Ai Rate Limit Tracker

io.github.lazymac2xPublished by GitHub account lazymac2xv1.0.0Updated Oct 24, 2026

Cloudflare Workers MCP server: ai-rate-limit-tracker

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

A remote MCP server that tracks AI provider rate limits, records API usage, and forecasts when limits will run out.

What you can do
Look up published rate limit specs (RPM, TPM, RPD, context window) for a provider and optional model, and list supported providers with their models and default limits. Record an AI API call to get real-time usage counters and warnings when approaching limits. Forecast when rate limits will be exhausted and get scheduling recommendations.
When to use it
Useful when you call AI provider APIs and want an assistant to check published limits, keep usage counters, and plan around approaching or forecast exhaustion.
Requirements
A remote streamable HTTP endpoint; no packages, environment variables, headers, or authentication are declared.
Before you install
track_usage records AI API call data on a third-party service; the input does not state what is stored or retained. No authentication is declared, so consider what usage data you send.

Installation

In SourceWeft

  1. Open Ai Rate Limit Tracker in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.lazymac2x%2Fai-rate-limit-tracker/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "ai-rate-limit-tracker": {
      "type": "http",
      "url": "https://api.lazy-mac.com/ai-rate-limit-tracker/mcp"
    }
  }
}

README

ai-rate-limit-tracker-api

Cloudflare Workers MCP server: ai-rate-limit-tracker. REST + MCP (JSON-RPC 2.0). Live: api.lazy-mac.com/ai-rate-limit-tracker

Source: README.md at commit 5809593

Tools

4

get_provider_limits

Get published rate limit specs (RPM, TPM, RPD, context window) for an AI provider and optional model.

Parametersmodelproviderrequired

list_providers

List all AI providers supported by the tracker with their models and default limits.

Takes no parameters.

track_usage

Record an AI API call and get real-time usage counters plus warnings if approaching limits.

Parametersmodelapi_keyrequiredproviderrequiredlatency_mstokens_used

get_forecast

Forecast when rate limits will be exhausted and get scheduling recommendations.

Parametersmodelapi_keyrequiredproviderrequiredrate_rpm

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

90% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.