1z0-1157-26 Agentic AI Foundations Associate Questions and Answers

MCP standardizes how external systems expose capabilities to an AI application, but the model does not need to reason about the transport or deployment location of each capability. Once an MCP server's tools are discovered and incorporated into an agent's available tool set, they are represented to the model as callable tools with names, descriptions, and input schemas. Locally implemented function tools are presented through essentially the same model-facing tool abstraction. OpenAI's Agents SDK documentation explicitly states that tools obtained from configured MCP servers are added to the agent's list of available tools, alongside ordinary tools. Therefore, from the LLM's perspective, both are selected and invoked through the tool-calling mechanism rather than through separate network-specific interfaces.

Authentication, network connectivity, server lifecycle, authorization, and actual execution remain responsibilities of the application/MCP infrastructure. They are deliberately abstracted away from the model. Therefore, option B precisely captures the architectural consistency described in the course question.

Study Guide reference/topic: Model Context Protocol (MCP) Fundamentals — MCP tools, tool discovery, agent tool abstraction, and client-server integration.

===============

The OpenAI Responses API is an inference and agent-interaction interface. At its fundamental level, an application supplies input together with a selected model and optional instructions, tools, or other configuration; the model then produces a response containing generated output. The uploaded course material states this core purpose directly and identifies C as correct.

OpenAI's current API reference defines the Responses endpoint as creating a model response from text, image, or file inputs and returning generated text, structured JSON, tool calls, or other supported response items. The input field provides content to the model, while the response object's output array contains items generated by the model.

Although modern Responses API functionality extends beyond simple text generation—for example, built-in tools, function calling, conversation state, structured outputs, and agentic workflows—the basic abstraction remains model input followed by generated model output.

It is not a prompt-compression billing service, a local model-hosting environment, or a foundation-model training API. Those alternatives describe completely different system responsibilities.

Therefore, C accurately expresses the core purpose being tested.

Study Guide reference/topic: OpenAI Responses API and Agents SDK — Responses endpoint, model input, generated output, tools, and agentic workflows.

===============

The Vector Stores API provides infrastructure for ingesting content and retrieving the portions that are semantically relevant to a query. Files associated with a vector store can be chunked and prepared for vector-based retrieval, allowing applications and agents to locate content based on semantic similarity rather than only exact lexical matches .

OpenAI's official Vector Stores API supports searching a vector store with a natural-language query and returns relevant content chunks together with similarity scores. The API also supports attaching files to vector stores and configuring the chunking strategy used during ingestion. This architecture is foundational to retrieval-augmented generation and File Search workflows: source material is indexed, a user query retrieves semantically related chunks, and those chunks can then provide grounded context to a model.

Language translation is a generative-model task. Object Storage encryption is a cloud-storage security function, while video streaming is unrelated to the purpose of a vector store.

Accordingly, “Indexing and retrieving data by meaning” is the technically correct description and is also the answer specified by the uploaded question source.

Study Guide reference/topic: OpenAI Responses API and Agents SDK — Vector Stores, semantic retrieval, chunking, File Search, similarity ranking, and RAG.

===============

The MCP Host is the top-level AI application in the Model Context Protocol architecture. Its responsibility is to coordinate the broader application experience and manage the MCP clients used to connect with one or more MCP servers. The official MCP architecture specifies that an MCP host creates a separate MCP client for each server connection and describes the host as the AI application that coordinates and manages one or multiple MCP clients.

The distinction between host, client, and server is essential. An MCP client maintains the protocol connection to a corresponding MCP server. An MCP server exposes capabilities such as tools, resources, and prompts. The host integrates these connections with the AI application's model and user interaction flow. Therefore, it is incorrect to define the host as the protocol specification itself, an external REST service, or the component that necessarily implements each individual tool.

Option D most accurately represents this orchestration role: the host coordinates the LLM-facing application and MCP client connections to the servers providing capabilities. The source question identifies D accordingly.

Study Guide reference/topic: Model Context Protocol (MCP) Fundamentals — MCP Host, MCP Client, MCP Server, and client-server architecture.

===============

Modern LLM-based agents are specifically designed to avoid requiring every possible execution path to be predetermined. The uploaded course material therefore correctly identifies “Requiring every execution path to be predefined” as the behavior that is NOT characteristic of an agent.

OpenAI defines agents as systems capable of independently accomplishing workflows using an LLM to manage workflow execution and make decisions. An agent can determine when a workflow is complete, correct its actions after receiving observations, and dynamically select tools according to the current state. This differs fundamentally from conventional deterministic automation in which developers encode every branch and execution path beforehand.

Agents commonly pursue objectives across multiple reasoning-and-action cycles. They can invoke external APIs, databases, search systems, or other tools; inspect the resulting observations; and choose subsequent actions. A typical agent loop continues until an exit condition is reached rather than following one permanently fixed sequence.

Predetermined rules may still be used for safety, permissions, and guardrails, but the complete path toward the goal does not need to be pre-scripted.

Therefore, D is the correct answer.

Study Guide reference/topic: Introduction to AI Agents — autonomy, agent loops, observations, dynamic tool use, multi-step goal execution, and deterministic workflows.

Streamable HTTP is the standard MCP transport intended for remote or network-accessible client-server communication. Current MCP architecture documentation distinguishes it from STDIO by explaining that Streamable HTTP uses HTTP POST for client-to-server communication and can optionally use Server-Sent Events for streaming. It enables communication with remote MCP servers and can support standard HTTP authentication mechanisms.

The MCP transport specification further establishes two standard transport mechanisms: stdio and Streamable HTTP . With STDIO, the client launches an MCP server as a local subprocess and exchanges JSON-RPC messages through standard input and standard output. That pattern is therefore most appropriate for local process integration. By comparison, a Streamable HTTP server operates as an independent service and can handle multiple client connections, making it suitable for centralized or cloud-hosted MCP deployments.

Raw TCP sockets and local Unix pipes are not the standard remote MCP transport defined by the protocol. Therefore, C is correct and matches the supplied source material.

Study Guide reference/topic: Model Context Protocol (MCP) Fundamentals — STDIO versus Streamable HTTP transport and remote MCP deployment.

===============

The OpenAI Agents SDK implements an iterative agent loop in which the model determines which available capability should be invoked, receives the resulting observation, and can then make another tool call based on that updated context. Consequently, the model first requests multiply(15, 8) . The function executes and returns 120 ; that tool output is supplied back to the model. The model then determines that the remaining operation requires divide(120, 3) and requests the second tool.

OpenAI describes Agents as LLMs equipped with tools and explains that the SDK runtime manages repeated model/tool interactions until the workflow produces final output. Function tools expose schemas and executable implementations to this orchestration process.

The Runner is responsible for coordinating the loop; it does not independently substitute its own arithmetic logic for the model's tool decisions. Similarly, the SDK does not synthesize a new combined function when two distinct tools are required, nor does it invoke every available tool without reason.

The uploaded question source explicitly marks the sequential multiply-then-divide behavior as correct.

Study Guide reference/topic: OpenAI Responses API and Agents SDK — agent loop, sequential function calling, tool observations, and Runner orchestration.

===============

OCI production AI architectures use the standard OCI observability and governance services to provide operational visibility and accountability. OCI Logging collects and centralizes service and application logs; OCI Generative AI hosted applications can expose deployment logs that open directly in OCI Logging and the Observability and Management service. OCI Monitoring supplies metrics and alarms for monitoring resource health and operational conditions. OCI Audit records calls made to supported OCI public API endpoints, providing an authoritative record of administrative and resource-management actions for investigation and compliance. Oracle's architecture guidance specifically recommends enabling OCI Logging, OCI Monitoring, and OCI Audit logs for critical AI-platform components. The services in the other options have legitimate OCI purposes, but they do not collectively represent the principal observability-and-auditing stack. Therefore, option A is the verified combination. Oracle Docs

===============

In MCP, Tools are the primitive explicitly designed to be model-controlled. They represent executable functions that an MCP server exposes so that a language model can take actions, retrieve information, query databases, invoke APIs, modify files, or perform computations. The uploaded question set identifies Tools as the correct answer.

The official MCP specification defines three principal server primitives with different control models: Prompts are user-controlled , Resources are application-controlled , and Tools are model-controlled . Tools can be discovered by the model-facing application and invoked automatically according to the model's contextual interpretation of the user's request.

Resources differ because they primarily provide contextual data such as file contents or database schemas. Prompts provide reusable templates or instructions normally selected through user interaction. “Schemas” are not one of the three MCP primitives in this control hierarchy; schemas describe structures such as tool parameters rather than constituting a standalone primitive.

Therefore, A is correct.

Study Guide reference/topic: Model Context Protocol (MCP) Fundamentals — MCP primitives, Tools, Resources, Prompts, control hierarchy, and tool invocation.

===============

Oracle AI Vector Search supports both in-database embedding generation and external embedding providers , making A the correct answer. The supplied question source identifies the same combination.

For in-database processing, Oracle AI Database includes an ONNX runtime. Compatible ONNX embedding models can be imported as database objects and invoked directly through SQL using functions such as VECTOR_EMBEDDING . This allows vectorization to occur without moving source data outside the database.

Oracle also supports REST-based embedding generation. DBMS_VECTOR.UTL_TO_EMBEDDING and related APIs can call external or local providers. Officially documented providers include OCI Generative AI, Cohere, OpenAI, Google AI, Hugging Face, Vertex AI, Mistral, Ollama, and Private AI, depending on the operation and configuration.

Manual Python export/import workflows are technically possible in custom architectures, but they are not the supported approaches being tested. Option C is explicitly false because Oracle supports in-database ONNX inference.

Therefore, A correctly captures Oracle's native and external embedding-generation strategies.

Study Guide reference/topic: Agentic AI for Oracle AI Database — ONNX Runtime, VECTOR_EMBEDDING, DBMS_VECTOR, REST embedding providers, and AI Vector Search.

===============

The Agents SDK separates validation at the input and output boundaries of an agent workflow. Input guardrails evaluate the initial user input, while output guardrails evaluate the final agent output before that result is accepted and returned. This makes B the intended architectural answer. A technical nuance is that current SDK input guardrails support both blocking and parallel execution: with blocking execution, validation completes before agent execution starts; with the default parallel mode, the guardrail can execute concurrently with the agent. Output guardrails, however, operate on the completed final output and always execute after the agent finishes producing it. Guardrails are runtime controls rather than decisions the LLM must explicitly request. OCI's agentic architecture similarly emphasizes governed model-and-tool workflows, making these validation boundaries important when implementing production AI agents. OpenAI GitHub

===============

In MCP architecture, executable capabilities are exposed by an MCP server . The server advertises available tools through the protocol, including each tool's name, description, and input schema. An MCP client discovers those capabilities using tools/list and invokes a selected tool through tools/call . The uploaded course material therefore correctly identifies the separate MCP server as the location associated with production MCP tool implementations.

The official MCP architecture defines an MCP server as the program that provides context and capabilities to MCP clients. It also defines tools as executable functions exposed by servers for actions such as API calls, database queries, or file operations. During execution, the AI application routes the model-generated tool call through the corresponding MCP client to the appropriate MCP server.

Tools are not encoded into an LLM's trained weights. Locally defined function tools can indeed be declared in agent code, but that is distinct from an MCP-served tool. Likewise, the MCP client handles communication and protocol coordination; it is not conceptually the server-side implementation host.

Therefore, A is architecturally correct.

Study Guide reference/topic: Model Context Protocol (MCP) Fundamentals — MCP Servers, tool hosting, tools/list, tools/call, and client-server separation.

===============

Memory poisoning is an agent-security attack in which malicious, misleading, or attacker-controlled information is introduced into memory that the agent may reuse in future reasoning or actions. The uploaded course source defines it as malicious content inserted into persistent memory stores and identifies C as correct.

Oracle's current AI Agent Memory security guidance explains why persistent memory must be treated as a security-sensitive surface. Model-derived memories, summaries, context cards, metadata, and retrieved records can become persistent state and later be inserted into prompts. Oracle therefore advises treating memory-derived content as untrusted and emphasizes that write-capable memory paths can influence future prompts and retrieval results.

The broader agent-security definition is also explicit in OWASP's Agentic AI guidance: memory poisoning involves malicious data being persisted in agent memory so that it can influence future sessions or behaviors.

This differs from temporary context-window pressure, SQL injection, or physical RAM corruption. The essential security property is persistence : compromised memory can affect later reasoning long after the original malicious interaction.

Therefore, C is correct.

Study Guide reference/topic: Introduction to AI Agents — agent memory, persistent state, memory poisoning, prompt injection persistence, and agent security.

Oracle Autonomous AI Database includes a managed MCP Server that is natively integrated with the database rather than requiring customers to deploy and operate a separate MCP infrastructure tier. Oracle states that the service eliminates the need to manage customer-side MCP server infrastructure, directly reducing deployment and operational overhead. It also integrates with database identity, authorization, governance, auditing, network controls, database roles, Virtual Private Database policies, ACLs, and private endpoints.

Architecturally, this is significant because MCP-exposed Select AI Agent tools remain close to the database security boundary. The managed multi-tenant MCP layer can expose approved tools while relying on established database governance controls. Oracle's architecture describes a Unified Security Layer, managed MCP Server, and Select AI Agent Framework working together as an integrated stack.

The capability does not remove SQL, move database execution outside the database, or require a universal MCP host. Instead, its primary advantage is minimizing additional infrastructure while preserving strong database-native control over access and operations. Thus C is technically correct and matches the uploaded source.

Study Guide reference/topic: Agentic AI for Oracle AI Database — Autonomous AI Database MCP Server, native security integration, governance, and managed MCP infrastructure.