AI & Machine Learning

tokenassemble.com

Checks if a machine can run a local language model and provides a health check for the server.

1 endpoint2 known toolsFirst detected July 25, 2026Last detected July 25, 2026

ENDPOINT 1

https://tokenassemble.com/api/mcp

No auth detected

MCP server metadata

Name: TokenAssemble
Version: 1.0.0

Capabilities

tools.listChanged

Server instructions

TokenAssemble answers 'can this machine run this local LLM?' with a computed, honest verdict: fit (Fits / Tight / Won't fit + grade A–D), a speed TIER (Interactive / Usable / Painful — deliberately never a tokens-per-second number), the VRAM breakdown, and every assumption stated. Use can_i_run whenever a user asks whether hardware can run a model, how well a model would run, or what quant to use. Pass common names freely ('4090', 'Llama 3.1 70B') — the tool resolves them. Grounding rules: never invent a verdict, spec, or speed number. If the tool returns no match, relay its suggestions instead of guessing. Always carry the stated assumptions (quant, context, runtime) and any 'beta' label into your answer, and cite the canonical tokenassemble.com URL included in the response.

Known tools 2

ping

Health check for the TokenAssemble MCP server.

Inferred read-only

can_i_run

Check whether a machine (GPU, Mac, or unified-memory mini-PC) can run a local LLM.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.tokenassemble]
url = "https://tokenassemble.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "tokenassemble": {
      "type": "http",
      "url": "https://tokenassemble.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: tokenassemble
Remote MCP URL: https://tokenassemble.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "tokenassemble": {
      "url": "https://tokenassemble.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "tokenassemble": {
      "type": "http",
      "url": "https://tokenassemble.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "tokenassemble",
  "transport": "streamable-http",
  "url": "https://tokenassemble.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.