Claude Talk To Figma MCP

by arinspunk• 675•• Scanned•Claim this listing•Request removal
Design & Mediaantigravityclaudeclaude aiclaude codecursor

A Model Context Protocol (MCP) that allows Claude Desktop and other AI tools (Claude Code, Cursor, Antigravity, etc.) to read, analyze, and modify Figma designs

Claude Talk To Figma MCP is an open-source mcp server by arinspunk, written mainly in TypeScript, with 675 GitHub stars and the MIT license. Its code was last updated Apr 18, 2026.

Scan summary: scanned Nov 5, 2026 at commit c7adf24. Seen able to run shell commands. Scan policy

Scanned
Full scan at c7adf24 · Nov 5, 2026
Scanned
Static code scanwarn
Secrets scanpass
Dependency audit166 known vulnerabilitiesfail
Manifestnonewarn
Buildfail
Boot & handshaken/a
Network egressn/a
Reproducible (×3)n/a

Findings (52)

  • high
    dropper issue
    Details are available to the maintainer after claiming this listing.
  • high
    dependencies issue
    Details are available to the maintainer after claiming this listing.
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/configure-claude.js:60
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/launcher.js:21
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/launcher.js:34
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/launcher.js:36
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/launcher.js:95
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/launcher.js:103
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/launcher.js:105
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/launcher.js:107
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/launcher.js:110
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/launcher.js:123
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/test-integration.js:87
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/test-integration.js:127
  • medium
    Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.
    scripts/test-integration.js:144
  • medium
    @hono/node-server@1.19.9: 3 known vulnerabilities
    GHSA-92pp-h63x-v22m, GHSA-frvp-7c67-39w9, GHSA-wc8c-qw6v-h7f6
    bun.lock
  • medium
    @modelcontextprotocol/sdk@1.29.0: 6 known vulnerabilities
    GHSA-22jm-h49p-29qw, GHSA-46jr-4wx8-v453, GHSA-6prh-2h8m-c8cw, GHSA-6qxp-vccf-f47h, GHSA-f897-62hf-6gxq +1 more
    bun.lock
  • medium
    body-parser@2.2.2: 2 known vulnerabilities
    GHSA-27r3-jxmh-p828, GHSA-v422-hmwv-36x6
    bun.lock
  • medium
    brace-expansion@1.1.11: 8 known vulnerabilities
    GHSA-3jxr-9vmj-r5cp, GHSA-6j4f-fj2g-mc7p, GHSA-f886-m6hf-6m8v, GHSA-mh99-v99m-4gvg, GHSA-q2hr-2g5m-vwhr +3 more
    bun.lock
  • medium
    brace-expansion@2.0.1: 8 known vulnerabilities
    GHSA-3jxr-9vmj-r5cp, GHSA-6j4f-fj2g-mc7p, GHSA-f886-m6hf-6m8v, GHSA-mh99-v99m-4gvg, GHSA-q2hr-2g5m-vwhr +3 more
    bun.lock
  • medium
    browserslist@4.25.0: 2 known vulnerabilities
    GHSA-73wf-gq98-2v4g, GHSA-c83g-rgw3-j3cx
    bun.lock
  • medium
    express-rate-limit@8.2.1: 1 known vulnerability
    GHSA-46wh-pxpv-q5gq
    bun.lock
  • medium
    fast-uri@3.1.0: 12 known vulnerabilities
    GHSA-333x-w4r6-6crp, GHSA-4c8g-83qw-93j6, GHSA-7p8r-x3mc-p8w7, GHSA-f65p-4m7j-42xc, GHSA-hrr3-gc8f-f4qj +7 more
    bun.lock
  • medium
    fflate@0.8.2: 1 known vulnerability
    GHSA-px8p-9vwx-vf98
    bun.lock
  • medium
    glob@10.4.5: 2 known vulnerabilities
    GHSA-3g3m-2fjr-6pw4, GHSA-5j98-mcp5-4vw2
    bun.lock
  • medium
    hono@4.11.9: 35 known vulnerabilities
    GHSA-26pp-8wgv-hjvm, GHSA-2gcr-mfcq-wcc3, GHSA-3hrh-pfw6-9m5x, GHSA-458j-xx4x-4375, GHSA-5pq2-9x2x-5p6w +30 more
    bun.lock
  • medium
    ip-address@10.0.1: 6 known vulnerabilities
    GHSA-h3mg-xc3c-68pw, GHSA-j6r3-76f7-8jcv, GHSA-mwp4-54f8-5fhr, GHSA-rpw4-54j3-4h4q, GHSA-rxp7-6hxx-x8q5 +1 more
    bun.lock
  • medium
    js-yaml@3.14.1: 5 known vulnerabilities
    GHSA-2883-xcg3-v3hh, GHSA-52cp-r559-cp3m, GHSA-5p4m-2wfm-xmqj, GHSA-h67p-54hq-rp68, GHSA-mh29-5h37-fv8m
    bun.lock
  • medium
    minimatch@3.1.2: 3 known vulnerabilities
    GHSA-23c5-xmqv-rm74, GHSA-3ppc-4f35-3m26, GHSA-7r86-cg39-jmmj
    bun.lock
  • medium
    minimatch@5.1.6: 3 known vulnerabilities
    GHSA-23c5-xmqv-rm74, GHSA-3ppc-4f35-3m26, GHSA-7r86-cg39-jmmj
    bun.lock
  • medium
    minimatch@9.0.5: 4 known vulnerabilities
    GHSA-23c5-xmqv-rm74, GHSA-3ppc-4f35-3m26, GHSA-7r86-cg39-jmmj, GHSA-g3hv-75wg-m249
    bun.lock
  • medium
    node-forge@1.3.3: 15 known vulnerabilities
    GHSA-2328-f5f3-gj25, GHSA-4487-j8r4-4g2f, GHSA-4642-5mcj-2rqw, GHSA-525v-9gp9-w22h, GHSA-5cwg-6vw7-rj6p +10 more
    bun.lock
  • medium
    path-to-regexp@8.2.0: 4 known vulnerabilities
    GHSA-27v5-c462-wpq7, GHSA-j3q9-mxjg-w52f, GHSA-27v5-c462-wpq7, GHSA-j3q9-mxjg-w52f
    bun.lock
  • medium
    picomatch@2.3.1: 2 known vulnerabilities
    GHSA-3v7f-55p6-f55p, GHSA-c2c7-rcm5-vvqj
    bun.lock
  • medium
    picomatch@4.0.2: 2 known vulnerabilities
    GHSA-3v7f-55p6-f55p, GHSA-c2c7-rcm5-vvqj
    bun.lock
  • medium
    rollup@4.37.0: 1 known vulnerability
    GHSA-mw96-cpmx-2vgc
    bun.lock
  • medium
    tmp@0.0.33: 2 known vulnerabilities
    GHSA-52f5-9888-hmc6, GHSA-ph9p-34f9-6g65
    bun.lock
  • medium
    uuid@11.1.0: 1 known vulnerability
    GHSA-w5hq-g745-h8pq
    bun.lock
  • medium
    ws@8.18.1: 4 known vulnerabilities
    GHSA-58qx-3vcg-4xpx, GHSA-96hv-2xvq-fx4p, GHSA-58qx-3vcg-4xpx, GHSA-96hv-2xvq-fx4p
    bun.lock
  • medium
    zod@3.25.76: 1 known vulnerability
    GHSA-mrhx-c7xc-m3w5
    bun.lock
  • medium
    @modelcontextprotocol/sdk@1.7.0: 5 known vulnerabilities
    GHSA-46jr-4wx8-v453, GHSA-6prh-2h8m-c8cw, GHSA-8r9q-7v3j-jr4g, GHSA-rvq5-wwqv-78pq, GHSA-w48q-cv73-mx4w
    src/talk_to_figma_mcp/bun.lock
  • medium
    body-parser@2.1.0: 2 known vulnerabilities
    GHSA-27r3-jxmh-p828, GHSA-v422-hmwv-36x6
    src/talk_to_figma_mcp/bun.lock
  • medium
    uuid@9.0.1: 1 known vulnerability
    GHSA-w5hq-g745-h8pq
    src/talk_to_figma_mcp/bun.lock
  • medium
    zod@3.24.2: 1 known vulnerability
    GHSA-mrhx-c7xc-m3w5
    src/talk_to_figma_mcp/bun.lock
  • medium
    Install or build failed in a clean environment
    s/tsup/dist/index.js:1545:26) at Worker.emit (node:events:519:28) at MessagePort.<anonymous> (node:internal/worker:270:53) at [nodejs.internal.kHybridDispatch] (node:internal/event_target:843:20) at MessagePort.<anonymous> (node:internal/per_context/messageport:23:28) DTS Build error
  • low
    @babel/core@7.27.4: 1 known vulnerability
    GHSA-4x5r-pxfx-6jf8
    bun.lock
  • low
    deepmerge@4.3.1: 1 known vulnerability
    GHSA-gcqx-w48m-w2h4
    bun.lock
  • low
    qs@6.14.0: 10 known vulnerabilities
    GHSA-4mjr-xmp4-gh2g, GHSA-6pq8-jhm2-2vcw, GHSA-6rw7-vpxm-498p, GHSA-q8mj-m7cp-5q26, GHSA-w7fw-mjwx-w883 +5 more
    bun.lock
  • low
    qs@6.15.0: 4 known vulnerabilities
    GHSA-4mjr-xmp4-gh2g, GHSA-6pq8-jhm2-2vcw, GHSA-q8mj-m7cp-5q26, GHSA-x5fp-wj9c-mxmx
    bun.lock
  • low
    diff@4.0.2: 1 known vulnerability
    GHSA-73rr-hh4g-fpgx
    src/talk_to_figma_mcp/bun.lock
  • low
    qs@6.13.0: 5 known vulnerabilities
    GHSA-4mjr-xmp4-gh2g, GHSA-6pq8-jhm2-2vcw, GHSA-6rw7-vpxm-498p, GHSA-q8mj-m7cp-5q26, GHSA-w7fw-mjwx-w883
    src/talk_to_figma_mcp/bun.lock
  • low
    No manifest declaring network access and environment variables (agent.json)

Network activity

During install
registry.npmjs.org
While running
Not run — the code wasn't started in this scan

Automated result for the commit shown. See our scan policy. View the scan log

Maintainers can claim the listing to rescan, or dispute a result.

Claude Talk To Figma MCP alternatives

View more →

Similar mcp servers in Design & Media, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

NameStarsLicenceLast updatedScan
Claude Talk To Figma MCP (this page)
arinspunk
675MITApr 18, 2026Scanned, no flagged issues
Next AI Draw Io
DayuanJiang
37kApache-2.0Nov 1, 2026Scanned, no flagged issues
MCP For Blender
ahujasid
33kMITOct 29, 2026Scanned, no flagged issues
Figma Context MCP
GLips
16kMITOct 27, 2026Scanned, no flagged issues
Nginx UI
0xJacky
12kAGPL-3.0Nov 1, 2026Scanned, no flagged issues
Lamda
firerpa
8.7kMITSep 27, 2026Scanned, no flagged issues