Skip to main content
Glama
162,699 tools. Last updated 2026-05-30 10:29

"A guide for reducing token count in AI requests" matching MCP tools:

  • Fetch repository statistics: file count, symbol count, edge count, line count, and estimated token costs per mode. Use to plan your token budget.
    AGPL 3.0
  • Retrieve AI-extracted feature requests from user feedback, ranked by vote count, with filtering options for status, app ID, and search.
  • Count tokens for AI models like GPT-4, Claude, and Gemini before sending requests to manage usage and costs effectively.
    MIT

Matching MCP Servers

Matching MCP Connectors

  • Cloudflare Workers MCP server: ai-token-counter

  • India Open Government Data (OGD) Platform MCP — data.gov.in

  • Fetch SRC-20 token metadata by ticker: deploy info, max supply, mint progress, holder count, and creator. Provides essential data for Bitcoin Stamps fungible tokens.
    MIT
  • Retrieve BRC-20 token protocol and market metadata by ticker: price, supply, mint progress, holder count, and market cap.
    MIT
  • Get your current usage against all enforced budgets: star count, monthly unstar budget, and daily MCP and REST API requests, each with a reset timestamp.
    MIT
  • List ClickHouse tables in a database with optional pattern filtering, pagination, and column detail control. Each table shows schema, comment, row count, and column count for quick database inspection.
    Apache 2.0
  • Retrieve all available indicator feeds for a given token: includes EMA, RSI, Bollinger, and Volatility across timeframes, along with reliability stats and data source count.
    MIT
  • Retrieve the top Pump.fun token launches ranked by market capitalization within the last 24 hours. Provides a formatted table including rank, token name, mint address, market cap, and trade count for analysis.
    MIT
  • Execute multiple Gitopia operations atomically in one on-chain transaction, reducing gas costs and round-trips. Supports up to 10 operations: dao_vote, dao_update_members, comment_on_issue, comment_on_pull_request.
    MIT
  • Retrieve a client-side token by ID for initializing Paddle.js in sandbox or production environments, with status indicators for active or revoked tokens.
    Apache 2.0
  • Execute LLM requests by burning Shells to get AI-generated responses with calculated costs based on model and token usage.