Instant Meshes MCP Server

本项目用于通过MCP协议提供3D模型处理服务,基于Instant Meshes和pymeshlab对3D模型(OBJ/GLB)进行自动重拓扑、减面和质量分析,支持批量处理、URL输入、材质贴图保留、归档管理等功能。

Local serverstdioPython

What is the Instant Meshes MCP MCP server?

Instant Meshes MCP MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. 本项目用于通过MCP协议提供3D模型处理服务,基于Instant Meshes和pymeshlab对3D模型(OBJ/GLB)进行自动重拓扑、减面和质量分析,支持批量处理、URL输入、材质贴图保留、归档管理等功能。.

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

What the assistant can call

Once Instant Meshes MCP is connected, these are the calls the assistant has available:

  • input_model — 输入模型路径(支持GLB/OBJ文件、文件夹或URL)
  • target_faces — 目标面数
  • operation — 操作类型
  • auto — 自动选择(水密模型用simplify,有问题的用remesh)
  • simplify — 纯减面,保持原有网格结构
  • remesh — 重拓扑,修复网格问题
  • mode — 重拓扑模式(balanced/fine/coarse/fix_holes)
  • preserve_boundaries — 是否保持边界特征
  • preserve_uv — 是否保持UV坐标
  • create_archive — 是否创建归档文件夹(默认true)
  • quality — 网格质量分析(面数、拓扑、建议等)
  • folder — OBJ文件夹结构分析

Configuration and credentials

You will need 2 environment variables: PYTHONUNBUFFERED, BLENDER_PATH. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Instant Meshes MCP.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the instant meshes mcp mcp server does with a few real requests.

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Instant Meshes MCP's toolset — input_model, target_faces, operation and 11 more — is a fair guide to whether it matches your workflow. It is maintained by lxy2109; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
input_model输入模型路径(支持GLB/OBJ文件、文件夹或URL)
target_faces目标面数
operation操作类型
auto自动选择(水密模型用simplify,有问题的用remesh)
simplify纯减面,保持原有网格结构
remesh重拓扑,修复网格问题
mode重拓扑模式(balanced/fine/coarse/fix_holes)
preserve_boundaries是否保持边界特征
preserve_uv是否保持UV坐标
create_archive是否创建归档文件夹(默认true)
quality网格质量分析(面数、拓扑、建议等)
folderOBJ文件夹结构分析
validationOBJ包完整性验证
full执行所有可用分析

How to install the Instant Meshes MCP MCP server

{
  "mcpServers": {
    "instant-meshes-mcp": {
      "command": "python",
      "args": [
        "your_abs_dir/instant-meshes-mcp/server.py"
      ],
      "env": {
        "PYTHONUNBUFFERED": "1",
        "BLENDER_PATH":"your_blender3.6.abs_dir"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
PYTHONUNBUFFEREDConfiguration value read at startup.Optional
BLENDER_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Instant Meshes MCP to input model.
  • Use Instant Meshes MCP to target faces.
  • Use Instant Meshes MCP to operation.

Frequently asked questions

It connects Instant Meshes MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (input_model, target_faces, operation, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Instant Meshes MCP directly.