Developer · Local MCP server
Tensorcad
Design transformer LLM architectures and report their parameters, FLOPs, memory and cost.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.Filip-Pajalic/tensorcad- Version
- 0.1.21
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-09-26
- Updated
- 2026-09-26
- Publisher
- Filip-Pajalic (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/Filip-Pajalic) · how
- Website
- github.com/Filip-Pajalic/TensorCAD
- Repository
- github.com/Filip-Pajalic/TensorCAD (folder packages/mcp)
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npmruntime: npx | @tensor-cad/mcp | 0.1.21 | stdio |
How to connect Tensorcad
Tensorcad runs locally from a Node.js package published to the npm registry: @tensor-cad/mcp version 0.1.21. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx - the usual command is npx -y @tensor-cad/mcp@0.1.21. It reads the environment variable TENSORCAD_ROOT; set it in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"tensorcad": {
"command": "npx",
"args": [
"-y",
"@tensor-cad/mcp@0.1.21"
],
"env": {
"TENSORCAD_ROOT": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| temporal-mcpWall-clock awareness for LLM agents. Two tools: elapsed-time-between-turns + day rollover detection. | Remote & Local · HTTP, stdioLive check: ✓ handshake |
| Tempreon - Personal AI MemoryPerson-owned AI memory that learns, not just stores - portable context for any MCP client. | Remote · HTTPLive check: sign-in required |
| TenantsdbMulti-tenant database orchestration: isolated Postgres, MySQL, MongoDB, Redis tenants on demand. | Remote · HTTPLive check: sign-in required |
| Tenki Sandbox MCPDisposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs. | Local · stdio |
| Tentra - Memory for AI Coding AgentsMemory for AI coding agents. Call graphs + refactor safety + persistent code context. 35 MCP tools. | Remote & Local · SSE, stdioLive check: sign-in required |
| TeramindMCP server for Teramind's insider-threat/employee-monitoring API (read-only, metadata-only surface). | Local · stdio |
| TermadaPersistent, policy-controlled missions for AI agents operating local and SSH environments. | Local · stdio |
| TermcpAn MCP server that lets AI agents act like a human at a real terminal, local or over SSH. | Local · HTTP |