MCP servers tagged token-saving

7 live MCP servers tagged "token-saving", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with token-saving.

live servers

avg trust

Codex Chatgpt Bridge

A safe bridge for Codex and ChatGPT to hand off coding work, save tokens, and keep local execution under control.

Contextcore

ContextCore: An MCP server for Claude (or any AI tool) that enables massive token saving through hybrid search (BM25 + Embeddings)

Opencode Lazy Loading

Opencode lazy load plugin Saves 85%+ on tools and MCP servers tokens per request. The LLM loads tool instructions on-demand instead of receiving thousands of tokens of schemas it…

Supamem

Project-agnostic dual-memory MCP CLI for Claude Code, Cursor, and OpenCode (Qdrant tuned hybrid retrieval + structural memory hooks)

Tokesave

The ultimate AI token-saving MCP middleware — compression, caching, injection shield, multi-server routing, and more.

Suber Agent Team

MCP server that offloads Claude Code sub-agents to a cheap model (Haiku / any OpenAI- or Anthropic-compatible API) - run 20-100 parallel agents for fan-out, map-reduce & research…

Hermes Ztk Integration

Transparent ztk (shell output compressor) integration for Hermes Agent. Auto-wraps non-interactive commands, saves 60-99% context tokens.