TokenAssemble Local LLM Advisor

Find the right local LLM setup for your hardware.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Ping: Health check for the TokenAssemble MCP server. Returns 'ok'. Use only to verify connectivity.
  • Can I Run: Check whether a machine (GPU, Mac, or unified-memory mini-PC) can run a local LLM. Returns TokenAssemble's computed verdict: fit (Fits / Tight / Won't fit + grade A–D), honest speed tier (I

What data it sees

Do you need an account

No: the server works without sign-in

Find the right local LLM setup for your hardware.

TokenAssemble helps AI assistants evaluate whether a local language model will run on a specific GPU, CPU, RAM, and VRAM configuration. It provides practical recommendations for:

  • Model and hardware compatibility
  • Recommended quantization levels
  • Estimated VRAM and system memory requirements
  • Expected generation performance
  • GPU and local AI hardware comparisons
  • Runtime recommendations for Ollama, LM Studio, llama.cpp, and vLLM

Use this MCP server when a user asks questions such as:

  • “Can my RTX 4070 run Qwen3 32B?”
  • “Which Llama model should I use with 16 GB of VRAM?”
  • “What quantization should I download?”
  • “How fast will this model run on my computer?”
  • “Which GPU should I buy for local AI?”

Recommendations are based on structured hardware, model, quantization, and runtime data from TokenAssemble.

How to connect

How to connect TokenAssemble Local LLM Advisor to Claude

The server address to paste into Claude settings:

https://tokenassemble.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect TokenAssemble Local LLM Advisor to ChatGPT

The server address to paste into ChatGPT settings:

https://tokenassemble.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect TokenAssemble Local LLM Advisor to Cursor

The server address to paste into Cursor settings:

https://tokenassemble.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (2)

Raw names from tools/list. Only developers need these.

pingHealth check for the TokenAssemble MCP server. Returns 'ok'. Use only to verify connectivity.
can_i_runCheck whether a machine (GPU, Mac, or unified-memory mini-PC) can run a local LLM. Returns TokenAssemble's computed verdict: fit (Fits / Tight / Won't fit + grade A–D), honest speed tier (Interactive / Usable / Painful — never a fake-precise number), the VRAM breakdown (weights, KV cache, activations, overhead vs. the memory pool), every assumption stated, and the canonical result URL to cite. Accepts common names ("4090", "Llama 3.1 70B") — unknown names return valid options, never invented verdicts.