Figma Context MCP
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
AI API cost calculator, recommender & MCP server. 29 models across text/image/video/audio.
Pick the AI app you use, then copy the settings.
Passed 3/3 checks · Runs on your computer
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude, with some setup first
Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
One time only; it works for every server that needs Python (uv)
SettingsDeveloperEdit Config
Checking the commands · copy buttons appear once they pass
Use AI-Cost-CLI and tell me what you can do for me, then show me one thing✓ If Claude says it is using AI-Cost-CLI or shows a AI-Cost-CLI tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
ChatGPT cannot connect AI-Cost-CLI yet
AI-Cost-CLI runs on your computer, but ChatGPT can only connect servers that run on the web
A · Use an app that can connect AI-Cost-CLI
B · Others in Design, images & audio that work with ChatGPT
Picked from the most used in the same category, only ones that connect by address with no key
Works with Claude Code, with some setup first
Install Python (uv) on your computer first (one time)
One time only; it works for every server that needs Python (uv)
Mac: press Command+Space and type Terminal · Windows: open PowerShell
Checking the commands · copy buttons appear once they pass
You should see AI-Cost-CLI listed as connected
Use AI-Cost-CLI and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using AI-Cost-CLI or shows a AI-Cost-CLI tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Cursor, with some setup first
Install Python (uv) on your computer first (one time)
One time only; it works for every server that needs Python (uv)
Checking the commands · copy buttons appear once they pass
Use AI-Cost-CLI and tell me what you can do for me, then show me one thing✓ If Cursor says it is using AI-Cost-CLI or shows a AI-Cost-CLI tool in the answer, you are connected
Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with VS Code, with some setup first
Install Python (uv) on your computer first (one time)
One time only; it works for every server that needs Python (uv)
Checking the commands · copy buttons appear once they pass
Use AI-Cost-CLI and tell me what you can do for me, then show me one thing✓ If VS Code says it is using AI-Cost-CLI or shows a AI-Cost-CLI tool in the answer, you are connected
Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.
JSON settings are under “For developers” below
Claude Code
Checking the commands · copy buttons appear once they pass
Claude Desktop (claude_desktop_config.json)
Checking the commands · copy buttons appear once they pass
Cursor (~/.cursor/mcp.json)
Checking the commands · copy buttons appear once they pass
VS Code (mcp.json)
Checking the commands · copy buttons appear once they pass
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Run on your computer in
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
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 13, 2026
The registry name was verified with the GitHub account ufhouck, which owns the repo
Code last changed 12 days ago
Uses MIT
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
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
No reviews yet
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.
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 12 days ago, and the latest version (1.1.0) reached the registry 7 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Figma Context MCP, AutoClip, Next AI Draw.io
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.
Clip long videos into short clips with covers and captions. Local CLI and MCP.
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
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.
A terminal-based calculator and recommendation engine for AI API costs. Supports multiple providers, local currency conversion, and automated pricing updates.
Compare the effective cost of using models directly vs. through gateways like OpenRouter, including platform fees.
Comparison: gpt-4o vs openrouter/gpt-4o
┏━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━┓ ┃ Attribute ┃ gpt-4o ┃ openrouter/gpt-4o ┃ ┡━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━┩ │ Provider │ OpenAI │ OpenRouter │ ├──────────────────┼─────────────────────────────────┼─────────────────────────┤ │ Source │ Direct │ Aggregator │ ├──────────────────┼─────────────────────────────────┼─────────────────────────┤ │ Platform Fee │ 0.0% │ 5.5% │ ├──────────────────┼─────────────────────────────────┼─────────────────────────┤ │ Type │ text │ text │ ├──────────────────┼─────────────────────────────────┼─────────────────────────┤ │ Input Cost │ 111.4775 TRY (1M) │ 117.6088 TRY (1M) │ ├──────────────────┼─────────────────────────────────┼─────────────────────────┤ │ Output/Unit Cost │ 445.9100 TRY (1M) │ 470.4350 TRY (1M) │ └──────────────────┴─────────────────────────────────┴─────────────────────────┘
| Model | Provider | Input/1M | Output/1M | Tags |
|---|---|---|---|---|
| Claude Opus 4.7 | Anthropic | $5.00 | $25.00 | reasoning, coding, vision, agentic |
| GPT-5.5 | OpenAI | $5.00 | $30.00 | multimodal, coding, agentic |
| GPT-5.5 Pro | OpenAI | $30.00 | $180.00 | precision, enterprise, agentic |
| Claude Sonnet 4.6 | Anthropic | $3.00 | $15.00 | coding, fast, general |
| GPT-4o | OpenAI | $2.50 | $10.00 | reasoning, coding, vision |
| Gemini 3.1 Pro | $2.00 | $12.00 | long-context, multimodal | |
| DeepSeek R1 | DeepSeek | $0.55 | $2.19 | reasoning, coding, smart |
| Gemini 2.5 Flash | $0.30 | $2.50 | fast, reasoning, legacy | |
| Gemini 3.1 Flash-Lite | $0.25 | $1.50 | fast, cheap, agentic | |
| DeepSeek V3 | DeepSeek | $0.14 | $0.28 | general, coding, cheap |
| Model | Provider | Price | Type |
|---|---|---|---|
| Imagen 4 Fast | $0.02/image | Image | |
| GPT-Image-1 | OpenAI | $0.02/image | Image |
| DALL-E 3 | OpenAI | $0.04/image | Image |
| Imagen 4 Ultra | $0.06/image | Image | |
| Veo 3 Lite | $0.05/sec | Video | |
| Veo 3 | $0.40/sec | Video | |
| Lyria 3 Clip | $0.04/clip | Music | |
| Lyria 3 Pro | $0.08/song | Music | |
| Whisper | OpenAI | $0.006/min | Speech-to-Text |
| TTS Standard | OpenAI | $15/1M chars | Text-to-Speech |
Full list available via
aicost list --currency USD
pip install aicost-cli
With MCP server support:
pip install aicost-cli[mcp]
Or from source:
git clone https://github.com/ufhouck/aicost.git
cd aicost pip install -e .
aicost list --currency TRY
# Text model — token-based
aicost calc claude-opus-4.7 --input 1000000 --output 500000 --currency TRY
aicost calc openrouter/gpt-4o --input 1000000 --output 500000 --currency TRY
Output Example:
╭───────── Cost Calculation ──────────╮
│ Model: openrouter/gpt-4o │ │ Source: Aggregator │ │ │ │ Base Cost: 316.9976 TRY │ │ Platform Fee (5.5%): 17.4349 TRY │ │ │ │ Total Cost: 334.4325 TRY │ ╰─────────────────────────────────────╯
aicost compare claude-opus-4.7 gpt-5.5 --currency USD
aicost recommend "fast cheap coding" --currency USD
aicost sync
Start the Model Context Protocol server for AI agent integration:
aicost mcp
io.github.ufhouck/aicost-cliSee CONTRIBUTING.md for guidelines on how to contribute, including pricing updates, bug reports, and code contributions.
MIT — see LICENSE for details. Developed by Ufuk Aydın.