Meshy MCP Server

Official

Overview Schema Source Related Servers Discussions Admin

Auto-Rig 3D Character

meshy_rig

Auto-rig a textured humanoid GLB into an animation-ready skeleton, including walk and run animations for character motion.

Instructions

Auto-rig a humanoid character for animation. Cost: 5 credits, including free walking + running animations (GLB + FBX, separate files).

REQUIREMENT: a textured humanoid (biped) model with a clear body and limbs, ≤300,000 faces (checked first; remesh if over). model_url must be a .glb facing +Z. Generate characters with pose_mode "t-pose" for the best rig.

Next steps: meshy_download_model (task_type "rigging") returns the rigged model and walk/run URLs. Other actions: meshy_list_animations → meshy_animate. A described motion: meshy_text_to_motion → meshy_animate with motion_task_id.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`model_url`	No	Public URL of a textured humanoid .glb (max 400 MB), or a GLB data URI (max 100 MB)
`height_meters`	No	Character height in meters; helps scaling
`input_task_id`	No	A SUCCEEDED task with a textured humanoid model
`response_format`	No	markdown (default) or json	markdown
`texture_image_url`	No	The model's UV-unwrapped base color texture (.png, max 20 MB)

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

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly=false, destructive=false, idempotent=false, openWorld=true, so the safety profile is covered. The description adds genuinely useful behavior beyond that: a concrete cost (5 credits), included walk/run animations in GLB+FBX, the face-count precheck, and the .glb orientation constraint. It does not describe async/polling behavior for the resulting task, which is the one gap.

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

Conciseness4/5

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

Front-loaded with purpose, cost, and included outputs, then a clearly delineated REQUIREMENT block and a Next steps block. Efficient and scannable; slightly verbose with the chained next-step arrows, but every clause earns its place.

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?

For a create-style rigging tool with an output schema and full annotation coverage, the description supplies the prerequisites, cost, deliverables, and the routing to download/animate tools. Nothing an agent needs to invoke it correctly appears missing.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents all five parameters including the model_url format and the texture_image_url pattern ref. The description reinforces the .glb/+Z constraint and mentions pose_mode, which is not even present in the schema (a minor mismatch). Baseline 3 is appropriate since the schema carries the parameter burden.

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+resource ("Auto-rig a humanoid character for animation") and immediately constrains it (textured humanoid/biped). An agent can distinguish this from meshy_animate, meshy_text_to_motion, and the *_to_3d siblings 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 states upfront requirements (textured biped, ≤300k faces, .glb facing +Z, pose_mode t-pose for best results) and names routing alternatives: meshy_download_model with task_type "rigging", meshy_list_animations → meshy_animate, and meshy_text_to_motion → meshy_animate. This is textbook when/when-not/alternative guidance.

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