mcpbeat Sign in

Token Diet MCP Server

answering

Token Diet is answering right now. Last checked 2 min ago.

LLM token optimization gateway implementing semantic pruning.

Uptime history 48 days of history · worst day 99%
48 days agonow
100.0%
Uptime 24h
92 of 92 checks
Tools
hidden behind auth
92 ms
Response time
average over 24h
authentication required
Access
sse

Nothing serious here today

Today is the operative word: we check Token Diet every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

run in your terminal
claude mcp add token-diet --transport http https://token-diet-mcp.vercel.app/api/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "token-diet": {
      "url": "https://token-diet-mcp.vercel.app/api/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.token-diet]
url = "https://token-diet-mcp.vercel.app/api/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "token-diet": {
      "url": "https://token-diet-mcp.vercel.app/api/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "token-diet": {
      "url": "https://token-diet-mcp.vercel.app/api/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.

Endpoints

URLTransportStateLatencyChecked
https://token-diet-mcp.vercel.app/api/mcp sse needs auth 89 ms 2 min ago

Alternatives to Token Diet

same job, measured the same way
Wordlift
by wordlift

Knowledge Graph, GraphQL, GS1 Digital Link and SEO tools for semantic content optimization.

answering
Authenticated Multi LLM Agent
by mikerawsonnz

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f

2 tools answering
Hardware Probe
by yamaru-eu

Hardware probe for performance diagnostics, thermal monitoring, and LLM optimization.

39 installs/wk local only
MCP Checkup
by yifanyifan897645

Analyze your MCP setup: token costs, grades, duplicates, and optimization tips

72 installs/wk local only
MCP LLM Gateway
by daedalus

MCP-compatible LLM gateway that proxies completion requests.

56 installs/wk local only
Agentskin
by shawn5cents

The Semantic Layer for AI Agents. Prunes noisy API data by 70%+ for token-efficient reasoning.

163 installs/wk local only
distil
by munhq

Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.

53 installs/wk local only
datoon
by andrii-su

Smart structured-data to TOON gateway: converts to TOON only when it saves LLM tokens.

100 installs/wk local only

Token Diet — questions

Answers built from our own checks of this server.

Why is there no tool list for Token Diet?
The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.
Is Token Diet working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 92 ms. The bar chart above shows every period we have measured.
How do I connect Token Diet?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You will need your own credentials: it refuses anonymous clients.
Does Token Diet need an API key?
Yes. Every time we knock, Token Diet answers with an authorization challenge instead of its tool list — that is how we know it is running and gated rather than broken. Bring your own credentials and it will talk.
How fast is Token Diet?
It answers our handshake in 92 ms on average, which is faster than 84% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.