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)
Turn slide images, charts and screenshots into editable PowerPoint (PPTX) or SVG files.
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.
AuthorizationValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http convert https://unraster.ai/mcp --header 'Authorization: your-value'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"convert": {
"url": "https://unraster.ai/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}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": {
"convert": {
"type": "http",
"url": "https://unraster.ai/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}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 address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
Authorization secret required HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 8, 2026. The maker wrote them, not us; we show them as plain text.
quote_conversionShow the credit price of converting an image to editable PowerPoint and/or SVG, and the account balance. Free; nothing is charged.
convert_imageConvert a PNG, JPEG or WebP image into an editable PowerPoint (.pptx) and/or SVG and return download links. Spends credits only when files are delivered (SVG 1, PowerPoint 2); a failed conversion is not charged. Waits up to about 45 seconds; if still running, returns conversion_i
get_conversionCheck the status, progress and download links of a conversion started with convert_image. Free.
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 9, 2026
The registry name was verified against the domain unraster.ai (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 743 ms (HTTP 200)
No sign-in needed
Read 3 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 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.
You need to fill in: Authorization
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 (1.0.1) reached the registry yesterday.
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:↓ Downloads per weeki★ 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.
Connect Claude Code, Cursor or Codex to the Unraster MCP server and turn slide images, charts, flowcharts and screenshots into editable PowerPoint (.pptx) or SVG files.
.pptx or .svg. export UNRASTER_API_KEY="your-api-key"
https://unraster.ai/mcp (Streamable HTTP, stateless), authenticated with Authorization: Bearer $UNRASTER_API_KEY.claude mcp add --transport http unraster https://unraster.ai/mcp \
--header "Authorization: Bearer $UNRASTER_API_KEY"
Your shell fills in the key when you run the command, and Claude Code saves it in its own configuration. Also see configs/claude-code.md.
Add this to ~/.cursor/mcp.json (or .cursor/mcp.json in a project). Cursor reads the key from your environment.
{
"mcpServers": { "unraster": { "url": "https://unraster.ai/mcp", "headers": { "Authorization": "Bearer ${env:UNRASTER_API_KEY}" } } } }
Add this to ~/.codex/config.toml. Codex sends the value of UNRASTER_API_KEY as the Bearer token.
[mcp_servers.unraster]
url = "https://unraster.ai/mcp" bearer_token_env_var = "UNRASTER_API_KEY"
Use the same URL and Authorization header in any client that supports Streamable HTTP servers.
The Unraster skill ships as a plugin in zane-labs/agent-skills. It adds the MCP server for you and tells the agent when to use it, what it costs and where to save the file:
claude plugin marketplace add zane-labs/agent-skills
claude plugin install unraster@zane-agent-skills
For Codex: codex plugin marketplace add zane-labs/agent-skills, then codex plugin add unraster@zane-agent-skills.
| Tool | Access | Inputs | Returns |
|---|---|---|---|
quote_conversion | Read-only | outputs: pptx, svg or both | Credit price and your balance |
convert_image | Spends credits | image_url (https) or image_base64 + mime_type (up to 5 MB decoded); outputs defaults to pptx | Download links and expires_at, or a conversion_id after about 45 seconds |
get_conversion | Read-only | conversion_id | Status, progress and download links when ready |
Example prompts:
outputs: pptx) is free.For many images, use the Batches API: create a batch, upload each file, start it, poll until finished_at is set, then download one zip of every delivered file. Batches need a plan with batch access ($49.9/month and up, 50 or 100 files per batch); other plans return 403 plan_required. Each file can be up to 20 MiB. Credits are reserved for the whole batch when it is created, and only delivered files are charged. The zip is kept for 7 days.
The bundled script does the whole flow with curl and jq:
bash scripts/batch.sh pptx results.zip slides/*.png
Documentation: https://unraster.ai/docs/api#batches
MIT. See LICENSE.