What is doubao-seedream-mcp AGENTS.md?

A set of AGENTS.md instructions describing a Cloudflare Workers MCP server that connects AI agents to Volcengine’s Doubao Seedream image-generation API. It documents the project’s architecture, files, authentication, and design decisions.

Use it when working on this server’s TypeScript code, MCP tools, Cloudflare Worker setup, or request authentication.

It gives a coding agent the project-specific context needed to make consistent changes safely.

How MingGH/doubao-seedream-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to MingGH/doubao-seedream-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/MingGH/doubao-seedream-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/MingGH/doubao-seedream-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/minggh/doubao-seedream-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/minggh/doubao-seedream-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/minggh/doubao-seedream-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/minggh/doubao-seedream-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/minggh/doubao-seedream-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/minggh/doubao-seedream-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 614 This file is loaded in full into every session.

When invoked 614 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00614	$0.00614
Opus 5.5	$0.00246	$0.00246
Sonnet 5.5	$0.00123	$0.00123
Haiku 4.5	$0.00061	$0.00061

Measured 2mo ago against content hash e26cc8ba5926, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

doubao-seedream-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Overview

This is a Cloudflare Workers-based MCP (Model Context Protocol) server that wraps the Volcengine Doubao Seedream image generation API. It exposes 4 MCP tools for AI agents to generate images.

Architecture

Runtime: Cloudflare Workers (stateless, Streamable HTTP transport)
MCP SDK: @modelcontextprotocol/sdk + agents (Cloudflare's agents framework)
Language: TypeScript
Build: Wrangler (Cloudflare's CLI tool)

Project Structure

src/
├── index.ts    # Worker entry point, MCP server factory, tool definitions
├── client.ts   # HTTP client for Volcengine Ark API
└── types.ts    # TypeScript type definitions

Key Design Decisions

Per-request server instantiation: Each request creates a new McpServer instance via createServer(apiKey, model). This is required by MCP SDK 1.26.0+ to prevent response leakage between clients.
Header-based authentication: API key and model are extracted from HTTP request headers (Authorization, X-Model), enabling multi-tenant usage without server-side secrets.
Closure-based config passing: Since MCP tool handlers don't receive HTTP headers directly, apiKey and model are captured via closure when tools are registered in createServer().
Dual return format: Tools support both url (text content with download link) and b64_json (MCP image content for direct rendering) via the response_format parameter.

Tools

Tool	Purpose
`text_to_image`	Generate single image from text prompt
`image_to_image`	Generate image from reference image(s) + text
`generate_image_group`	Generate multiple related images (sequential)
`search_and_generate`	Web search-enhanced image generation

External API

Endpoint: POST https://ark.cn-beijing.volces.com/api/v3/images/generations
Auth: Bearer token in Authorization header
Docs: https://www.volcengine.com/docs/82379/1541523

Development Commands

Read the full file on GitHub · 66 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 66 lines · 614 tokens per session scan A e26cc8ba5926

Subscribe to this mod's changes

doubao-seedream-mcp AGENTS.md is an instructions file published in the GitHub repository MingGH/doubao-seedream-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 614 tokens to every session, about $0.0025 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

doubao-seedream-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
doubao-seedream-mcp AGENTS.mdMingGH/doubao-seedream-mcp	Instructions file	0	5mo ago	MIT	A	614	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

doubao-seedream-mcp: Instructions file for Codex