Zero-cost token optimization engine for AI coding assistants (Claude Code, Cursor, Antigravity, Windsurf). Saves 70-95% tokens via AST skeletons, differential cache, and line slicing.
🍯 TokenJar Put tokens back in your jar. Save 70-95% tokens for AI coding assistants without losing functionality.
MCP server that saves 70-95% tokens for AI coding assistants — without losing functionality.
TokenJar sits between your AI coding assistant and your codebase, intelligently compressing code reads, terminal outputs, and file operations to dramatically reduce token consumption, context compaction, and latency.
Works with Claude Code, Cursor, Antigravity (AGY), Windsurf, Continue.dev, and any MCP-compatible AI assistant.
Module What It Does Token Savings :---:---:--- 🦴 Code Skeletonizer Extracts structural skeleton (signatures, types, docstrings) via Tree-sitter AST 80-95% 📖 Smart File Reader L1 RAM + L2 Persistent SQLite cache with differential reads & diff headers 90-99% 🛡️ Lockfile & Asset Shield Intercepts massive lockfiles & minified bundles with surgical version queries (query="react") 99% 🎯 Blast Radius & Symbols Instant global symbol lookup & cross-file reference caller tracking (findsymbolreferences) 85-95% 🖥️ Terminal Pruner Compresses test/build/git terminal streams, keeps errors and summary info 60-90% 🗺️ Repo Map PageRank & Graph Centrality codebase overview fitted into custom token budgets Budget-fitted 🎨 On-Demand UI Dashboard Lightweight standalone control panel (tokenjar ui) with Zero Background RAM Instant ⚡ 1-Click IDE Configuration Automatic configuration & non-destructive rollback for Cursor, Windsurf, Claude, VS Code Zero-effort
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/Farukes--TokenJar.html)
Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
00200200/tokencutKeep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
pinoox/neuromeshThe Biomimetic Context Engine & Neural Runtime for AI Coding Assistants
ParsaVictor/code-context-engineLocal-first MCP context engine for AI coding agents — cuts token cost ~90% via a per-project code graph + code folding. Works with Cursor, Claude Code, Codex & any MCP client. Web + ML/PyTorch codebas
mcpdelta/mcpdeltaDelta MCP is a free app that sits between your AI apps and their MCP servers: one program per task instead of one tool call per step, up to 24.1× fewer tokens in our benchmarks. Every change is record
2akouwu/reverifyStop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.