MCP server

Token Diet

io.github.Evozim/token-diet

Checked 26 Oct 2026, 08:29 UTC · Not tested (older connection type)

LLM token optimization gateway implementing semantic pruning.

Not checked

https://token-diet-mcp.vercel.app/api/mcp

At a glance

Type: MCP server
Publisher: Not verified
Status: Not checked
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

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 token-diet https://token-diet-mcp.vercel.app/api/mcp

Claude Desktop

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

Codex (config.toml)

[mcp_servers.token-diet]
url = "https://token-diet-mcp.vercel.app/api/mcp"

Gemini CLI

{"mcpServers":{"token-diet":{"httpUrl":"https://token-diet-mcp.vercel.app/api/mcp"}}}

Cursor

{"mcpServers":{"token-diet":{"url":"https://token-diet-mcp.vercel.app/api/mcp"}}}

VS Code

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

Antigravity

agy mcp add token-diet https://token-diet-mcp.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":"token-diet","server_url":"https://token-diet-mcp.vercel.app/api/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"token-diet","server_url":"https://token-diet-mcp.vercel.app/api/mcp"}

JarvisClaw — AI Gateway & API Marketplace
320 AI models + 2,720 pay-per-call APIs. x402 USDC on Base or Solana, no API key.
GLM Flash Pruned
Chat with the 62-GiB expert-pruned GLM Flash on ZeroGPU
dompruner-mcp
Strips layout noise via DOM AST; with a query, BM25 filters to relevant sections. No model or API.
TokenZero
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
Meeba Brain
Repository knowledge graph MCP server for codebase understanding and debugging.
ContextFetch
Web search and any page as LLM-ready Markdown for AI agents. Free keyless tier, no signup.
RQM Robotics Jobs
Delegate 20 typed RQM Robotics jobs for validation, diagnosis, comparison, and optimization.
AgentIndex x402
Jev-powered decisions, web search, PDF/web to Markdown, summarize. From $0.001, no API key.

[![AptLynx](https://aptlynx.net/badge/io.github.Evozim/token-diet.svg)](https://aptlynx.net/servers/io.github.Evozim/token-diet)

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