Manufacturing intelligence
for your entire organization.

# Analyze a model and get production config
import mimolabs

client = mimolabs.Client(api_key="mimo_enterprise_...")

# Upload and analyze
asset = client.upload("bracket-v3.step")
analysis = client.analyze(
    asset_id=asset.id,
    checks=["walls", "overhangs", "bridges", "part_id"]
)

# Configure for production
config = client.configure(
    asset_id=asset.id,
    material="nylon-pa12",
    quantity=50,
    quality="production"
)

print(f"Unit cost: ${config.unit_price:.2f}")
print(f"Lead time: {config.lead_days} days")

# CLI workflow for CI/CD integration
$ mimo analyze bracket-v3.step \
    --checks walls,overhangs,bridges \
    --format json \
    --fail-on-critical

# Batch configure a directory of models
$ mimo batch-configure ./parts/ \
    --material "nylon-pa12" \
    --quality production \
    --output ./configs/

# Export production-ready 3MF for all parts
$ mimo export ./configs/ \
    --format 3mf \
    --machine "bambu-x1c" \
    --output ./production/

Exported 12 production-ready files to ./production/

// MCP tool integration for AI agent pipelines
// Mimo exposes 200+ tools via MCP protocol

const server = new MCPServer({
  transport: "stdio",
  tools: mimolabs.getMCPTools({
    scope: "enterprise",
    orgId: "acme-corp"
  })
});

// Your AI agent can now call:
//   analyze_model, configure_print,
//   suggest_material, calculate_pricing,
//   generate_concept_images, export_3mf,
//   ... and 194 more tools

server.start();
// MCP server running on stdio