Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Description from the maker (original English)
Design, check, simulate and launch Solana game economies on loot, one shared program, no contract.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"solana-kit": {
"command": "npx",
"args": [
"-y",
"@xgamesfun/solana",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add solana-kit -- npx -y @xgamesfun/solana mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"solana-kit": {
"command": "npx",
"args": [
"-y",
"@xgamesfun/solana",
"mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"solana-kit": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@xgamesfun/solana",
"mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account XGamesFun, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.20.1) reached the registry 8 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Figma Context MCP, Claude Real Video, Figma MCP Server
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Let any LLM watch a video locally — and search everything it has ever watched.
Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
The tools for loot, one shared Solana program for game and community economies. This repository is the npm package @xgamesfun/solana:
@xgamesfun/solana/client), a player module for apps (/play) and a results client (/results);xsolana CLI and an MCP server with ten xsolana_* tools;xsolana-economy skill, and one plugin that carries the tools and the skill to Claude Code and Codex;An economy is a JSON spec, not a new smart contract. Every project shares the one program, and none writes its own.
Status: loot 0.22.0, program ID
9cwqM1TXytPnFZsLfmUyv2dg4uW6Ch9C6UJVPns7NFQ, devnet only. The program is
not independently audited, and nothing runs on mainnet until it is. See SECURITY.md.
Disclaimer: provided as is, with no warranty and no guarantee that the program or the tools are safe. Use them
at your own risk; you are responsible for every transaction you approve and for making sure what you build is legal
where it runs. Nothing here is legal or financial advice. Read DISCLAIMER.md before you use it.
Every move leaves a public receipt. docs/program.md describes how the program behaves.
The MCP server and the skill let Claude Code, Codex or any MCP agent turn a one-line idea into a checked, simulated economy and hand you the command that puts it live in your own wallet.
Claude Code
/plugin marketplace add XGamesFun/solana-kit
/plugin install xsolana@xgamesfun
Codex
codex plugin marketplace add XGamesFun/solana-kit
codex plugin add xsolana@xgamesfun
Any agent with MCP (Cursor, opencode, Cline…): run the server with npx -y --package=@xgamesfun/solana@0.22.0 xsolana mcp. Or let npx -y @xgamesfun/solana@0.22.0 connect register it, with the skill, for Claude Code and Codex.
Then ask for an economy, for example *"a fishing game where each cast costs 0.02 SOL, with a rare golden fish and a monthly draw"*.
Going live is always yours: npx -y @xgamesfun/solana@0.22.0 approve opens a page on your computer where you connect a devnet wallet and approve each transaction. The agent never signs and never asks for a key.
Every tool runs from the CLI too, on a spec file (xsolana.json by default):
npx -y @xgamesfun/solana@0.22.0 examples shop with loot boxes # the nearest worked examples
npx -y @xgamesfun/solana@0.22.0 check xsolana.json # refusals and warnings npx -y @xgamesfun/solana@0.22.0 simulate xsolana.json # where the money goes, day by day npx -y @xgamesfun/solana@0.22.0 cost xsolana.json # what going live and each action cost npx -y @xgamesfun/solana@0.22.0 explain xsolana.json # the economy in plain words npx -y @xgamesfun/solana@0.22.0 approve xsolana.json # go live, approved in your own wallet
xsolana help lists every command. Every command names the exact version, so npx runs that release and never whatever is newest under the name.
npm install @xgamesfun/solana
import * as loot from '@xgamesfun/solana/client';
const ix = loot.openBoxIx({ player, project, box, nonce }); // one builder per instruction, no Solana SDK
| Import | What |
|---|---|
@xgamesfun/solana | the economy tools: check, simulate, plan, cost, explainEconomy, model |
@xgamesfun/solana/client | every PDA, one builder per instruction, account and receipt decoders, grant vouchers |
@xgamesfun/solana/play | solanaApp: what a player does with a live economy, from a browser app |
@xgamesfun/solana/results | results and vouchers a game's server signs |
@xgamesfun/solana/chain/* | browser-safe Solana primitives: base58, Borsh, transactions, PDAs, tokens, Core |
@xgamesfun/solana/idl.json | the program's IDL, the authority for account and argument layouts |
@xgamesfun/solana/release.json | the program build, IDL and client this release is pinned to |
The client, chain and play modules run in browsers and Node 22 or later, with no bundler required. The package ships TypeScript declarations for every entry point.
docs/program.md | the program: who signs, accounts, every instruction, fees, limits, receipts, costs |
docs/nfts.md | NFTs and tokens, with and without the project's authority |
docs/harnesses.md | how the plugin reaches Claude Code and Codex, and the release checklist |
skills/xsolana-economy | the skill an agent follows |
examples/ | whole economies that check and go live in the tests; ideas.json, 112 real economies rated |
evals/ | fresh-session evals of agents building on loot |
CHANGELOG.md, SECURITY.md | versions, the trust model, reporting a vulnerability |
| Path | What |
|---|---|
js/chain/ | browser-safe Solana primitives, no SDK |
js/client/ | the client; idl/ is the program's IDL |
js/economy/ | the economy spec (version 2, schema.json), checker, simulation, setup plan, cost, explainer, guide |
js/play/, js/results/ | a player's side of a live economy; results a server vouches for |
js/approve/, js/mcp/, js/connect/ | the approval page, the MCP server and its tools, xsolana connect |
js/sim/, js/test/ | LiteSVM running the real program; the tests and their pinned fixtures |
bin/xsolana.mjs | the CLI |
skills/, plugin/ | the skill (copied to plugin/skills, .claude/skills, .agents/skills) and the plugin |
scripts/ | fixtures, skill sync, IDL sync, release manifest, a devnet end-to-end run |
release.json | the program binary, IDL and client hashes this version is pinned to |
Node 22 or later.
npm ci
npm run fixtures # downloads the loot program from devnet and the programs it calls from mainnet, each checked by hash npm test # every instruction the client builds, and every example's whole setup, against the real program in LiteSVM npm run lint # ESLint npm run check # fixtures, skill copies and release.json in step, lint, then the tests
Nothing in the tests deploys or spends SOL.
| Variable | What it does |
|---|---|
XSOLANA_RPC_URL | a devnet RPC of your own for xsolana approve and xsolana status (a mainnet URL is refused) |
XSOLANA_NO_OPEN | xsolana approve prints its link without opening a browser |
XSOLANA_DEBUG | the CLI prints a failure's whole stack, not one line |
| XSOLANA_PROGRAM_DIR | the tests run that program build's target/deploy/loot.so, and check the IDL against it | To try the tools in your own agent from a clone, node bin/xsolana.mjs connect --local registers this checkout's MCP server and the skill with Claude Code and Codex (--remove takes them out again).
After editing skills/, run npm run sync-skills. Changes to tool texts, the skill or the plugin are best measured with the evals before and after (evals/README.md). AGENTS.md has the rules for working in this repository, for people and coding agents alike.
Issues and pull requests are welcome: see CONTRIBUTING.md. Please run npm run check before sending a change, and report a vulnerability privately as SECURITY.md describes.
Apache-2.0. See NOTICE and DISCLAIMER.md: provided as is, without warranty, at your own risk.