Verified conversions across 205 color spaces: CSS strings, gamut checks, .cube LUTs
Nothing to run from here
figmcp is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
2
downloads a day
local
runs on your machine
937
downloads in 30d
What it does
Local Figma MCP server: Figma frames to Flutter and React code, and design in Figma. No API limits.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user figmcp '--' npx -y @irshad.io/figma-local-mcp
# 2 — ask your agent for something these tools do
# get_code_connect_map, add_code_connect_map, remove_code_connect_map and 12 more
figmcp costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts figmcp as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user figmcp '--' npx -y @irshad.io/figma-local-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
15 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Get the mapping from the component instances in a node to code
| Parameter | Type | Required | Notes |
|---|---|---|---|
| nodeId | no | — | |
| fileKey | yes | — |
Map a design component to a code component, so get_design_context names
| Parameter | Type | Required | Notes |
|---|---|---|---|
| nodeId | yes | — | |
| fileKey | yes | — | |
| componentName | string | yes | Code component name, e.g. AppPrimaryButton. |
| source | string | yes | Path of the code component in the project. |
| label | string | no | Framework, e.g. Flutter or React. |
Remove the code component mapping of a component (by instance, component or set id).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| nodeId | yes | — | |
| fileKey | yes | — |
Get design context for a Figma node — the primary tool for design-to-code
| Parameter | Type | Required | Notes |
|---|---|---|---|
| nodeId | no | — | |
| fileKey | yes | — | |
| framework | string | no | Code to generate: flutter or react. Default: from clientFrameworks / clientLanguages, else FIGMA_LOCAL_MCP_FRAMEWORK, else flutter when the project has a pubspec.yaml, else react. |
| clientLanguages | string | no | Comma separated languages of the client, e.g. "dart" (picks the framework). |
| clientFrameworks | string | no | Comma separated frameworks of the client, e.g. "flutter" (picks the framework). |
| screen | boolean | no | Flutter: draw the node as a phone screen that fills the screen and scrolls when tall (default: portrait frames 300-480 wide). |
| assetsDir | string | no | Flutter: folder of the asset paths in the code (default: the svg/png/images folders of the project's pubspec.yaml, else assets/figma). |
| screenUtil | boolean | no | Flutter: write lengths with flutter_screenutil (.w, .h, .r, .sp) so the layout scales from the design size (default: when the project's pubspec.yaml depends on flutter_screenutil). |
| excludeScreenshot | boolean | no | Leave the screenshot out of the response. |
| forceCode | boolean | no | Always return code, even for very large nodes. |
| disableCodeConnect | boolean | no | Draw mapped components from their layers instead of naming the code component. |
| skillNames | string | no | Accepted for compatibility (logging only). |
IMPORTANT: Always prefer to use get_design_context. Get metadata for a
| Parameter | Type | Required | Notes |
|---|---|---|---|
| nodeId | no | — | |
| fileKey | yes | — |
Generate a screenshot for a given node or the currently selected node
| Parameter | Type | Required | Notes |
|---|---|---|---|
| nodeId | no | — | |
| fileKey | yes | — | |
| maxDimension | integer | no | Longest edge of the PNG in pixels (default 1024). |
| contentsOnly | boolean | no | Render the node in isolation, without overlapping content. |
| enableBase64Response | boolean | no | Also include the PNG inline as base64. |
Get variable definitions for a given node id. E.g. {'icon/default/secondary': #949494}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| nodeId | no | — | |
| fileKey | yes | — |
Download assets for a single node: an exported render (export), the
| Parameter | Type | Required | Notes |
|---|---|---|---|
| nodeId | no | — | |
| fileKey | yes | — | |
| defaultFormat | string | no | — |
| defaultScale | number | no | — |
Status of the local Figma connection: whether the plugin is connected,
No parameter schema on file.
Save a design export JSON (frames with node trees, as the plugin
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Absolute path of the export JSON file. |
Write a full design export of a node (default: the selection) to a JSON
| Parameter | Type | Required | Notes |
|---|---|---|---|
| nodeId | no | — | |
| fileKey | yes | — | |
| path | string | no | Absolute .json path to write (default: the data folder). |
Search the design system of the file open in Figma Desktop: local
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Words to look for, e.g. "button primary". |
| kinds | array | no | What to search (default: all of …). |
| allPages | boolean | no | Search components on every page, not just the current one (slower on large files). |
| limit | integer | no | Most results per kind (default 50). |
| fileKey | yes | — |
Check Flutter code against the design: analyzes it, renders it with
| Parameter | Type | Required | Notes |
|---|---|---|---|
| nodeId | no | — | |
| fileKey | yes | — | |
| file | string | no | The .dart file with the widget, under the project's lib/ (absolute, or relative to the project). |
| widget | string | no | The widget class in file (default: its first widget class). |
| viewport | string | no | Lay the code out on a screen of this size, e.g. "360x780", and report runtime errors (overflows) and layers pushed off screen instead of comparing. |
| fonts | array | no | Folders with font files (default: the project's assets/fonts and the system fonts). |
| flutter | string | no | Path of the flutter tool, when it is not on PATH. |
Create or edit designs in the file open in Figma Desktop by running
| Parameter | Type | Required | Notes |
|---|---|---|---|
| code | string | yes | Body of an async function run with figma in scope. |
| fileKey | yes | — | |
| timeoutMs | integer | no | How long to wait for the script, in ms (default …). |
Put an image file from this computer into the file open in Figma
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Path of the image file (absolute, or relative to the project). |
| nodeId | no | Set the image as the fill of this layer instead of making a new one (not for SVG). | |
| parentId | no | Frame or group to put the new layer in. | |
| name | string | no | Layer name (default: the file name). |
| x | number | no | — |
| y | number | no | — |
| width | number | no | — |
| height | number | no | — |
| scaleMode | string | no | How the image fills the layer (default FILL). |
| keepFills | boolean | no | With nodeId: add the image above the existing fills instead of replacing them. |
| fileKey | yes | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install figmcp or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 1.5.2 · scanned 15 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings5 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digestca8e77b47efb1cfc7ed288062920aae1527dcf130921e1298497202461d7f332
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (15 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_code_connect_map | no tags | |
| add_code_connect_map | no tags | |
| remove_code_connect_map | no tags | |
| get_design_context | no tags | |
| get_metadata | no tags | |
| get_screenshot | no tags | |
| get_variable_defs | no tags | |
| download_assets | untrusted-input | untrusted-input: keyword "download" |
| whoami | no tags | |
| import_design_export | no tags | |
| save_design_export | no tags | |
| search_design_system | no tags | |
| verify_code | no tags | |
| use_figma | no tags | |
| place_image | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestca8e77b47efb1cfc
Scanned2026-10-15
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.5.2. Pin a release below and the command asks for exactly that one.
1.5.2
15 Oct 2026
latestNo release note was published with this version.
1.5.1
14 Oct 2026
No release note was published with this version.
1.4.2
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish figmcp can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.