← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionBlender MCPOpen-source MCP server to connect Blender with any LLM for AI-assisted 3D modeling.NPM Sentinel MCP ServerAI-powered NPM package analysis MCP server
FMRS59 / 100 · C79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions8 / 2016 / 20
Maintenance14 / 2018 / 20
Documentation16 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • 3D artists and modelers who want to interact with Blender via natural language to boost productivity.
  • Developers looking to integrate Blender into AI-driven workflows.
  • Developers auditing NPM dependencies within AI workflows
  • Teams performing supply chain security assessments
  • Users of Claude Desktop, Cursor, or VS Code
Not for
  • Not suitable for automated environments that require strict security controls, as execute_blender_code allows arbitrary code execution.
  • Not ideal for users needing reliable real-time rendering or complex animations, as tools focus on scene creation and modification.
  • Projects outside the NPM ecosystem (e.g., pure Python/Go)
  • Environments without network access to deps.dev, OSV.dev, and the npm registry
  • Scenarios requiring maintenance by an official upstream vendor
Required permissions
  • Network access to the Blender socket port (default 9876) for the MCP server.
  • Ability to execute arbitrary Python code, which can access the file system and other system resources.
  • External API keys (Sketchfab, Hyper3D, Hunyuan3D) for asset downloads and model generation.
  • Network access to the NPM registry and external services (deps.dev, OSV.dev, OpenSSF, npms.io, GitHub)
  • Read access to workspace lockfiles (pnpm-lock.yaml, package-lock., yarn.lock) for cache invalidation
Risks and side effects
  • The execute_blender_code tool can run arbitrary code, potentially causing data loss or system damage. Always save your work before using it.
  • Poly Haven integration may download large assets, consuming bandwidth and storage.
  • When running remotely, network connectivity may expose the server.
  • Third-party APIs may have usage limits or costs.
  • Third-party READMEs and changelogs are untrusted external content; they are wrapped in tags with _meta flags but should still be handled cautiously
  • Depends on availability and accuracy of external services
  • Batch requests are capped at 25 packages to prevent registry enumeration; larger sets require batching
  • Third-party open source project, not officially maintained by NPM or Anthropic
Supported clientsClaude DesktopClaude Desktop, VS Code, Cursor
Tools1419