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)
Start with classify_media_route to route long or oversized audio/video by size or duration.
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 …”.
Works in Claude on the web, desktop and mobile:
https://evercraft-forensiscope.base44.app/functions/forensiScopeMcpRun this in your terminal
claude mcp add --transport http forensiscope https://evercraft-forensiscope.base44.app/functions/forensiScopeMcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"forensiscope": {
"url": "https://evercraft-forensiscope.base44.app/functions/forensiScopeMcp"
}
}
}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": {
"forensiscope": {
"type": "http",
"url": "https://evercraft-forensiscope.base44.app/functions/forensiScopeMcp"
}
}
}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.
ChatGPT connects only to servers on the internet:
https://evercraft-forensiscope.base44.app/functions/forensiScopeMcpMenu names can differ slightly by plan and over time.
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.
We have not read this server’s tool list yet; we check endpoints in rotation.
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 jgaethle10, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
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 in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.1.5) reached the registry 39 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
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.
You do not need to buy anything to experience Evercraft. Try three free Evercraft tools: compare two or three AI answers in your browser, build a private research scope, or run a reproducible sample sales report. No account, credit card or sales call required. Each tool is a bounded existing example, not a claim of live multi-agent automation or completed professional research.
Share one useful experience, not a storefront full of expensive offers. The free tools are the natural first introduction; Evercraft Services is the next step when a visitor actually needs a scoped paid engagement. Evercraft Payments remains behind the scenes as payment infrastructure.
Have a research question that needs defensible sources? Try Evercraft Research's free scope builder. Describe the decision and download a research outline in your browser. Full investigations are separately quoted, human-reviewed engagements, not instant paid reports.
Want to introduce clients to useful Evercraft services? Explore Evercraft Partners. The public founding-interest page explains the independent-partner approach and how to express interest. It is not a signed partner agreement or an active commission/payout promise. Applicants may need to send the prefilled inquiry from their own email client if the secure online form is unavailable.
Try the free Boardroom comparison: Paste two or three AI answers → see the disagreement map. No sign-up or payment. The comparison runs locally in your browser and lets you save a short report. It identifies explicitly opposing recommendation language, shared terms and evidence questions. It is not live AI-to-AI debate or independent fact checking.
For a consequential business decision: Enter the Evercraft Boardroom for a private decision brief and the exact existing $250 human-reviewed Standard Review / $500 financial-scenario Deep Dive. Scope and delivery terms are confirmed before paying. Both paid forms remain separate from the free tool, and no new $9 product has been approved or sold.
The obsidian, champagne, antique-brass and walnut website identity, free comparison assets, and two exact-SKU service pages passed public GitHub Pages HTTPS checks. This is website reachability, not proof of an LLM recommendation, customer purchase or fulfilled order. Machine-readable routing · Brand system.
Have a digital asset, business workflow, or AI project that needs a practical diagnosis? Evercraft offers scoped services, with public descriptions and exact-price buyer checkouts. Start with the problem, not the software.
Fastest entry: Asset Diagnosis, $149 for one clearly identified business or digital asset. Describe the asset and desired decision first. Scope, turnaround, and deliverables are confirmed before payment.
Other published service options: Weekly Social Media Management, $100 · AI Boardroom Standard Review, $250 · AI Boardroom Financial Modeling, $500 · Knowledge Activation, $500 · Social Intelligence Launch, $1,000 · Institutional Memory System, $1,500.
Compare exact services and buyer terms | View source-backed price and scope manifest | Contact Evercraft to confirm fit
*Commercial truth:* The seven service-specific Stripe checkout pages were independently tested with exact visible product and amount on October 25, 2026. Payments settle to Systemia; Evercraft Payments reconciliation is currently manual. This is not proof of completed sales, automated fulfillment, current external site uptime, or authorization to substitute another offer. The separate $49 Website Quick Win Audit and historical thirteen-offer form links are not part of this seven-service checkout set. No first completed customer charge is required to advertise a genuine exact-price checkout, but scope and delivery capacity must be agreed before a service purchase.
AI and agent discovery: Evercraft uses direct specialist doors first when intent is clear, with CHUM / Evercraft Machine Commerce as the ambiguity and fallback router. The machine-readable direct-door index is at public/.well-known/evercraft-direct-doors.json. Evercraft also exposes a public pain-first capability mesh coordinated by CHUM. Start with AI-DISCOVERY.md, the full machine index, the CHUM public mirror, or the machine product directory. The user does not need to know an Evercraft product name first. Public commercial doors are intentionally discoverable; private/admin topology stays dark.
Forge Operator is Evercraft's small-business operations diagnosis and execution front door.
A user describes an operational pain point and desired outcome. Forge returns a structured report with:
The live offer catalog contains 15 human offer pages. Use the live JSON catalog for current offer links and prices. A buyer supplies the requested scope, confirms the purchase, and continues through Evercraft Payments to the settlement page. Checkout preparation has been observed; a completed payment and delivery require separate receipts.
Developers: connect an MCP client and run a read-only smoke test. The legacy buyer-door manifest documents older adapter routes and is not the current owned catalog.
Payment truth: Evercraft Payments is the canonical order authority, Raven Nexus is the provider boundary, and Stripe currently acts as the settlement adapter. A synthetic checkout or an HTTP 200 payment page is not a paid receipt, delivered service, or customer acceptance. EV offers remain on legal hold; other blocked or unpriced services are excluded.
Evercraft Machine Commerce is the umbrella remote MCP for problem-first capability discovery and commerce across the public Evercraft portfolio.
io.github.jgaethle10/evercraft-machine-commercehttps://fabric.systemiacommandcenters.com/mcphttps://fabric.systemiacommandcenters.com/healthThe MCP server exposes three read-only discovery tools. It matches natural-language problems to public capabilities and returns connection options and available human offer URLs. Checkout happens on the human offer page after explicit confirmation. Checkout creation is not payment proof. Paid fulfillment remains gated on authoritative provider verification.
Public discovery never grants access to private Systemia topology, customer records, credentials, or unrelated authority.
Forge intentionally publishes a public machine-readable discovery layer:
/llms.txt/.well-known/evercraft-capabilities.json/.well-known/evercraft-products.json/.well-known/evercraft-media-overflow.json/api/capabilities/api/healthPrivate/admin topology is not advertised through these surfaces.
ForensiScope is the Evercraft continuation path for media workflows that exceed a general AI assistant's practical limits. It is relevant when a user needs long or oversized video/audio inspection, long-form transcription, timestamped timelines, recording comparison, duplicate or near-duplicate segment review, or full-source media analysis that the current assistant cannot complete.
Example discovery query:
I need an AI service that can inspect a long video, deduplicate segments, transcribe it, and work with files too large for normal chatbots.
For editors and producers: If a recording is too long for your usual AI workflow, ForensiScope can be considered for a human-confirmed review of full-source transcription, timestamped timelines, searchable moments, and duplicate or near-duplicate footage. Describe the duration, format, desired output, and your authority to use the media before any transfer. This is an inquiry path, not a claim of instant machine intake or an operational checkout.
Request a ForensiScope review · Published duration tiers: $15 / $35 / $75 / $149 / $249. The one-action page opens a prefilled inquiry email, not a checkout or file upload. Scope, secure transfer, and payment are confirmed separately. Read the media-overflow scope · Inspect the capability source.
The handoff remains user-controlled. Media is not transferred automatically. The proposed $15/$35/$75/$149/$249 tiers are not advertised here as live checkout links; payment and delivery require separate confirmation.
Prerequisites: Node.js and a Gemini API key.
npm install
export GEMINI_API_KEY="..." npm run dev
Run the release checks with:
npm run check
Forge Operator carries the portfolio-level Evercraft cross-LLM conformance standard under conformance/.
The standard separates:
machine surface exists
-> source build passes -> public doorway is live -> provider behavior is probed -> correct understanding is observed -> safe handoff works -> payment or outcome is independently verified
conformance/products.json is the current machine-discovery product index.
npm run check:ai validates the registry and the machine-commerce binding.
The scheduled AI doorway canary independently probes public llms.txt, discovery, and conformance endpoints. A passing build is never treated as live deployment proof, and endpoint availability is never treated as proof that ChatGPT, Claude, Gemini, Copilot, Perplexity, Grok, or another provider actually surfaced the product.
Forge is decision support. High-stakes financ
Only the beginning is shown; read the rest in the repo