Tensorcad runs on your own machine — the client starts it, so there is no endpoint to ping. 70 installs a week from npm. Last commit 26 Sep 2026.
Design transformer LLM architectures and report their parameters, FLOPs, memory and cost
We read the source, 2 d ago · rules 995398eba69f
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.
этот файл ставится пользователю, но в репозитории его нет
out = eval(value, {"__builtins__": {}}, dict(resolved)) # noqa: S307
full := filepath.Join(target, clean)
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 tensorcad -- npx -y @tensor-cad/mcp
{
"mcpServers": {
"tensorcad": {
"command": "npx",
"args": [
"-y",
"@tensor-cad/mcp"
]
}
}
}
[mcp_servers.tensorcad]
command = "npx"
args = ["-y", "@tensor-cad/mcp"]
{
"mcpServers": {
"tensorcad": {
"command": "npx",
"args": [
"-y",
"@tensor-cad/mcp"
]
}
}
}
{
"servers": {
"tensorcad": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@tensor-cad/mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
TENSORCAD_ROOT (Directory the server scans for .tensorcad.json files and resolves relative paths against. Defaults to the process working directory).
Audit architecture, security, memory, and code quality in Flutter, Laravel, Node, Python, & Vue.
Maps any repo into an architecture diagram (Mermaid/Graphviz) and enforces architecture rules in CI
AI-native Day 0 modernization platform for PRDs, architecture, work orders, and code transformation.
Privacy-first work tracking with summaries, reports, coaching, and AI-ready long-term memory.
Create, update, complete nodes, search & replace with regex and dry run, usage reports, transforms
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
Answers built from our own checks of this server.