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

Figma MCP BridgeFramelink MCP for Figma

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

Comparable alternatives

Firecrawl MCPMCP100 SelectedPlaywright MCPMCP100 SelectedsanityMCP100 SelectedHugging Face MCPMCP100 SelectedGoogle Search Console MCP Server for SEOsMCP100 SelectedelevenlabsMCP100 Selected

Shown only when capability or industry context overlaps.

Side-by-side MCP evidence comparison
Evidence field	Figma MCP BridgeWatchlist candidate	Framelink MCP for FigmaMCP100 Selected
Task fit
Best for	Inspecting and operating the publisher-documented Figma bridge during design-to-code or design-automation work	Providing coding agents with Figma node structure, styles, variables, and design assets needed for implementation
Not ideal for	Replacing designer review or guaranteeing production-ready code and pixel accuracy from arbitrary Figma files	Replacing designer review or guaranteeing pixel-perfect production code from arbitrary files
Avoid when	The connected Figma file contains confidential designs, comments, assets, or data that must not reach the MCP client	The connected Figma account exposes confidential files that should not be sent to the AI client
Provenance
Provenance details	Community implementation github:gethopp · Publisher source ↗	Community implementation io.github.GLips · Publisher source ↗
Maintenance
Maintenance details	Repo: Aug 10, 2026 Package: Not documented	Repo: Aug 7, 2026 Package: Jun 18, 2026
Popularity evidence
GitHub stars	484 GitHub stars · checked 2026-08-14T18:46:26.000Z	15,658 GitHub stars · checked 2026-08-14T18:46:26.000Z
30-day package downloads	No reliable download data	350,316 30-day package downloads · checked 2026-08-14T18:46:26.000Z
External adoption evidence	github: repository stars: 484Exact attributable signal.github: repository stars · Admission snapshot · checked 2026-08-14T18:46:26.000ZEvidence source ↗	github: repository stars: 15,658Exact attributable signal.github: repository stars · Admission snapshot · checked 2026-08-14T18:46:26.000ZEvidence source ↗
Client coverage
Client coverage details	Claude Code✓ Local stdio Claude Desktop✓ Local stdio Codex✓ Local stdio VS Code✓ Local stdio Cursor✓ Local stdio OpenCode✓ Local stdio	Claude Code✓ Local stdio Claude Desktop✓ Local stdio Codex✓ Local stdio VS Code✓ Local stdio Cursor✓ Local stdio OpenCode✓ Local stdio
Client coverage note	Local stdio runs on your computer. Streamable HTTP connects to a remotely hosted MCP server.
Access and data
Authentication	MCP authentication or tokens are not documented. The current Figma user must have permission to edit the target file for writes.	Uses a personal access token through FIGMA_API_KEY or X-Figma-Token, or an OAuth bearer token. HTTP also supports per-request token headers.
Cost	The MIT-licensed project documents npx installation and lists no MCP usage fee. Figma plan, client, and model costs are separate.	The MIT-licensed server lists no MCP fee. Figma plan and API limits, client, and model costs are separate.
Permissions	Reads connected Figma files, documents, selections, styles, variables, metadata, and screenshots. Opt-in tools can edit text and properties, create or delete nodes, reparent content, and save screenshots locally; writes require Figma edit permission.	Reads Figma file and node data through the Figma API and downloads PNG, SVG, or GIF assets into a configured local image directory; no Figma write capability is documented.
Data handling	Streams live Figma document data from the plugin to the AI client through the local bridge; screenshots can be returned or saved locally. Telemetry, retention, and model-training behavior are not documented.	Figma metadata and API responses are returned to the MCP client; raw tools write figma-raw.json locally and image tools save assets locally. Telemetry sends server, platform, session, and event metadata by default; retention is not documented.
Limitations
Tradeoffs	Live design context reduces screenshot guesswork, while the bridge and Figma-side setup add moving parts and expose document content to the agent.	Structured design context reduces screenshot guesswork, but output quality still depends on file organization and granting access to Figma data.
Risk context	Read tools can expose private designs and write tools can modify or delete shared files. Keep the unauthenticated local WebSocket and HTTP bridge restricted and require confirmation for writes.	Private design data and assets can reach the MCP client or model and local raw logs; telemetry adds metadata transmission. Protect tokens, restrict the image directory, and review downloaded and raw files.
Evidence date
Editorial review	2026-08-11	2026-08-11
Candidate evidence	2026-08-14T18:46:26.000Z	2026-08-14T18:46:26.000Z

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

Read the evidence method →