Item detail
github.com

grab/cursor-talk-to-figma-mcp

grab/cursor-talk-to-figma-mcp is an MCP server that RepoRadar is tracking in its Radar section, currently rated Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 9.9 out of 10.

Score8.4
Popularity1.0
Riskconditional
TierGold
Score breakdown
Usefulness8.0
Novelty8.0
Momentum8.0
Maturity6.6
Open-source/build8.4
Evidence7.2
Workflow potential9.9
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for frontend and design-system teams that want a higher-bandwidth path from Figma into Cursor, Claude Code, or Codex when shipping UI work with agent help.

Where this stands now

grab/cursor-talk-to-figma-mcp ranks #210 of 2770 tracked Radar items by composite score (8.4 against a section median of 4.9). The section currently carries 1659 Bronze, 645 Gold, 466 Silver. RepoRadar has retained observations for this record since 2026-07-01 (94 days in the current window). Signal extremes versus the section: momentum at the 83th percentile; novelty at the 83th percentile.

Who should use it

Frontend engineers turning live Figma files into implementation context Design-system teams testing agent-assisted design refactors Product builders comparing Figma-to-agent bridges on maturity and installability UI teams that want design reads and edits without a custom internal connector

Who should skip it

Skip grab/cursor-talk-to-figma-mcp unless the captured evidence suggests it solves a problem you are actively working on.

About this signal

grab/cursor-talk-to-figma-mcp is tracked by RepoRadar as an MCP server in the Radar section. First seen 2026-07-01; the source record was last checked on 2026-07-01. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. Across RepoRadar's eight signals, grab/cursor-talk-to-figma-mcp is strongest on workflow potential (9.9) and open-source/build quality (8.4) and weakest on setup ease (6.4) — a profile worth weighing against your own priorities. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The grab/cursor-talk-to-figma-mcp record combines a 8.4/10 composite score with separate popularity (1.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.

Questions worth asking before you adopt this

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

It can read private Figma files and modify designs programmatically, so initial trials should stay in a sandbox workspace with a throwaway design file; The local MCP plus plugin plus websocket setup widens the trust surface, so teams should review the bridge before pointing it at production design systems.

Evidence links
Closest alternatives / related signals
figma mcp design frontend developer-tools mit
Verification record

What RepoRadar actually verified

Discovered

Automated discovery and source capture. Last checked 2026-10-03T17:13:14.190776Z.

No editorial or hands-on review is claimed. This record remains at Discovered.

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

73 dated snapshots retained from 2026-07-01 through 2026-10-03; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score8.4 current · +0.0 net
Repository momentum5.5 current · -2.5 net
GitHub stars (observed)7,046 current · +154 net
GitHub stars7,046 exact observation
VersionNot reported by source
Last releaseNot reported by source
Maintenancemaintained
Current riskConditional
Current verdictTry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineClaude Code, Model Context Protocol, OpenAI Codex

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-10-038.45.57,046ConditionalTry nowmaintained
2026-10-028.45.57,046ConditionalTry nowmaintained
2026-10-018.45.57,048ConditionalTry nowmaintained
2026-09-308.45.57,045ConditionalTry nowmaintained
2026-09-298.45.57,043ConditionalTry nowmaintained
2026-09-288.45.87,040ConditionalTry nowmaintained
2026-09-278.45.57,038ConditionalTry nowmaintained
2026-09-268.45.87,038ConditionalTry nowmaintained
2026-09-258.45.07,034ConditionalTry nowmaintained
2026-09-248.45.57,035ConditionalTry nowmaintained
2026-09-238.45.57,033ConditionalTry nowmaintained
2026-09-228.45.57,032ConditionalTry nowmaintained

Why the record changed

Stars change

Stars changed: 7048 → 7046.

Stars change

Stars changed: 7047 → 7048.

Stars change

Stars changed: 7045 → 7047.

Stars change

Stars changed: 7043 → 7045.

Stars change

Stars changed: 7041 → 7043.

Stars change

Stars changed: 7040 → 7041.

Stars change

Stars changed: 7038 → 7040.

Stars change

Stars changed: 7034 → 7038.

Stars change

Stars changed: 7035 → 7034.

Stars change

Stars changed: 7033 → 7035.

Stars change

Stars changed: 7032 → 7033.

Stars change

Stars changed: 7031 → 7032.