AI Token Cost Optimization MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AI Token Cost Optimization MCP Servercount tokens in 'What is the capital of France?' for gpt-4o"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AI Token Cost Optimization — MCP Server
A production-ready Model Context Protocol (MCP) server that provides 4 tools to count tokens, estimate API costs, optimize prompts, and compare AI model pricing. Compatible with Cline, Claude Desktop, and any MCP-compatible client.
Tools Overview
Tool | Description |
count_tokens | Count tokens in any text for GPT-4o, GPT-4o-mini, Claude 3.5 Sonnet, Claude 3.5 Haiku, or Gemini 1.5 Flash. Includes cost estimation. |
estimate_cost | Estimate the full API call cost: input cost + output cost. Supports USD and INR. |
optimize_prompt | Analyze a prompt and get suggestions to reduce token usage. Also recommends the cheapest model for your text. |
compare_models | Compare all 5 models side-by-side for your prompt, sorted from cheapest to most expensive. |
Related MCP server: TokenLens MCP Server
Project Structure
my-mcp-server/
├── src/
│ ├── index.ts # MCP server (4 tools)
│ ├── types.ts # TypeScript interfaces
│ ├── pricing.ts # Model pricing data (USD/INR)
│ └── tokenizer.ts # Token counting (gpt-tokenizer o200k_base)
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration
├── README.md # This file
└── DOCUMENTATION.md # Full process documentationPrerequisites
Node.js v18 or higher
npm (comes with Node.js)
Quick Start
# Navigate to the project directory
cd C:\Users\ghosh\Documents\MSS\my-mcp-server
# Install dependencies
npm install
# Run in development mode
npm run devUsage
Development Mode (hot-reload with tsx)
npm run devDevelopment Mode (with auto-reload)
npm run dev:watchProduction Mode
npm run build # Compile TypeScript to dist/
npm start # Run compiled versionTypeScript Type-Check
npx tsc --noEmitTesting the Server
Option 1: MCP Inspector (Recommended)
npx @modelcontextprotocol/inspector npx tsx src/index.tsOpens a web UI at http://localhost:5173 — browse tools, call them, see responses.
Option 2: Quick Command-Line Test
Test all 4 tools in one command:
cd C:\Users\ghosh\Documents\MSS\my-mcp-server
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}
{"jsonrpc":"2.0","method":"notifications/initialized"}
{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"count_tokens","arguments":{"text":"Hello World!","model":"gpt-4o"}}}
{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"compare_models","arguments":{"prompt":"Hello","estimated_output_tokens":100}}}' | npx tsx src/index.ts 2>/dev/nullCline Configuration
Add to your Cline MCP settings:
{
"mcpServers": {
"hello-world": {
"command": "npx",
"args": [
"tsx",
"C:\\Users\\ghosh\\Documents\\MSS\\my-mcp-server\\src\\index.ts"
]
}
}
}macOS/Linux: Use forward slashes:
"/Users/ghosh/Documents/MSS/my-mcp-server/src/index.ts"
Tool Details
count_tokens
Parameters:
Field | Type | Required | Description |
| string | ✅ | The text to count tokens for |
| string | ✅ | gpt-4o, gpt-4o-mini, claude-3.5-sonnet, claude-3.5-haiku, gemini-1.5-flash |
| string | ❌ | USD (default) or INR |
Example response:
{
"model": "gpt-4o",
"token_count": 7,
"character_count": 31,
"tokenizer": "OpenAI o200k_base (via gpt-tokenizer) — exact",
"estimated_input_cost": "$0.000018",
"currency": "USD"
}estimate_cost
Parameters:
Field | Type | Required | Description |
| string | ✅ | The input prompt text |
| number | ❌ | Default: 500 |
| string | ✅ | Model identifier |
| string | ❌ | USD (default) or INR |
Example response:
{
"model": "gpt-4o",
"provider": "OpenAI",
"input_tokens": 6,
"output_tokens": 200,
"input_cost": "$0.000015",
"output_cost": "$0.002000",
"total_cost": "$0.002015",
"currency": "USD"
}optimize_prompt
Parameters:
Field | Type | Required | Description |
| string | ✅ | The prompt to analyze |
| string | ✅ | Model identifier |
Example response:
{
"original_token_count": 15,
"character_count": 62,
"suggested_improvements": [
{ "suggestion": "Replace verbose phrases...", "estimated_savings_percent": 5 },
{ "suggestion": "Consider using GPT-4o-mini...", "estimated_savings_percent": 60 }
],
"best_model_recommendation": "Switch to gpt-4o-mini for ~60% cost savings."
}compare_models
Parameters:
Field | Type | Required | Description |
| string | ✅ | The input prompt text |
| number | ❌ | Default: 500 |
| string | ❌ | USD (default) or INR |
Example response:
{
"prompt_character_count": 11,
"estimated_output_tokens": 100,
"currency": "USD",
"comparisons": [
{ "model": "gpt-4o-mini", "total_cost": "$0.000060" },
{ "model": "claude-3.5-haiku", "total_cost": "$0.000503" }
],
"summary": {
"cheapest": "gpt-4o-mini",
"most_expensive": "claude-3.5-sonnet"
}
}Supported Models & Pricing
Model | Provider | Input (per 1K tokens) | Output (per 1K tokens) |
GPT-4o | OpenAI | $0.00250 | $0.01000 |
GPT-4o-mini | OpenAI | $0.00015 | $0.00060 |
Claude 3.5 Sonnet | Anthropic | $0.00300 | $0.01500 |
Claude 3.5 Haiku | Anthropic | $0.00100 | $0.00500 |
Gemini 1.5 Flash | $0.00150 | $0.00900 |
Technical Details
Field | Value |
SDK |
|
Token Counting |
|
Transport |
|
Module System | ES Modules ( |
Runtime | Node.js >= 18 |
Dev Runner |
|
Example Cline Prompts
After connecting the server, try asking Cline:
"Count the tokens in 'Hello World from my MCP Server!' using GPT-4o"
"Estimate the cost of sending a 100-token prompt with 500 output tokens on Claude 3.5 Sonnet in INR"
"Which is the cheapest model for this prompt: 'Write a poem about artificial intelligence' with 200 output tokens?"
"Analyze this prompt for optimization: 'I would like you to please write a detailed report'"
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Find AI model pricing, estimate token costs and compare offers. No API key required.
Compare up-to-date pricing for 40+ LLMs (incl. Chinese) & estimate cost from tokens. EN/zh.
Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.
Compare LLM API pricing, estimate workload costs, and benchmark cloud compute. By OptimNow.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides real-time token pricing for AI models, model comparison, cost calculation, and token usage tracking for agents and developers.-
- FlicenseAqualityDmaintenanceEnables AI agents to compare AI model pricing plans, run cost scenarios, find break-even points, and get plan recommendations using TokenLens data.4-
- FlicenseNot gradedqualityDmaintenanceEnables AI cost calculation, comparison, and optimization across major providers like Anthropic, OpenAI, Google, Meta, and Mistral. Supports cost estimation, budget-aware model finding, and token estimation through a simple API and MCP integration.-
- AlicenseNot gradedqualityDmaintenanceEstimates, compares, and controls LLM API costs before agents spend tokens, with tools for cost estimation, model comparison, and budget checking.44 npmMIT