io.github.stevecrates489-commits/tokcalc
down checked
Unclaimed · Unverified
Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.
Publisher-provided title
tokcalc MCP Server
Publisher-provided description
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
Summary by lookupd
Lets an agent estimate LLM serving needs such as VRAM, KV cache size, GPU layout, latency and cost for deployment planning.
Install
Claude Code, remote (streamable-http)
claude mcp add --transport http tokcalc https://tokcalc.vercel.app/api/mcp
Claude Code, npm package (stdio)
claude mcp add tokcalc -- npx -y @tokcalc/mcp-server
Codex, remote (streamable-http)
codex mcp add tokcalc --url https://tokcalc.vercel.app/api/mcp
Codex, npm package (stdio)
codex mcp add tokcalc -- npx -y @tokcalc/mcp-server
Cursor, remote (streamable-http) → .cursor/mcp.json
{
"mcpServers": {
"tokcalc": {
"url": "https://tokcalc.vercel.app/api/mcp"
}
}
}Cursor, npm package (stdio) → .cursor/mcp.json
{
"mcpServers": {
"tokcalc": {
"command": "npx",
"args": [
"-y",
"@tokcalc/mcp-server"
]
}
}
}Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.
Details
- Version: 0.3.4
- Transports: streamable-http, stdio
- Uptime (7 days): 0%
- First indexed:
- Last seen in registry:
- Repository: https://github.com/stevecrates489-commits/tokcalc
Badge for your README
Shows this live status and links here; updates hourly.
[](https://lookupd.com/servers/io.github.stevecrates489-commits/tokcalc)
- 62141 servers
- Last crawl: 2026-11-11T18:17:25.333Z
- API base:
https://api.lookupd.com - MCP URL:
https://api.lookupd.com/mcp