Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ekakit/lightfast-mcpnpx agentmods add rules/ekakit/lightfast-mcp/blender-integrationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/ekakit/lightfast-mcp/blender-integration)<a href="https://agentmods.dev/rules/ekakit/lightfast-mcp/blender-integration"><img src="https://agentmods.dev/badge/rules/ekakit/lightfast-mcp/blender-integration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/ekakit/lightfast-mcp/blender-integration"><img src="https://agentmods.dev/badge/rules/ekakit/lightfast-mcp/blender-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01150 |
| Opus 5.5 | $0.00000 | $0.00460 |
| Sonnet 5.5 | $0.00000 | $0.00230 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
blender-integration scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -f http://localhost:8001/health || echo "❌ Blender server not responding" How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blender Development Workflow
When editing Blender MCP files, follow this specific workflow:
Immediate Actions After Blender Code Changes
- Restart Blender Server: Kill and restart the Blender MCP server
- Test Blender Connection: Verify connection to Blender instance
- Test New/Modified Tools: Use Cursor chat to test Blender tools
- Check Blender Addon Status: Ensure addon is still active
Automatic Commands for Blender Development
After Editing Server Files (src/lightfast_mcp/servers/blender/)
# Stop any running Blender server
pkill -f lightfast-blender-server
# Run fast tests
nox -s test_fast
# Start Blender server in background for testing
uv run lightfast-blender-server &
BLENDER_PID=$!
# Wait for server startup
sleep 3
# Test server is responding
curl -f http://localhost:8001/health || echo "❌ Blender server not responding"
# Test via orchestrator
uv run lightfast-mcp-orchestrator ai
After Editing Blender Addon (addons/blender/)
# Note: Blender addon requires manual reload in Blender
echo "🔄 Blender addon updated - reload addon in Blender:"
echo " 1. Open Blender Preferences > Add-ons"
echo " 2. Find 'Lightfast Blender MCP Addon'"
echo " 3. Disable and re-enable the addon"
echo " 4. Check the Lightfast MCP panel shows 'Server active'"
Blender Development Checklist
Before Testing Blender Tools
- Blender is running (open Blender application)
- Blender addon is installed and enabled
- Blender MCP panel shows "Server active" status
- No port conflicts on 8001 (Blender MCP) and 9876 (Blender internal)
- Network connectivity between MCP server and Blender
Tool Development Validation
- Tool descriptions mention 3D/Blender context
- Error handling for Blender API exceptions
- Input validation for Blender object names
- Clear documentation of what the tool does in Blender
- Test with both empty and populated Blender scenes
Blender Testing Workflow
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 167 lines · 0 tokens per session scan A 1a531243ee9e
blender-integration is a cursor rule published in the GitHub repository ekakit/lightfast-mcp (2 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,150 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.