# Structured Output MCP Agent

The Structured Output MCP Agent MCP server turns a prompt and field schema into validated typed JSON. Use it when an agent response must follow a defined structure.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 3042 installs
- Author: a2a
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/a2a/structured-output-agent
- Updated: 2026-05-31
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/structured-output-mcp-agent

## What it does

Structured Output MCP Agent exposes `invoke` for requests that need a schema-bound result. The tool sends the prompt and field definition through Instructor with Gemini 2.5 Flash on Vertex AI, then returns typed JSON that can be passed to application code.

The `selftest` tool runs the live agent against a fixed input. Its response includes the produced result, an assertion score, and a trust manifest containing a signed Agent Card, JWKS, the governance and licence chain, the safety posture, and a proof link for each claim.

The service is reached over HTTP at `https://structured-output-agent--a2a.run.tools`. It can be connected to Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, or Gemini CLI. Since `invoke` uses Gemini 2.5 Flash on Vertex AI, that service is part of its runtime path.

## Requirements
- Remote server: `https://structured-output-agent--a2a.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http structured-output-agent https://structured-output-agent--a2a.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add structured-output-mcp-agent --url https://structured-output-agent--a2a.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "structured-output-mcp-agent": {
            "url": "https://structured-output-agent--a2a.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "structured-output-mcp-agent": {
            "type": "http",
            "url": "https://structured-output-agent--a2a.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http structured-output-mcp-agent https://structured-output-agent--a2a.run.tools
```

## When to use it
- turn a prompt and field schema into typed JSON
- validate a structured result before using it in code
- run a live self-check against a fixed input
- inspect trust claims with proof links

## Example prompts
- Use `invoke` to return this request as typed JSON that follows the supplied field schema.
- Run `selftest` and show the result, assertion score, and trust manifest.
- Send this prompt through `invoke` and validate the returned JSON against the schema.

## Similar
- [structured-output-extractor](https://affpapa.org/en/nevibecode/skills/structured-output-extractor.md) — skill · 323 installs
- [create-structured-output](https://affpapa.org/en/nevibecode/skills/create-structured-output.md) — skill · 154 installs
- [gemini-live-api](https://affpapa.org/en/nevibecode/skills/gemini-live-api.md) — skill · 5200 installs
- [google-agents-cli-publish](https://affpapa.org/en/nevibecode/skills/google-agents-cli-publish.md) — skill · 587200 installs
- [Google AI Search MCP](https://affpapa.org/en/nevibecode/mcp/google-ai-search-mcp.md) — MCP server · ★ 7 repo stars
- [vertex-infra-expert](https://affpapa.org/en/nevibecode/skills/vertex-infra-expert.md) — skill · 154 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
