Meshy MCP Server

Official

Overview Schema Source Related Servers Discussions Admin

Transform Image using AI

meshy_image_to_image

Edit or restyle images with a text prompt and reference images; supports background removal and multi-view output for 3D conversion.

Instructions

Edit or restyle images with a text prompt. Cost: nano-banana 3, nano-banana-2 6, nano-banana-2-lite 3, nano-banana-2-1 4, nano-banana-pro 9, GPT Image models 12 credits. Give exactly ONE reference source: input_task_id (all images of an earlier image task), reference_file_paths (local files; never base64-encode them yourself) or reference_image_urls.

To make the result 3D: meshy_image_to_3d with input_task_id = this task (multi-view output: meshy_multi_image_to_3d).

Example: { ai_model: "nano-banana-2", prompt: "make it red", input_task_id: "abc-123" }

Input Schema

TableJSON Schema

Name	Required	Description	Default
`prompt`	Yes	Text description
`ai_model`	Yes	Image model; ask the user.
`aspect_ratio`	No	Default '1:1'; '3:2' and '2:3' are GPT Image models only. Not with generate_multi_view.
`input_task_id`	No	A SUCCEEDED text-to-image / image-to-image task; all its images are the references. Wins over the other sources.
`response_format`	No	markdown (default) or json	markdown
`remove_background`	No	Transparent-background PNG (no effect on multi-view output).
`generate_multi_view`	No	Front/side/back views (input for meshy_multi_image_to_3d). Not with aspect_ratio.
`reference_file_paths`	No	1–5 absolute paths to local images; the server encodes them
`reference_image_urls`	No	1–5 public .jpg/.jpeg/.png/.webp URLs

Output Schema

TableJSON Schema

Name	Required	Description	Default
`status`	Yes
`message`	Yes
`task_id`	Yes
`estimated_time`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.6.4Oct 15, 2026

TDQS

A5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only cover the read/write/idempotency profile; the description adds genuinely new operational context: a per-model credit cost table, a precedence rule ('Wins over the other sources'), an exclusivity constraint, and a safety instruction never to base64-encode files yourself. These are exactly the traits annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then cost, then the reference-source constraint, then the 3D pointer, then an example. Dense but every sentence carries a distinct actionable fact with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need no explanation. For a 9-parameter tool with model selection, cost, and source-exclusivity rules, the description supplies everything an agent needs to construct a correct call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so 3 is the floor, but the description adds meaning the schema cannot encode: the cross-parameter exclusivity of the three reference sources, the precedence of input_task_id, the per-value cost of each ai_model, and the file-handling instruction for reference_file_paths.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Edit or restyle images with a text prompt') and implicitly separates itself from the generation sibling meshy_text_to_image. It also names the downstream sibling meshy_image_to_3d and its multi-view variant, so an agent can place the tool in the pipeline without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells the agent to give exactly ONE reference source and enumerates the three mutually exclusive options with their differences (task id vs local files vs URLs). It also gives the routing rule for 3D follow-up work and closes with a concrete invocation example.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.