MCP server

tokcalc MCP Server

io.github.stevecrates489-commits/tokcalc

Checked 26 Oct 2026, 08:29 UTC · It answered and asked for a sign-in

LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.

Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Needs an API key

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http tokcalc https://tokcalc.vercel.app/api/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.tokcalc]
url = "https://tokcalc.vercel.app/api/mcp"

Gemini CLI

{"mcpServers":{"tokcalc":{"httpUrl":"https://tokcalc.vercel.app/api/mcp"}}}

Cursor

{"mcpServers":{"tokcalc":{"url":"https://tokcalc.vercel.app/api/mcp"}}}

VS Code

{"servers":{"tokcalc":{"type":"http","url":"https://tokcalc.vercel.app/api/mcp"}}}

Antigravity

agy mcp add tokcalc https://tokcalc.vercel.app/api/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"tokcalc","server_url":"https://tokcalc.vercel.app/api/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"tokcalc","server_url":"https://tokcalc.vercel.app/api/mcp"}

Needs an API key or token from its maker, usually added as a header in the setup.

Browse

• GitHub tools
• GitHub and code hosting
• Calling other AI models

Related MCP servers

• calc.engineer
  88 free engineering calculators: RF link budgets, LoRa/Meshtastic, PCB, solar, homelab. Keyless.
• Neurogenesis
  Developmental agents for the agent economy: create an agent from a digital genome, then evolve it wi
• Nodegrove VRAM: can I run it?
  Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
• exascale.build
  US ISO interconnection queues and cited energy data. 25 free queries, then $49/mo or $490/yr.
• Upper Route Planner MCP by usefulapi
  Read Upper drivers and stops; create and optimize routes, assign drivers, share routes to the app.
• GPU Economy - cloud GPU prices
  Hourly cloud GPU prices from 80+ providers: find, compare, cost and track GPUs.
• Hive DePIN
  MCP server: DePIN reward routing, capacity verification, settlement reports · Hive Civilization
• Liqaa Meetings
  Create encrypted LIQAA video meetings; read plans, capacity & stats. No install, no account.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.stevecrates489-commits/tokcalc.svg)](https://aptlynx.net/servers/io.github.stevecrates489-commits/tokcalc)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents