MCP
Responses API
OpenAI's current primary API for generating model output, designed as the successor to Chat Completions for agent-style applications.
In depth
OpenAI's current primary API for generating model output, designed as the successor to Chat Completions for agent-style applications. Inputs and outputs are typed Items, such as messages, function calls, and function call outputs, rather than a single message format. It includes built-in tools like file search, code interpreter, computer use, and remote MCP, and it can keep conversation state server-side through previous_response_id or the Conversations API. OpenAI recommends it for all new projects, while Chat Completions remains supported.
Primary source: developers.openai.com
Example
Inputs and outputs are typed Items, such as messages, function calls, and function call outputs, rather than a single message format.
Go deeper at Developers Digest
Hands-on guides, comparisons, and tutorials that cover MCP.
FAQ
Common questions
What is Responses API?
OpenAI's current primary API for generating model output, designed as the successor to Chat Completions for agent-style applications.
Why does Responses API matter for AI developers?
Responses API sits in the MCP part of the AI stack. Understanding it helps you make better decisions when building, debugging, and shipping AI features.
Where can I learn more about Responses API?
Developers Digest publishes tutorials and videos that cover MCP topics including Responses API. Check the blog and YouTube channel for hands-on walkthroughs.
Related
Related terms
MCP
MCP Tool
A function exposed by an MCP server that an AI agent can call to perform an action.
MCP
MCP Tasks
A Model Context Protocol extension, made first-class in the 2026-07-28 spec, that gives long-running work a proper home - builds, deployments, long agent runs, and batch jobs that do not finish inside a single request.
MCP
MCP Tool Poisoning
MCP tool poisoning is an attack where a malicious MCP server hides instructions in a tool's description, which the model reads but the user usually never sees.
Put this concept to work
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever