Blender MCP
Website
Community plugin to control Blender 3D with any LLM of your choice. Not affiliated with the official Blender Foundation.
Is Blender MCP safe? Promising trust profile, but some evidence still deserves review.
Compare Blender MCP
How does it stack up against its MCP Servers neighbours?
Pick any agent to compare →In detail: Blender MCP scores 57.5/100 (Grade C), ranked #737 of 1371 tracked open-source AI agent projects, on evidence coverage C (2 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 3.2/10; 36% of recent commits are signed; last pushed 2026-10-06. Every point is earned from checkable signals — never paid placement. How scoring works →
What Blender MCP can reach, and who runs it
Checked 2026-10-09, each with its source. PUBLISHER is the company's or project's own statement, which we haven't verified; CHECKED is something we observed ourselves. These facts describe the product. They don't change its score.
What it can reach
- PUBLISHER By default the AI can run any Python code in Blender through its execute_blender_code tool; BLENDER_MCP_SAFE_MODE=1 checks each script first and blocks risky code. The README says to always save your work before using it.
- PUBLISHER The Blender add-on runs a socket server that listens on localhost by default. It has no authentication or encryption, so anyone who can reach its port can run Python inside Blender.
Where your data goes
- PUBLISHER Sends a minimal anonymous usage record by default (tool name, success, timing, versions, operating system). Prompts, generated code and screenshots are collected only if you opt in, and DISABLE_TELEMETRY=true turns telemetry off entirely. It says telemetry data may be used for research and to train AI models.
Security practice
- CHECKED OSV lists 1 advisory (medium), published in July 2026, for its PyPI package under its earlier name, blender-mcp. The repository has no SECURITY.md, and GitHub private vulnerability reporting is off.
How Blender MCP could raise its score
Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.
- Raise the OSSF Scorecard from 3.2 to 9.0lowest checks: CI-Tests 0, CII-Best-Practices 0, Dependency-Update-Tool 0 +12.2 → 69.7 B · #212 of 781
- Sign every commit36% signed today +3.2 → 60.7 C · #351 of 781
Chain of custody
Scanners check what the code says. This traces who ships Blender MCP and whether that has changed: from the source repository, through how changes are reviewed and released, to the code you run. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.
-
Source Partly signed
github.com/ahujasid/mcp-for-blender, MIT, last pushed 2026-10-06. 36% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.
-
Review and release Weak
OpenSSF Scorecard rates the repository's practices 3.2/10 (scanned Sep 23, 2026, refresh pending). The checks that decide who can get a change released:
- Code Review2
- Branch Protection6
- Signed Releasesn/a
- Dangerous Workflown/a
- Token Permissionsn/a
- Pinned Dependencies0
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 6CI-Tests 0CII-Best-Practices 0Code-Review 2Contributors 3Dangerous-Workflow -1Dependency-Update-Tool 0Fuzzing 0License 10Maintained 10Packaging -1Pinned-Dependencies 0SAST 0Security-Policy 0Signed-Releases -1Token-Permissions -1Vulnerabilities 0 -
Published packages None
No registry package. Blender MCP is used from its repository, so what you run is whatever you check out: pin a release tag or commit.
Changes to this chain
No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of Blender MCP.
Evidence behind this score
Coverage C: 2 of 5 independent evidence types found.
- GitHub repository data
- Package downloads (missing)
- Supply-chain checks
- Public actions (missing)
- Community mentions (missing)
Verify this score yourself
Every build re-issues Blender MCP’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.
What this score doesn’t check
It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.
How Blender MCP compares in MCP Servers
- #397 ripwire 57.5 ±0
- #398 OpenResearch MCP 57.5 ±0
- #399 Blender MCP 57.5 this agent
- #400 Joplin MCP Server 57.3 −0.2
- #401 Xiaohongshu MCP 57.2 −0.3
Bars show each HVTrust score; the tick marks Blender MCP’s 57.5.
Where the 57.5 comes from
HVTrust dimensions vs the MCP Servers average
57.5 / 100 · 100.0% confidenceBlender MCP MCP Servers average (781 agents)
Quick Trust Read
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade C reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage C is separate — it grades how many independent signal types back the score (2 of 5), so a high score on thin evidence stays visible. Full methodology →
Rank Trend
Activity & Reach
Analysis
Activity Inputs
87.9 / 100Common questions about Blender MCP
Does Blender MCP publish package provenance?
Does Blender MCP have an OpenSSF Scorecard?
Is Blender MCP actively maintained?
What license does Blender MCP use?
Are Blender MCP's commits signed?
Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.
AI agent surface
MCP, providers, tool surface
These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →
- MCP signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
Detected changes to Blender MCP's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.
Maintain Blender MCP?
For maintainers
HVTrust scores Blender MCP from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.
Reputation Timeline
Signal history
Embed Badge Badge guide for maintainers →
For maintainers
[](https://hvtracker.net/agents/blender-mcp)
<a href="https://hvtracker.net/agents/blender-mcp"><img src="https://hvtracker.net/badge/blender-mcp.svg" alt="HVTrust"></a>
Other agents in MCP Servers
GitHub REST API (repo, commits, stars, forks, license) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON