Verified conversions across 205 color spaces: CSS strings, gamut checks, .cube LUTs
Nothing to run from here
Localfig 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
4
downloads a day
local
runs on your machine
226
downloads in 30d
What it does
The Figma desktop app as an MCP server: full Plugin API for AI agents. Local, no token, no quota.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user localfig-mcp '--' npx -y localfig
# 2 — ask your agent for something these tools do
# figma_status, figma_eval, figma_metadata and 7 more
Localfig costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
LUAll 1 server
LucasGorgal1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Localfig 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 localfig-mcp '--' npx -y localfigReconnect, 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
10 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.
Check whether localfig can reach Figma and what the plugin is looking at. Call it first in a session, whenever another tool reports that no plugin is connected or times out, and after the person switches files. Read-only. Returns the bridge state: owner or client, version and export folder. When…
No parameter schema on file.
No parameter schema on file.
Read the layer tree of a node or of the current page: ids, names, types, positions, sizes and text content. Use it to understand an existing design and to get node ids before editing with figma_eval. To search a large file by name or text, use figma_find instead; for the file's variables and…
No parameter schema on file.
Render nodes to image or data files, to see a design or hand it off. Use PNG to check your work visually: PNG and JPG results up to 2 MB come back inline as images. Use SVG for icons and vector assets, PDF for print, and JSON for the node tree in Figma REST API format, which design-to-code tools…
No parameter schema on file.
List the design system defined in the open file: every local variable collection with its modes and each variable's value per mode, plus local paint, text and effect styles. Use it before generating code from a design or building new screens, so you reuse existing tokens instead of hard-coding…
No parameter schema on file.
Search the file for nodes by type, layer name or text content. Use it to locate things in a large file before reading them with figma_metadata or editing them with figma_eval. To browse one known frame, use figma_metadata instead. Read-only. Filters combine, so a node must match every filter…
No parameter schema on file.
Report what changed in the file since your last check: nodes created, deleted or edited, with the properties that changed. Use it before editing a design the person may have touched, so you do not overwrite their work, and pass the returned seq as since on the next call. Edits made by localfig's…
No parameter schema on file.
Save a restore point, or undo localfig's most recent edit. action "snapshot" saves a named version to the file's version history, which the person can restore from Figma; use it before large or risky changes. action "undo" reverts every edit made by the most recent figma_eval, figma_place_image or…
No parameter schema on file.
Use components, styles and variables from the team libraries enabled for this file. action "collections" lists the library variable collections available; "variables" lists the variables in one collection; "import" copies one component, component set, style or variable into this file by its key…
No parameter schema on file.
Fill a node with a local image file, such as a photo or an illustration. Use it instead of figma_eval whenever the image comes from disk. The node must support fills, like a rectangle, ellipse or frame, and its existing fills are replaced by the image. Any format a browser can read works,…
No parameter schema on file.
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 Localfig 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 0.4.1 · scanned 14 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
Findings2 threat · 3 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest57b55ad05ddb2dd871159bd415e75badbc8bf4f8c9e1df34c5285781dc72e8a2
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 (10 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 |
|---|---|---|
| figma_status | no tags | |
| figma_eval | code-execstate-write | code-exec: keyword "eval" in tool name; state-write: declares readOnlyHint: false, destructiveHint: true |
| figma_metadata | no tags | |
| figma_export | state-write | state-write: declares readOnlyHint: false |
| figma_tokens | no tags | |
| figma_find | untrusted-input | untrusted-input: keyword "browse" |
| figma_changes | no tags | |
| figma_history | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| figma_library | state-write | state-write: declares readOnlyHint: false |
| figma_place_image | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest57b55ad05ddb2dd8
Scanned2026-10-14
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 0.4.1. Pin a release below and the command asks for exactly that one.
0.4.1
undated
latestNo release note was published with this version.
—
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 Localfig 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.