Skip to content
AdminKit

Structured content (MCP)

What is Structured content (MCP)?

Structured content is the optional structuredContent field a Model Context Protocol tool result can return alongside its usual content array, carrying the result as a plain JSON object validated against the tool's declared outputSchema instead of text a client has to parse. AdminKit's guide to securing an MCP server covers why that output still needs validation, not blind trust.

By AdminKit team, Netbase JSC · Updated

Structured content is an optional field, structuredContent, a Model Context Protocol tool can return in its call result alongside — not instead of — the usual content array of text, image or resource blocks, carrying the result as a plain JSON object rather than text a client has to parse back out itself. That object is ordinary JSON as standardized in RFC 8259, so a client’s existing JSON parser can read it without any format-specific decoding. A tool definition can declare an outputSchema, a JSON Schema describing the shape that result is expected to take; when it does, the server MUST return structured content conforming to it, and a client SHOULD validate the response against that schema before trusting it. For backwards compatibility, a tool returning structured content should still serialize the same JSON into a text block too, so an older client that only understands unstructured content doesn’t break. The specification notes this is unrelated to LLM “structured outputs” (schema-constrained model generation). A resource’s contents, by contrast, are read directly by URI rather than returned as a tool’s call result.

Structured content (MCP) is part of AdminKit’s AI agents & MCP cluster; the full AdminKit glossary lists other related terms.

Frequently asked questions

What does structuredContent carry that the usual content array doesn't?

A plain JSON object validated against the tool's declared outputSchema, instead of text blocks a client has to parse back out itself.

What must a server do if its tool declares an outputSchema?

It MUST return structured content conforming to that schema, and a client SHOULD validate the response against it before trusting it.

Why does a tool with structured content still include a text block?

For backwards compatibility -- an older client that only understands unstructured content still gets the same result serialized as text.