Mcp Token Optimizer

io.github.rccola990-cloudPublished by GitHub account rccola990-cloudv0.1.1Updated Oct 24, 2026

Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.

VerifiedSTDIODesktop onlyAI & ML

Overview

AI-generated overview

Local MCP server that helps an assistant count tokens, estimate LLM costs, trim prompts, and choose a cheaper capable model.

What you can do
  • Count tokens in text or prompts before sending them to a model.
  • Estimate the cost of a request or workload.
  • Slim down prompts to reduce token usage.
  • Compare models and suggest the cheapest one that still fits the task.
When to use it
Useful when you want to keep LLM spending down: checking how large a prompt is, comparing model prices, or trimming context before a costly call. Less relevant if you do not work with LLM prompts or budgets.
Requirements
Runs as a local process over stdio, installed from the npm package mcp-token-optimizer, so Node.js is needed. No authentication, environment variables, or headers are declared.
Before you install
No credentials or write actions are declared. Cost and model recommendations are estimates, so verify pricing against the provider before relying on them for budgeting.

Installation

In SourceWeft

  1. Open Mcp Token Optimizer in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

This repository has no README.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.