Thrixel MCP Server
Enables AI agents to create, edit, detail, and download game-ready 3D models through natural conversation, with visual feedback on each result.
README
Thrixel MCP Server
Model Context Protocol (MCP) server for the Thrixel 3D generation platform. Enables AI agents to create, edit, detail, and download game-ready 3D models through natural conversation — and to see each result before building on it.
<!-- TODO(screenshot): hero demo GIF — agent prompted for a game prop, tool call runs, GLB lands in the project, thumbnail comes back inline. Save as docs/demo.gif -->
TODO — demo GIF goes here (
docs/demo.gif).
Features
12 tools covering the Thrixel generation pipeline:
| Category | Tools |
|---|---|
| Create | thrixel_create_model, thrixel_sculpt_model |
| Refine | thrixel_edit_model, thrixel_autofix_model |
| Detail & Texture | thrixel_detail_model, thrixel_retexture_model |
| Optimize | thrixel_reduce_triangles |
| Inspect | thrixel_inspect_model, thrixel_list_assets |
| Jobs & Download | thrixel_job_status, thrixel_download |
| Account | thrixel_account_status |
Key Capabilities
- Text to 3D:
create_modelreturns an editable, multi-part mesh — parts stay separate and named, so you can retexture or transform individual pieces later. The default for props, vehicles, buildings, weapons, furniture. - Image to 3D:
sculpt_modelturns a photo or a description into a dense single organic mesh — creatures, characters, plants, food. - Natural-language editing:
edit_modelchanges one thing and leaves the rest alone, optionally scoped to named parts. Iterating beats regenerating. - Detail & retexture:
detail_modeladds high-resolution geometry and PBR texture;retexture_modelswaps materials without touching geometry — the cheap way to restyle a whole asset set. - Free triangle reduction:
reduce_triangleshits a game budget for zero cubes and routes to the right backend operation automatically. Never re-run a detail pass just to get a lighter mesh. - Budget-aware:
account_statusreports the cube balance, the enforced concurrency cap, and what is running, so a batch can be sized before it starts instead of failing partway through. - Visual feedback loop: every finished job returns a rendered thumbnail as image content, so the agent can judge the result and retry rather than carrying a broken asset forward.
- Waits for you: job tools block until the model is finished and write the GLB straight into your project. One tool call equals one finished asset — no agent-authored polling loop to silently give up halfway.
- Style consistency: reuse one
reference_image_idacross many assets, or passstyle_reference_submission_id, to keep a set looking like a set. Reusing a reference image is not re-charged.
Prerequisites
-
uv — one binary, no Python setup needed.
macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | shWindows (PowerShell)
irm https://astral.sh/uv/install.ps1 | iex -
A Thrixel API key (get one here — Account → API keys)
uvx fetches the server and a suitable Python into a throwaway environment on
first run. You do not need to clone anything, create a virtualenv, or install
Python yourself.
Installation
Option 1 · Claude Code · Recommended
This form takes no JSON, so it works identically in every shell — use it on Windows and macOS / Linux alike:
claude mcp add thrixel --env THRIXEL_API_KEY=sk-thrixel-YOUR_API_KEY -- uvx thrixel-mcp
<details> <summary>Prefer <code>add-json</code>? Quoting differs per shell</summary>
Only the outer quoting changes; the JSON itself is identical.
macOS / Linux, Git Bash, WSL
claude mcp add-json thrixel '{"command":"uvx","args":["thrixel-mcp"],"env":{"THRIXEL_API_KEY":"sk-thrixel-YOUR_API_KEY"}}'
Windows PowerShell — PowerShell rewrites inner double quotes when passing
arguments to a native command, so they must be escaped. Without this you get
Invalid configuration: : Invalid input.
claude mcp add-json thrixel '{\"command\":\"uvx\",\"args\":[\"thrixel-mcp\"],\"env\":{\"THRIXEL_API_KEY\":\"sk-thrixel-YOUR_API_KEY\"}}'
Windows CMD — wrap in double quotes and double every inner one.
claude mcp add-json thrixel "{""command"":""uvx"",""args"":[""thrixel-mcp""],""env"":{""THRIXEL_API_KEY"":""sk-thrixel-YOUR_API_KEY""}}"
</details>
Verify with claude mcp list, then open a new session.
Option 2 · Install by Asking Your AI Agent
Already chatting with Cursor / Claude Code / Codex? Paste this prompt:
Install the Thrixel MCP server for me. Docs: https://github.com/thrixel/thrixel_mcp
Run it with: uvx thrixel-mcp
Use this env var: THRIXEL_API_KEY=sk-thrixel-YOUR_API_KEY
Option 3 · Manual Install
<details> <summary><b>Cursor</b></summary>
Paste into .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
macOS / Linux
{
"mcpServers": {
"thrixel": {
"command": "uvx",
"args": ["thrixel-mcp"],
"env": { "THRIXEL_API_KEY": "sk-thrixel-YOUR_API_KEY" }
}
}
}
Windows — GUI apps often do not inherit your shell PATH, so give the full
path to uvx.exe (find it with where.exe uvx):
{
"mcpServers": {
"thrixel": {
"command": "C:\\Users\\YOU\\.local\\bin\\uvx.exe",
"args": ["thrixel-mcp"],
"env": { "THRIXEL_API_KEY": "sk-thrixel-YOUR_API_KEY" }
}
}
}
</details>
<details> <summary><b>Claude Desktop</b></summary>
Add to claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"thrixel": {
"command": "uvx",
"args": ["thrixel-mcp"],
"env": { "THRIXEL_API_KEY": "sk-thrixel-YOUR_API_KEY" }
}
}
}
Windows: replace
"uvx"with the absolute path touvx.exe— the desktop app does not inherit your shellPATH. See the Cursor block above.
</details>
<details> <summary><b>Codex / VS Code / Windsurf</b></summary>
Same shape as above — command: "uvx", args: ["thrixel-mcp"], and
THRIXEL_API_KEY in the env block.
</details>
<details> <summary><b>Without uv (pip fallback)</b></summary>
pip install thrixel-mcp
Then point the client at your interpreter:
{
"mcpServers": {
"thrixel": {
"command": "python",
"args": ["-m", "thrixel_mcp.server"],
"env": { "THRIXEL_API_KEY": "sk-thrixel-YOUR_API_KEY" }
}
}
}
Use an absolute path to python if the client cannot find it on PATH.
</details>
<details> <summary><b>Pre-release / unpublished builds</b></summary>
uvx can run straight from the repository, no PyPI release needed:
# latest main, ahead of the newest release
uvx --from git+https://github.com/thrixel/thrixel_mcp thrixel-mcp
# a local checkout
uvx --from /path/to/thrixel_mcp thrixel-mcp
Same shape in a client config — replace args with
["--from", "git+https://github.com/thrixel/thrixel_mcp", "thrixel-mcp"].
</details>
Activate After Install
Most clients auto-load the new server, but Cursor and VS Code require a manual toggle:
| Client | What to do | Verify |
|---|---|---|
| Claude Code | Nothing — auto-loads on next message | /mcp shows thrixel ✓ connected |
| Cursor | Restart → Settings → MCP & Integrations → toggle thrixel on → wait for green dot ● → open a new chat |
List the thrixel tools available |
| Claude Desktop | Quit & relaunch the app | List the thrixel tools available |
| VS Code | Run command MCP: List Servers → click thrixel → Start |
List the thrixel tools available |
| Codex | Nothing — auto-loads on next session | List the thrixel tools available |
<!-- TODO(screenshot): connected-state screenshot (Cursor green dot / /mcp output).
Save as docs/connected.png -->
TODO — connected-state screenshot goes here (
docs/connected.png).
Usage
Once connected, just ask:
Make me a low-poly wooden market stall for a game, under 5000 triangles.
The agent will chain thrixel_create_model → thrixel_detail_model → thrixel_reduce_triangles, save the GLB into ./thrixel_assets/, and show you the render at each step.
<!-- TODO(screenshot): before/after — Architect blockout vs detailed result. Save as docs/pipeline.png -->
TODO — pipeline before/after image goes here (
docs/pipeline.png).
Troubleshooting
Invalid configuration: : Invalid input(Windows) —claude mcp add-jsonreceived mangled JSON because PowerShell rewrote the inner double quotes. Either escape them (\") or skip JSON entirely and use the flag form:claude mcp add thrixel --env THRIXEL_API_KEY=... -- uvx thrixel-mcp. See Option 1.spawn uvx ENOENT— the client cannot finduvxonPATH. Use the absolute path:which uvxon macOS / Linux,where.exe uvxon Windows (usuallyC:\Users\YOU\.local\bin\uvx.exe). GUI clients are the usual culprits — they don't inherit your shellPATH.THRIXEL_API_KEY is not set— the key didn't reach the server. Make sure it sits inside an"env": {...}block in your MCP config, not inargs.- Tool calls return "Thrixel rejected the API key" — the key is invalid or revoked. Regenerate at https://thrixel.com/beta (Account → API keys).
- First call is slow —
uvxis resolving and caching the package. Subsequent starts are fast. - "You have N jobs already running" — you hit the per-plan concurrency cap (free 2, pro 5, studio 10). Run large batches in waves;
thrixel_account_statusshows what's in flight. - "Out of cubes" — see Costs.
thrixel_account_statusshows the balance;thrixel_reduce_trianglesand rebakes are free. - Jobs time out — GPU work can queue behind other jobs. Raise
THRIXEL_TIMEOUT_S, or submit withwait=falseand poll viathrixel_job_status. - Client doesn't list
thrixel— make sure the config file is valid JSON (no trailing commas), then fully restart the client. - Stuck on an old version —
uvxcaches builds. Force a refresh withuvx --refresh thrixel-mcp.
Costs
Cubes are Thrixel's usage credits. Three pricing shapes:
| Operation | Cost |
|---|---|
detail_model, sculpt_model, retexture_model |
Flat 40 cubes each |
reduce_triangles, texture rebake |
Free |
create_model, edit_model, autofix_model |
Metered — charged after the run on actual model usage |
Metered is not a synonym for cheap. It scales with how complex the request is:
observed runs land anywhere from single digits to over 100 cubes, so a complex
create_model can cost more than a flat GPU operation. Call
thrixel_account_status to see your balance before a big batch.
Every export format (GLB, FBX, OBJ, STL, USDZ) is free on every plan.
Configuration
| Environment Variable | Description | Default |
|---|---|---|
THRIXEL_API_KEY |
Required. Your Thrixel API key (starts with sk-thrixel-) |
— |
THRIXEL_API_BASE |
API base URL | https://api.thrixel.com |
THRIXEL_OUTPUT_DIR |
Where generated models are written. Writes outside it are refused | ./thrixel_assets |
THRIXEL_TIMEOUT_S |
Ceiling in seconds for a single submit-and-wait cycle | 600 |
THRIXEL_LOG_LEVEL |
Server log level, written to stderr | INFO |
Development
End users need only uvx; contributors want a real environment. Either works:
git clone https://github.com/thrixel/thrixel_mcp.git
cd thrixel_mcp
# uv
uv sync --extra dev
# or conda
conda env create -f environment.yml
conda activate thrixel-mcp
# Unit tests — no backend required
pytest
# End-to-end against a local backend
export THRIXEL_API_BASE=http://localhost:8000
export THRIXEL_API_KEY=sk-thrixel-...
python tests/smoke_local.py # list registered tools
python tests/smoke_local.py thrixel_account_status
python tests/smoke_local.py thrixel_create_model '{"prompt":"a rusted oil drum"}'
Run the packaged entry point exactly as a user would:
uvx --from . thrixel-mcp
This server holds no state and no business logic — it is a client of the public Thrixel API. Anything it can do, a direct API caller can do too.
Seeing the raw protocol
Three levels of visibility, least to most invasive.
1. Tool schemas and one-off calls — MCP Inspector. Prints the raw JSON-RPC result. Note that -e flags go after the target command:
# every tool exactly as the model receives it
npx -y @modelcontextprotocol/inspector --cli uvx thrixel-mcp \
--method tools/list -e THRIXEL_API_KEY=sk-thrixel-...
# invoke one
npx -y @modelcontextprotocol/inspector --cli uvx thrixel-mcp \
--method tools/call --tool-name thrixel_account_status \
-e THRIXEL_API_KEY=sk-thrixel-...
Drop --cli for a web UI that shows each request/response pair.
2. Client-side lifecycle — Claude Code debug log. Shows the connection, negotiated capabilities, which tool was dispatched, and the server's stderr. It does not include the JSON-RPC payloads:
claude --debug-file /tmp/mcp.log -p "check my thrixel account"
grep -i mcp /tmp/mcp.log
3. Every frame from a real session — the wire tap. A transparent stdio proxy that logs both directions to JSONL. This is the only way to see what the model actually chose to send during a normal session:
claude mcp add thrixel-tapped \
--env THRIXEL_API_KEY=sk-thrixel-... \
--env MCP_WIRETAP_LOG=/tmp/thrixel-wire.jsonl \
-- python /path/to/thrixel_mcp/tests/wiretap.py uvx thrixel-mcp
tail -f /tmp/thrixel-wire.jsonl | jq -c '{dir, method, tool, id}'
Each line carries dir (client->server / server->client), the parsed msg, and lifted method / tool / id fields for grepping.
HTTP Transport
<!-- TODO(phase-2): remote Streamable HTTP transport + OAuth 2.1, mounted into the existing FastAPI service. Not implemented yet. -->
TODO — remote HTTP transport is planned but not implemented.
stdioonly for now.
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.