Our grade: 4 checks
Based on public data, not a full audit. See how we grade. Something changed? Request a re-grade.
Community rating
- 5 0
- 4 1
- 3 9
- 2 8
- 1 0
Trust in production
- Trust it - 0%
- With caveats - 56%
- Wouldn't - 44%
39% would recommend this server
How reviewers scored it
- Setup & docs 2.6
- Auth experience 2.4
- Reliability 2.6
- Maintainer responsiveness 3.6
Why it got a D
The Blender MCP most people use: an MIT-licensed community project by Siddharth Ahuja with about 33,500 GitHub stars and 46 contributors, not affiliated with the Blender Foundation. It has two parts, a stdio MCP server (PyPI mcp-for-blender, renamed from blender-mcp) and a Blender addon that listens on localhost port 9876. Its main tool, execute_blender_code, runs any Python the model writes inside Blender with your user's rights, and safe mode (BLENDER_MCP_SAFE_MODE=1, which blocks file, process and network access) is off by default. Its one CVE, CVE-2026-66004 (a Poly Haven download could write files outside the asset folder), was fixed in 1.6.5, about two months after it was reported in public. A minimal anonymous usage record is sent by default; set DISABLE_TELEMETRY=true to stop it. Biggest deduction: there is no authentication anywhere, so any program on your machine that can reach port 9876 can run Python in Blender, and turning on remote connections exposes that to your network.
How to connect
// .cursor/mcp.json (project) or global MCP settings
{ "mcpServers": { "blender": { "command": "uvx",
"args": ["mcp-for-blender"] } } }claude mcp add blender uvx mcp-for-blender// claude_desktop_config.json
{ "mcpServers": { "blender": { "command": "uvx",
"args": ["mcp-for-blender"] } } }Is MCP for Blender (ahujasid/mcp-for-blender, formerly blender-mcp) safe?
Is MCP for Blender (ahujasid/mcp-for-blender, formerly blender-mcp) safe to use?
MCP for Blender (ahujasid/mcp-for-blender, formerly blender-mcp) grades D (notable weaknesses - review closely). There is no login: anything that can start or reach it gets its full access. Past advisories were fixed slowly, so stay on the latest release. It can run model-controlled code or uses a plaintext remote connection, so run it isolated with no credentials.
Does MCP for Blender (ahujasid/mcp-for-blender, formerly blender-mcp) have known vulnerabilities?
Not in our current data: it has no open CVEs or advisories. We re-check as new ones are published.
Does MCP for Blender (ahujasid/mcp-for-blender, formerly blender-mcp) support authentication?
No. It has no login of its own, so limit who and what can start it.
Alternatives in Developer Tools
- A Atlassian Rovo MCP ServerOfficial hosted Atlassian server for Jira, Confluence, Jira Service Management, Compass, Bitbucket, Loom, Goals, Projects, and Teams, with OAuth 2.1 sign-in.
- A Buildkite MCP ServerOfficial Buildkite server for pipelines, builds, jobs, logs, annotations, and Test Engine data, hosted or local.
- A Dynatrace Remote MCP ServerDynatrace's hosted MCP server, running inside your Dynatrace SaaS environment, to run and explain DQL, look into problems, vulnerabilities and Kubernetes events, and forecast time series.
- A GitHub MCP ServerOfficial GitHub server for repos, issues, pull requests, Actions, and code security, hosted or local.
- A GitLab MCP ServerGitLab's built-in MCP server for projects, merge requests, work items, code, and CI pipelines, on GitLab.com or your own instance.
Embed this badge
[](https://trustedmcp.io/servers/blender-mcp)<a href="https://trustedmcp.io/servers/blender-mcp"><img src="https://trustedmcp.io/badge/blender-mcp.svg" alt="TrustedMCP grade D" height="80"></a>Community reviews
Went back to calling the API directly
I wanted to like this one. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list.
Used for Looking up for Blender (ahujasid/-for-blender, formerly blender-) data without leaving the editor
- Setup & docs 2/5
- Auth experience 3/5
- Reliability 2/5
- Maintainer responsiveness 3/5
Not ready for anything that matters
Ran into problems pretty quickly. Runs locally over stdio, so startup is instant and nothing leaves my machine unless a tool calls out.
Used for Onboarding new devs with an agent that answers repo questions
- Setup & docs 3/5
- Auth experience 2/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Useful, with a few rough edges
I like it, with reservations. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list.
Used for Debugging sessions in Cursor
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 5/5
Solid core, fiddly setup
Good for experimenting, still deciding about production. Filed an issue and got a reply within two days. There is no auth layer, so whatever can reach it can use it. I keep it local only. Fine in production if you sandbox it.
Used for CI failure investigation
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Security story needs work
Not what I expected from the description. Local stdio process, easy to start and stop from the client. I will check back in a few releases.
Used for Scripting routine maintenance tasks
- Setup & docs 1/5
- Auth experience 1/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Struggled to get it stable
Setup was rough and the result was flaky. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list.
Used for Keeping project tickets in sync with code changes
- Setup & docs 1/5
- Auth experience 1/5
- Reliability 1/5
- Maintainer responsiveness 3/5
Capable but needs guardrails
Took longer to configure than I expected. There is no auth layer, so whatever can reach it can use it. I keep it local only.
Used for Code review summaries for pull requests
- Setup & docs 2/5
- Auth experience 3/5
- Reliability 4/5
- Maintainer responsiveness 4/5
Does the job, docs could be better
Some tools are great, a couple feel half finished. Releases come often and the changelog is clear. There is no auth layer, so whatever can reach it can use it. I keep it local only.
Used for Pairing with Claude Code on a monorepo
- Setup & docs 4/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 5/5
OK for read-only work
Useful tool, though I would not hand it to a junior unsupervised. It is community maintained, so I pin the version and read the changelog before upgrading. Worth it, just do not skip the hardening steps.
Used for Code review summaries for pull requests
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 2/5
- Maintainer responsiveness 5/5
Fine once configured properly
Works well enough for what I need. You can tell it is actively maintained, the rough edges keep getting fixed. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box. Keep permissions tight and it is a good tool.
Used for Generating boilerplate from existing patterns
- Setup & docs 3/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 4/5
Mixed feelings after two weeks
Good for experimenting, still deciding about production. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list. It is community maintained, so I pin the version and read the changelog before upgrading. I would use it in prod, but only with a human approving writes.
Used for Pairing with Claude Code on a monorepo
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 4/5
- Maintainer responsiveness 3/5
Too much access for my comfort
Gave it a fair shot over two weeks. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box. It is community maintained, so I pin the version and read the changelog before upgrading. For anything real I would look elsewhere.
Used for Debugging sessions in Cursor
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 1/5
- Maintainer responsiveness 3/5
Good, but read the permissions first
It does the job, but it took some tweaking. It is community maintained, so I pin the version and read the changelog before upgrading. There is no auth layer, so whatever can reach it can use it. I keep it local only.
Used for Onboarding new devs with an agent that answers repo questions
- Setup & docs 4/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Too many sharp edges
Gave it a fair shot over two weeks. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box. Runs locally over stdio, so startup is instant and nothing leaves my machine unless a tool calls out.
Used for Internal developer assistant
- Setup & docs 1/5
- Auth experience 2/5
- Reliability 1/5
- Maintainer responsiveness 3/5
Would not run this unattended
I wanted to like this one. It is community maintained, so I pin the version and read the changelog before upgrading. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box.
Used for CI failure investigation
- Setup & docs 1/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 4/5
Needs more maintenance love
It works in a demo, but things got shaky under real use. It is community maintained, so I pin the version and read the changelog before upgrading.
Used for Internal developer assistant
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 3/5
Handy for dev, careful in prod
Mostly reliable, with the odd timeout. You can tell it is actively maintained, the rough edges keep getting fixed. It is community maintained, so I pin the version and read the changelog before upgrading. Recommended, with sensible guardrails.
Used for Automating release notes
- Setup & docs 4/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Trustworthy enough for real work
Our agents call this dozens of times a day. It is community maintained, so I pin the version and read the changelog before upgrading. Releases come often and the changelog is clear. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list.
Used for Letting a coding agent open and triage issues
- Setup & docs 4/5
- Auth experience 3/5
- Reliability 4/5
- Maintainer responsiveness 4/5
Write a review
Ran this server? Tell other teams how it went. You get one review per server. We email you a link to confirm it, then an editor checks it before it goes up. We never show your email.