count_tokens
9 registry entries were observed exposing a tool named count_tokens — none of them flagged as a privileged capability.
Spelled count_tokens, count-tokens in the wild — all one tool for the purposes of this page.
Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 8,491 of 26,663 scannable entries (32%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.
- @ooples/token-optimizer-mcpverifiedMCP serverobserved · static extractionCross-client context optimization and durable live knowledge capture for AI coding agents and CLI tools
- com.promptibus/mcpverifiedMCP serverobserved · static extractionModel intelligence for AI agents — syntax, params, pricing for 67+ generative AI models.
- MCP serverobserved · static extractionMCP server that cuts LLM token costs: accurate token counting, cost estimates across GPT/Claude/Gemini, rule-based prompt slimming with meas
- MCP serverobserved · static extractionDeterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 38 tools.
- MCP serverobserved · static extractionPay-per-call AI agent utilities via x402 on Base (USDC). 7 tools, $0.003/call.
- MCP serverobserved · static extraction19 focused API tools for AI agents: contract review, prompt optimizer, context packing, and more.
- MCP serverobserved · static extractionToken-aware message truncation: fit a chat history into your model's context budget.
- MCP serverobserved · static extractionIntelligent token optimization achieving 95%+ reduction through caching, compression, and 80+ tools
- MCP serverobserved · static extractionAnalyze your MCP setup: token costs, grades, duplicates, and optimization tips