- Conduid
- Marketplace
- #token-savings
MCP servers tagged token-savings
30 live MCP servers tagged "token-savings", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with token-savings.
MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Enola
Understand, analyze, and govern software systems across repositories, languages, and technologies.
Opentoken
Token-saving companion for OpenCode — 42 compression layers, zero risk, no caveman speak
Git Courer
MCP server for Git with local Ollama — zero tokens for git operations
Git Courer
MCP server for Git with local Ollama — zero tokens for git operations
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. 93% token savings benchmarked. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cer…
PsYcGoD/sage
`, stores command history locally, and returns compressed terminal output to reduce context noise.
Context Diamond
Auditable context capsules for LLM handoffs, coding agents, and OpenCode MCP workflows.
Tscg
TSCG — Deterministic tool-schema compiler for LLM agents. 50-72% token savings, 50 tools in 2.4ms. Phi-4 recovers from 0% to 90% accuracy. 459 tests, zero dependencies, MIT.
Simplicio
🔥 Save up to 96% tokens — more than Caveman (65%) or RTK (80%). AI coding agent: chat, map, edit, multi-agent. Single Rust binary.
Supamem
Project-agnostic dual-memory MCP CLI for Claude Code, Cursor, and OpenCode (Qdrant tuned hybrid retrieval + structural memory hooks)
Novgraph
Open-source Novgraph client for coding agents: recorded intent, co-change context, ranked blast radius, architecture context, precise code discovery, continuous history, visible c…
Save My Tokens
Save Claude tokens by offloading tasks to free LLM APIs - 19x more workflows with the same token budget
Rwkv Router
Cut up to ~89% of cloud LLM tokens. Self-evolving local-first smart router (R0-R3, ~100% routing accuracy after evolution) - Stanford & Together AI baseline: 60-80% cost/energy sa…
Simem
simem — Super Intelligence Memory for AI coding agents. Local project memory shared across Claude Code, Codex and Cursor (every account, every worktree), and fewer tokens per sess…
Codex Agent Mem
Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs…
Token Savers
Curated, measurement-driven collection of token-saving MCPs for Claude Code, Codex, Cursor & Windsurf. Each MCP shipped here has passed Humanswith.ai's deterministic-compressor be…
Shuttle Stack
Local-inference layer for coding agents: your files are read by llama.cpp on your machine, not by your agent's context. MCP, rootless Podman, no egress, cited answers, measured.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.