Loading ToolBench

Reading the current corpus…

seedream-mcp-server MCP server · D · ToolBench

← Browse

seedream-mcp-server

github.com/syh52/seedream-mcp-server

MCP server for SeeDream 4.5 image generation - enables Claude to generate images via natural language

2025-06-18+STDIO6 tools

56/100

Definition Quality71

Protocol Readiness42

Supportability39

Spec posture

Inferred effective spec 2025-06-18+·current baseline 2026-07-28

Static source inference · medium confidence · detected: stateful session

Deprecated protocol patterns detected

Summary

The server provides 6 tools with generally complete schemas and descriptions. All tools have input schemas with type definitions and parameter descriptions. Descriptions are detailed and helpful, particularly for Claude.ai compatibility warnings. However, there are significant gaps in output schema documentation, error handling guidance, and some parameter naming/clarity issues. Tool composition is reasonable but could be more refined. The descriptions, while good, contain example usage patterns that could mislead LLMs into literal reuse.

Tools (6)

seedream_blendwriteauthsource verified73/100

Combine elements from multiple images using SeeDream 4.5. ⚠️ **CLAUDE.AI USERS**: This tool WILL TIMEOUT on Claude.ai (takes 30-60 seconds). Use "seedream_submit" instead with mode="multi" for Claude.ai compatibility. Use this tool to blend 2-14 reference images together. Perfect for: - **Virtual try-on**: Dress person from image 1 in clothes from image 2 - **Face/Subject swap**: Put face/subject from image 1 onto body/scene in image 2 - **Style transfer**: Apply style of image 2 to content of image 1 - **Product visualization**: Put product from image 1 into scene from image 2 - **Character consistency**: Combine character traits from multiple references

seedream_editwriteauthsource verified74/100

Edit an existing image based on text instructions using SeeDream 4.5. ⚠️ **CLAUDE.AI USERS**: This tool WILL TIMEOUT on Claude.ai (takes 20-40 seconds). Use "seedream_submit" instead with mode="image" for Claude.ai compatibility. Use this tool to modify, enhance, or transform an existing image. Supports: - **Addition**: Add elements (accessories, objects, background elements) - **Deletion**: Remove unwanted elements - **Replacement**: Swap one element for another - **Modification**: Change colors, styles, lighting, expressions - **Style transfer**: Apply artistic styles to photos

seedream_generatewriteauthsource verified75/100

Generate images from a text description using SeeDream 4.5. ⚠️ **CLAUDE.AI USERS**: This tool WILL TIMEOUT on Claude.ai (takes 30-60 seconds). Use "seedream_submit" instead with mode="text" for Claude.ai compatibility. This is the primary tool for creating images from scratch. **Default: Generates 4 images per prompt** using streaming for fast response.

seedream_statusread only43/100

Issues (7)

CRITICALtool ↗

Output schemas are completely undocumented across all tools

seedream_generateseedream_editseedream_blendseedream_variationsseedream_statusseedream_submit

HIGHconstrained-input ↗

Semantic ambiguity in 'strength' parameter across edit and blend tools

seedream_editseedream_blend

HIGHtool-description ↗

seedream_status description is inadequate (18 chars of substance)

seedream_status

HIGHrecovery-guide ↗

No error handling guidance in any tool description

seedream_generateseedream_editseedream_blendseedream_variationsseedream_statusseedream_submit

MEDIUMtool-description ↗

Recommendations

Document output schema for every tool: what fields are returned, their types, and which IDs/references they provide for downstream tool composition. Example format: 'Returns: {images: [{url: string, size: string, created_at: ISO8601}], generated_count: number}'
Unify 'strength' parameter semantics: rename one to 'preservation_strength' (edit: 0=change wildly, 1=preserve closely) and keep 'reference_strength' for blend (edit: 0-1 to 'preserve more' at higher values). Document the semantic inversion clearly.
Expand seedream_status description to explain: When to call it (e.g., before calling submit? After each generation?), what capabilities it reveals (API health, available models, rate limits?), and how to interpret results. Aim for 100-150 chars of actionable detail.
Add error handling guidance to each tool description: 'If timeout occurs (30-60s), call seedream_submit instead for async mode.' 'If invalid_prompt error, rephrase using seedream_generate guidance.' 'If rate_limit error, wait and retry.'
Formalize conditional parameters: In seedream_submit schema, mark 'images' as conditionally required via oneOf/anyOf in JSON Schema, or add prominent callout in description: 'images: REQUIRED if mode is image or multi; omit if mode is text.'
Remove example prompts from descriptions; replace with formal constraints: Instead of 'Dress the person in image 1 with outfit from image 2', describe: 'Prompt should reference images by number (1-14) and describe the combination operation (blend, swap, style transfer).'

Spec posture evidence

Inferred effective spec: 2025-06-18+.

Relies on Stateful initialize / Mcp-Session-Id (removed; protocol is stateless) - make each request self-contained

Score history

Overall score trend

↑ 11 points across a rubric change (v1 → v2)

56/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-22	D	56	2025-06-18+	v2
2026-03-09	F	45	2024-11-05+	v1