- Conduid
- Marketplace
- #tokenizer
MCP servers tagged tokenizer
10 live MCP servers tagged "tokenizer", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with tokenizer.
Tokenfold
Local, provider-neutral compression for LLM prompts, tool schemas, JSON, logs, and diffs. Lossless, receipt-audited, no ML tax.
Mcpusage
CLI for measuring MCP server tool advertisement token usage
Size
Bundle analyzer for MCP tools — measure MCP schema and context token overhead.
Codebase Index
⚠️ MOVED → https://github.com/lost-in-the/woods — install gem 'woods' instead
Context Canary
A token counter overlay for Claude. Warns you before context compaction hits so you can save what matters.
Tokenometer
LLM cost calculator, token counter, latency benchmark, CI guardrail, MCP server, and VS Code/Cursor extension.
Nuxs
Up to 99% token savings on AI agent context. Free. Provider-agnostic (Claude, Cursor, Codex, Cline, any MCP agent). 91.62% over 626.8M auditable tokens. Try: nuxs.ai/playground
Context Squeeze
Deterministic context-compression MCP server for Claude: squeeze codebases, files, and logs to fit token budgets using tree-sitter and tree-walking — no LLM in the loop. (Rust)
Token Guard
MCP server, written in Java 21 and compiled to a GraalVM native image, that reduces LLM token consumption in agentic coding workflows.
Agentfit
Fit your messages into the LLM context window. Token-aware truncation with multiple strategies, pluggable tokenizers, zero deps.