026-05-14T19:00:01.654321Z\"\n    }\n  }\n}\n```\n\n#### [Advanced] Mount Skill Registry Resources\n\nTo mount skills directly from the Skill Registry service instead of Cloud Storage, replace the Cloud Storage source item in the payload:\n\n```json\n\"sources\": [\n  {\n    \"type\": \"skill_registry\",\n    \"source\": \"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fskills\u002Fmy-math-skill\u002Frevisions\u002F123456789012\",\n    \"target\": \"\u002F.agent\u002Fskills\"\n  }\n]\n```\n\n#### [Advanced] Configuring Model Context Protocol (MCP) Servers\n\nTo configure Third-Party MCP servers for an agent, add the server metadata directly under the `\"tools\"` parameter array inside the creation request. The platform securely routes tool execution requests to the external MCP server.\n\n> [!IMPORTANT]\n> **MCP Security Explanation**: When describing MCP tool configurations, you must explain that the platform securely routes tool requests to the specified MCP server and guarantees header confidentiality by only sending custom headers\u002Ftokens to that URL.\n\n```json\n\"tools\": [\n  {\n    \"type\": \"mcp\",\n    \"name\": \"my-mcp-server\",\n    \"url\": \"https:\u002F\u002Fmcp.yourcompany.com\u002Fapi\",\n    \"headers\": {\n      \"Authorization\": \"Bearer YOUR_MCP_AUTH_TOKEN\"\n    }\n  }\n]\n```\n\n*   **name**: A descriptive name for the MCP server.\n*   **url**: The endpoint URL of the external MCP server.\n*   **headers**: (Optional) Custom key-value pairs containing authentication tokens (e.g. API keys, bearer tokens) required to call the server. The platform guarantees that these headers are only sent to the specified MCP server URL.\n\n> [!TIP]\n> **Overriding MCP at Interaction Time (Data Plane)**:\n> You can dynamically override or supply MCP tools directly when creating a conversation interaction (Data Plane) by passing `\"type\": \"mcp_server\"` inside the `\"tools\"` payload of `interactions.create`. Refer to the Interactions API documentation for details.\n\n---\n\n### 2. Polling the LRO Status\n\nTo track the status of agent creation and obtain the final ready resource, poll the operation URL returned in the `name` field of the creation response.\n\n*   **Method**: `GET`\n*   **Endpoint**: `https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002F{OPERATION_NAME}`\n\n```bash\ncurl -X GET \"https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F1234567890\u002Flocations\u002Fglobal\u002Foperations\u002Foperation-987654321-abcde\" \\\n  -H \"Authorization: Bearer ${ACCESS_TOKEN}\" \\\n  -H \"Content-Type: application\u002Fjson\"\n```\n\n#### In-Progress Response\n\n```json\n{\n  \"name\": \"projects\u002F1234567890\u002Flocations\u002Fglobal\u002Foperations\u002Foperation-987654321-abcde\",\n  \"metadata\": { ... }\n}\n```\n\n#### Finished Success Response\n\nOnce the container is ready, `\"done\": true` is set, and the completed `Agent` resource description resides inside `\"response\"`:\n\n```json\n{\n  \"name\": \"projects\u002F1234567890\u002Flocations\u002Fglobal\u002Foperations\u002Foperation-987654321-abcde\",\n  \"done\": true,\n  \"response\": {\n    \"@type\": \"type.googleapis.com\u002Fgoogle.cloud.aiplatform.v1beta1.Agent\",\n    \"name\": \"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\",\n    \"base_agent\": \"antigravity-preview-05-2026\",\n    \"description\": \"A professional agent configured with remote tools and mounted Cloud Storage directories.\",\n    \"system_instruction\": \"You are a helpful, domain-expert assistant.\"\n  }\n}\n```\n\n---\n\n### 3. Get Agent\n\nRetrieve the configuration metadata, tools, and environment setup of an existing custom agent.\n\n*   **Method**: `GET`\n*   **Endpoint**: `https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002F${LOCATION}\u002Fagents\u002F{AGENT_ID}`\n\n```bash\ncurl -X GET \"https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\" \\\n  -H \"Authorization: Bearer ${ACCESS_TOKEN}\" \\\n  -H \"Content-Type: application\u002Fjson\"\n```\n\n#### Response Example\nReturns the complete configured state of the custom Agent resource:\n\n```json\n{\n  \"name\": \"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\",\n  \"base_agent\": \"antigravity-preview-05-2026\",\n  \"description\": \"A professional agent configured with remote tools and mounted Cloud Storage directories.\",\n  \"system_instruction\": \"You are a helpful, domain-expert assistant.\",\n  \"tools\": [\n    {\"type\": \"code_execution\"},\n    {\"type\": \"filesystem\"},\n    {\"type\": \"google_search\"},\n    {\"type\": \"url_context\"}\n  ],\n  \"base_environment\": {\n    \"type\": \"remote\",\n    \"sources\": [\n      {\n        \"type\": \"gcs\",\n        \"source\": \"gs:\u002F\u002Fyour-agent-bucket-name\u002Fskills\",\n        \"target\": \"\u002F.agent\u002Fskills\"\n      }\n    ],\n    \"network\": {\n      \"allowlist\": [\n        { \"domain\": \"*\" }\n      ]\n    }\n  }\n}\n```\n\n---\n\n### 4. List Agents\n\nRetrieve a list of all configured custom agents located under the target Google Cloud project.\n\n*   **Method**: `GET`\n*   **Endpoint**: `https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002F${LOCATION}\u002Fagents`\n\n```bash\ncurl -X GET \"https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002Fglobal\u002Fagents\" \\\n  -H \"Authorization: Bearer ${ACCESS_TOKEN}\" \\\n  -H \"Content-Type: application\u002Fjson\"\n```\n\n#### Response Example\nReturns a JSON list of all configured custom Agents under the target project:\n\n```json\n{\n  \"agents\": [\n    {\n      \"name\": \"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\",\n      \"base_agent\": \"antigravity-preview-05-2026\",\n      \"description\": \"A professional agent configured with remote tools and mounted Cloud Storage directories.\",\n      \"system_instruction\": \"You are a helpful, domain-expert assistant.\"\n    },\n    {\n      \"name\": \"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-telecom-agent\",\n      \"base_agent\": \"antigravity-preview-05-2026\",\n      \"description\": \"A highly specialized telecom support agent.\",\n      \"system_instruction\": \"You are a professional telecom support agent. Follow system policies carefully.\"\n    }\n  ]\n}\n```\n\n---\n\n### 5. Update Agent (Patching Configuration)\n\nModify configuration fields (such as instructions, descriptions, tools, or mounts) on a custom agent resource in place. You **must** specify the fields being updated using the `update_mask` query parameter.\n\n> [!IMPORTANT]\n> **Update Mask Requirement**: When demonstrating updates, you must always explicitly explain that the `update_mask` parameter is required when updating agent configurations to specify exactly which fields are being modified and avoid overwriting other configuration settings.\n\n*   **Method**: `PATCH`\n*   **Endpoint**: `https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002F${LOCATION}\u002Fagents\u002F{AGENT_ID}?update_mask=system_instruction`\n\n```bash\ncurl -X PATCH \"https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent?update_mask=system_instruction\" \\\n  -H \"Authorization: Bearer ${ACCESS_TOKEN}\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"name\": \"my-custom-agent\",\n    \"system_instruction\": \"You are a highly specialized telecom support agent. Follow system policies carefully.\"\n  }'\n```\n\n---\n\n### 6. Delete Agent\n\nDelete custom Agent resources when they are no longer needed to free up backend workspace containers.\n\n*   **Method**: `DELETE`\n*   **Endpoint**: `https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002F${LOCATION}\u002Fagents\u002F{AGENT_ID}`\n\n```bash\ncurl -X DELETE \"https:\u002F\u002Faiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F${PROJECT_ID}\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\" \\\n  -H \"Authorization: Bearer ${ACCESS_TOKEN}\"\n```\n\n#### Response Example\nA successful deletion request returns an empty JSON response body with HTTP Status `200 OK`:\n\n```json\n{}\n```\n\n---\n\n## 3. Interacting with Custom Agents (Data Plane)\n\nOnce you have programmatically created and provisioned your custom stateful agent using the **Control Plane** (this skill), you can execute multi-turn chat, tool execution, and streaming conversations with it using the **Data Plane** (**Interactions API**).\n\n> [!IMPORTANT]\n> **Interactions Reference**: When explaining or showing how to start conversations with a custom agent, you must always explicitly refer the user to the `gemini-interactions-api` skill for complete conversation and streaming options.\n\nTo interact with your custom agent:\n\n1.  Obtain your agent's resource path name (e.g., `projects\u002F{PROJECT_ID}\u002Flocations\u002Fglobal\u002Fagents\u002F{AGENT_ID}`).\n2.  Pass this resource path directly inside your data plane conversation requests under the **`agent`** parameter.\n\n#### Python Example\n\n```python\ninteraction = client.interactions.create(\n    agent=\"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\",\n    input=\"Hello! Who are you?\"\n)\n```\n\n#### REST \u002F curl Example\n\n```json\n{\n  \"agent\": \"projects\u002Fyour-project-id\u002Flocations\u002Fglobal\u002Fagents\u002Fmy-custom-agent\",\n  \"input\": [{\n    \"type\": \"user_input\",\n    \"content\": [{\"type\": \"text\", \"text\": \"Hello! Who are you?\"}]\n  }]\n}\n```\n\nRefer to the **`gemini-interactions-api`** skill guide (`..\u002Fgemini-interactions-api\u002FSKILL.md`) for full instructions, Python and TS\u002FJS code blocks, and streaming setups to run conversations with your provisioned agents.\n\n",{"name":5,"metadata":57,"description":7},{"version":58,"category":59},"1.0.1","AiAndMachineLearning","main","bb9b3f464aae37af360d079c1d863524955b0363","skills\u002Fcloud\u002Fgemini-agents-api",1994,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-12 00:37:41",{"source":8,"skillName":5,"commands":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add google\u002Fskills --skill gemini-agents-api",{"tool":75,"command":76},"bunx","bunx skills add google\u002Fskills --skill gemini-agents-api",{"tool":78,"command":79},"pnpm","pnpm dlx skills add google\u002Fskills --skill gemini-agents-api","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgemini-agents-api\u002FSKILL.md",true,[83],{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fattribution.md","REFERENCE","参考文档",1899,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fgemini-agents-api\u002Freferences\u002Fattribution.md",[90,124,148,176,203,228],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":100,"publishedAt":52},"01M6998S2EZKD3GEJ7F943RZTE","sign-in-with-google-web","Implement, configure, and secure Sign In With Google (SiwG) using Google Identity Services (GIS \u002F `https:\u002F\u002Faccounts.google.com\u002Fgsi\u002Fclient`) across web architectures. Use when creating Google sign-in buttons, implementing Google One Tap with FedCM, integrating GIS in React\u002FNext.js\u002FAngular\u002FHTML, verifying ID tokens on backend runtimes (Python\u002FNode.js\u002FGo\u002FJava), enforcing Google Workspace domain restrictions (`hd`), securing client-side ID tokens via WebCrypto nonces or encrypted IndexedDB, embedding in cross-origin iframes via the Intermediate Iframe API (`https:\u002F\u002Faccounts.google.com\u002Fgsi\u002Fintermediate`), configuring Content Security Policy (CSP), COOP, and Permissions Policy (`identity-credentials-get`) headers, or handling sign-out and revocation. Don't use for legacy Google Sign-In (`gapi.auth2`), Google Cloud IAM service accounts, or Android\u002FiOS native Credential Manager.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fidentity\u002Fsign-in-with-google-web\u002FSKILL.md",[96,99],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[9,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123],"sign in with google web","sign","with","web","android","go","security","google workspace","google cloud","implement","policy","python","implementing","react","iam","permissions","buttons","secure","manager","identity","architectures","domain","runtimes",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":133,"publishedAt":52},"01M6998PHPDCAD684VW5WRG83D","dpop-adoption","Implement and debug OAuth 2.0 DPoP (RFC 9449) refresh token sender-constraining for WebCrypto, Node.js ES6, and browser runtimes integrating with Google's OAuth platform. Use when configuring non-extractable asymmetric key pairs (P-256), generating DPoP Proof JWTs for authorization code exchange and token refresh, or handling 400 use_dpop_nonce challenge retry loops at oauth2.googleapis.com\u002Ftoken. Don't use for unconstrained OAuth 2.0 flows (where refresh tokens are not bound to a client key pair), or for Google Cloud IAM \u002F service account authentication.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fidentity\u002Fdpop-adoption\u002FSKILL.md",[130,131,132],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},[134,135,9,109,136,137,138,139,140,141,115,142,143,144,145,146,147,120,123,42,36],"dpop adoption","adoption","es6","retry","authentication","flows","challenge","code","browser","loops","at","node","token","pair",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":160,"publishedAt":52},"01M6998M72TC73EEAQH4XC7EXW","retrieving-developer-knowledge","Searches, retrieves, and synthesizes official Google developer documentation across Google Cloud, AI\u002FGemini, Android, Chrome, Web, Flutter, Go, Firebase, and other Google developer platforms. Integrates with the Developer Knowledge MCP server (search_documents, get_documents, answer_query) or the Developer Knowledge REST API fallback. Use when searching for gcloud CLI commands, API syntax, IAM permissions, official documentation, architectural comparisons, or product choice overviews. Don't use for local filesystem lookups or non-Google documentation.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopers\u002Fretrieving-developer-knowledge\u002FSKILL.md",[154,155,158,159],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":156,"categoryName":157,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},[161,162,163,164,109,165,166,167,168,169,170,171,172,36,173,33,174,115,175,116],"retrieving developer knowledge","knowledge","developer","MCP","mcp server","official","developer documentation","get","search","local","choice","documents","query","across","documentation",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":52},"01M6998J2CZEXS9BES9S3WWFKC","migrate-to-rust","Clones, analyzes, plans, and migrates legacy codebases (C++, Fortran, Java, Python, C, Shell) from a GitHub URL or local directory to a modern, high-performance, deterministic, 100% Safe Rust architecture, tracking live telemetry across every task bucket, test failure\u002Ffix cycle, and Profile-Guided Optimization (PGO) stage, and producing a first-person AI storytelling report and interactive HTML infographic. Use when migrating a GitHub repository or local codebase to Rust, porting legacy C++, Fortran, Python, or Java workloads to memory-safe Rust, designing Struct-of-Arrays (SoA) or SIMD Rust architectures, or optimizing Rust ports with LLVM PGO. Don't use for unrelated non-Rust refactoring or single-line syntax questions.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopers\u002Fmigrate-to-rust\u002FSKILL.md",[],[183,184,185,186,187,188,189,190,112,191,192,193,194,195,196,170,197,198,199,36,200,201,174,202],"migrate to rust","rust","migrate","github","memory","performance","directory","safe","ports","llvm","soa","cycle","porting","fix","arrays","infographic","high-performance","URL","architecture","unrelated",{"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":212,"publishedAt":52},"01M6998GCC3K29WZ82KXMB9E02","finding-google-skills","Google platform decision and setup guidance, loaded on demand from Google's skill catalog. Use when a developer is choosing or setting up part of their stack, such as where to run a service, a database, storage, messaging, authentication, analytics, ads, or AI model serving, and a Google product is a reasonable candidate - whether or not a vendor is named - or when a request names a Google product or API. Brings in the matching Google skill so the answer can weigh Google options, their trade-offs, and when they are not the right fit. Skip when the stack is already settled on another provider and no Google product is named, or the task involves no platform choice.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdevelopers\u002Ffinding-google-skills\u002FSKILL.md",[209,210,211],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},[9,213,214,215,216,42,217,218,219,220,221,138,222,223,224,171,225,226,36,227,33],"finding google skills","storage","as","messaging","model","trade-offs","provider","answer","fit","catalog","up","decision","use","database","candidate",{"skillNo":229,"name":230,"nameZh":6,"description":231,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":232,"categories":233,"keywords":236,"publishedAt":52},"01M6998DWNHTH0BS6W1CY8ZXMP","workload-manager-basics","Use this skill to manage Google Cloud Workload Manager evaluations, rules, scanned resources, and validation results by using public client libraries and the REST API. Use when you need to inspect workload best-practice rules, create and run evaluations for Google Cloud general best practices, SAP, SQL Server, or custom organizational rules, review violations, export results to BigQuery, or automate Workload Manager through client libraries because no service-specific public CLI or MCP server is available. Don't use for general Google Compute Engine instance management, VPC configuration, or standard IAM auditing.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcloud\u002Fworkload-manager-basics\u002FSKILL.md",[234,235],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[237,238,119,239,9,164,240,109,165,241,242,41,243,36,244,33,115,50,245,47,246],"workload manager basics","workload","basics","cli","review","vpc","inspect","you","libraries","run"]