Thicken runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 16 Oct 2026.
Photos in: a 3D model at the object's real size and its metadata as JSON, for any kind of object.
We read the source, 6 h ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
execFile(program, ['-v', 'error', ...args], (error, stdout, stderr) => {
const picture = await upright(sharp(await readFile(path.join(dir, name))), { ...source, time: Math.round((k / rate) * 10) / 10 });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add thicken -- npx -y thicken
{
"mcpServers": {
"thicken": {
"args": [
"-y",
"thicken"
],
"command": "npx"
}
}
}
[mcp_servers.thicken]
command = "npx"
args = ["-y", "thicken"]
{
"mcpServers": {
"thicken": {
"args": [
"-y",
"thicken"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"thicken": {
"args": [
"-y",
"thicken"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
THICKEN_VISION_URL (An OpenAI-compatible vision endpoint (optional): photos needn't be cropped), THICKEN_VISION_KEY (The vision endpoint's key), THICKEN_VISION_MODELS (The endpoint's model names, comma-separated, primary first), GOOGLE_BOOKS_API_KEY (Your own Google Books quota, for book sizes).
The author declared them in the registry entry; get the values from the project itself.
Read RSS, Atom and JSON feeds, or find the feed of any website, with filters and only-new mode
SWAT+ watershed models for any river in the lower 48 states, with groundwater and PFAS data
Web access for AI agents: URL to Markdown, link metadata, screenshots, links and images of any URL.
Official MCP connector for Legalize: read and search its whole open corpus, at any point in time.
Read-only MCP connector for Charmshots photoshoots, photo metadata and owner-authenticated links.
Give any LLM agent a real Android or iPhone as its body. 62 MCP tools for mobile automation.
A real Android phone in the cloud for MCP agents: observe the screen, act, reset to a saved state.
Metadata-first fiction editing and reasoning tools for long-form writing projects.
Answers built from our own checks of this server.