Field-by-field comparison

Compare the evidence before choosing an MCP.

Each signal stays separate, missing facts remain visible, and the column order follows your selection.

MCPs in this comparison

Uncheck an MCP to remove it. Comparing two or three keeps each signal in its own row.

Open canonical comparison link

Comparable alternatives

Shown only when capability or industry context overlaps.

Side-by-side MCP evidence comparison
Evidence fieldMCP for Blender (ahujasid/blender-mcp)Watchlist candidateFigma MCPMCP100 Selected
Task fit
Best for
  • Blender users who accept a community—not Blender Foundation—MCP integration for AI-assisted 3D work.
  • Turning selected Figma frames into implementation context
  • Design-system teams using variables, components, and Code Connect
  • Human-supervised creation or modification of native Figma content
Not ideal for
  • Users who need a broadly proven, low-risk, fully mature Selected-grade integration today.
  • MCP clients outside Figma's supported catalog
  • Teams expecting one-click pixel-perfect production code
  • Headless automation that cannot complete user OAuth
Avoid when
  • Avoid high-impact or sensitive production use unless the documented authentication, permissions, rollback, and data handling match your environment.
  • Proprietary design content cannot be exposed to the selected AI client or model
  • Canvas writes cannot be reviewed before execution
  • A stable long-term zero-cost commitment is required
Provenance
Provenance details

Community implementation

github:ahujasid · Publisher source ↗

First-party MCP

Figma · Publisher source ↗

Maintenance
Maintenance details

Stale

Repo: Not documented

Package: Not documented

Repo: Not documented

Package: Not documented

Popularity evidence
Client coverage
Client coverage detailsNot documented
Claude Code✓ Streamable HTTP
Claude Desktop✓ Streamable HTTP
Codex✓ Streamable HTTP
VS Code✓ Streamable HTTP
Cursor✓ Streamable HTTP
OpenCode✓ Streamable HTTP
Client coverage noteLocal stdio runs on your computer. Streamable HTTP connects to a remotely hosted MCP server.
Access and data
AuthenticationLocal Blender connection does not imply hosted authentication; optional integrations can require Sketchfab, Poly Pizza, Hyper3D or Hunyuan3D credentials.The recommended remote server at https://mcp.figma.com/mcp uses user OAuth. Desktop mode relies on the signed-in Figma desktop application and its local endpoint.
CostProject is open source; Blender is free, while optional model/asset/API services may have costs.Figma documents the MCP feature as free during its current beta and says it is expected to become usage-based paid. Underlying Figma plans and plan-specific features may also apply.
PermissionsControls the active Blender environment and can modify scenes; optional integrations add external-service authority.OAuth grants access to authorized Figma resources. Available tools can read design context and, in supported workflows, create or modify canvas content. Desktop mode can also serve or download image and SVG assets.
Data handlingScene/context data is exposed to the connected AI client; optional external integrations may receive prompts/assets according to their policies.The remote service retrieves design nodes, components, variables, layouts, and potentially Make or Code Connect resources and returns them to the MCP client. Desktop mode can write downloaded assets into the local project.
Limitations
Tradeoffs
  • Third-party project with powerful local control; safety boundaries and long-term maintenance are not Selected-grade.
  • The hosted endpoint is easiest to connect and has the broadest feature set, but authorized design context passes through Figma and the connected AI workflow.
  • The desktop server is locally reachable through the Figma app, but it is intended for narrower organization and enterprise use cases.
  • Code Connect can improve component reuse but requires additional design-system setup.
Risk contextThird-party project with powerful local control; safety boundaries and long-term maintenance are not Selected-grade.Private designs can be disclosed through tool results, and write-enabled tools can change shared design files. Restrict accessible files, review OAuth consent, require confirmation for writes, and inspect downloaded assets before committing them.
Evidence date
Editorial review2026-09-13T00:00:00Z2026-07-24
Candidate evidence2026-09-13T00:00:00Z2026-07-29T20:58:26.000Z

Popularity, maintenance, fit, permissions, and client support are independent evidence fields.

Read the evidence method →
Compare MCPs | MCP100 Index