TokenSave

io.github.aovestdipaperinoPublished by GitHub account aovestdipaperinov4.0.2Updated Nov 3, 2026

Code intelligence for 15+ languages: semantic graph queries instead of file reads. 37 MCP tools.

VerifiedSTDIODesktop onlyKnowledge & Memory Developer Tools

Server details

Identifier: io.github.aovestdipaperino/tokensave
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account aovestdipaperino for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.aovestdipaperino%2Ftokensave.svg)](https://sourceweft.com/mcp/io.github.aovestdipaperino%2Ftokensave?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

TokenSave builds a local semantic code graph of your project so an AI coding agent can query symbols, callers and context instead of grepping and reading files.

What you can do: Search code by meaning and retrieve symbols, relationships and snippets in one call
Build task context with entry points, related symbols and source code
Trace callers, callees and impact radius of a symbol; detect dead code and complexity
Edit files through anchored replace, multi-replace and AST rewrite primitives, with automatic re-indexing
Index per git branch and compare or search across branches
Report code-health metrics, test mapping and token/cost savings
When to use it: Useful when an agent works in a large multi-language repository and burns tokens on repeated grep, glob and file reads, or when you want impact analysis and structured edits rather than raw file scanning.
Requirements: Runs as a local process on the user's machine (desktop only). Install via Cargo, Homebrew, Scoop or a prebuilt binary, then run the setup command to register the MCP server with your agent and initialize the project to create its local index. No API keys or environment variables are declared.

Before you install

The setup command registers the server and integrations with detected agents and can offer global Git hooks, so review what it writes. Edit tools modify files in your project, though the index re-syncs afterwards. The README states processing is local with no external services, but a privacy section on network calls exists, so check it if that matters.

Installation

In SourceWeft

Open TokenSave in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[MCP Toplist]

[TokenSave]

Semantic Code Intelligence for AI Coding Agents

Fewer tokens • Fewer tool calls • 100% local

[GitHub stars] [crates.io] [License: MIT] [Rust] [Built with AI — part of Enzo Lombardi's AI portfolio]

[macOS] [Linux] [Windows] [Hypercommit] [Listed in the Lulu MCP marketplace]

Why tokensave?

AI coding agents waste tokens exploring codebases. Every grep, glob, and file read costs money. On complex tasks, agents spawn multiple Explore sub-agents that scan hundreds of files just to build context.

tokensave gives agents a pre-indexed semantic knowledge graph. Instead of scanning files, the agent queries the graph and gets instant, structured answers -- the right symbols, their relationships, and source code, in one call.

How It Works

mermaid

flowchart TB    subgraph agent["AI Coding Agent (Claude Code, Codex, Gemini, Cursor, ...)"]        task["Implement user authentication"]        first["Sub-agent"]        second["Sub-agent"]        task --> first        task --> second        first --- second    end
    subgraph server["tokensave MCP Server"]        search["Search: auth"]        callers["Callers: login()"]        context["Context for task"]        db[("libSQL Graph DB<br/>Instant lookups<br/>FTS5 search")]        search --> db        callers --> db        context --> db    end
    first --> search    first --> callers    second --> context

flowchart TB    subgraph agent["AI Coding Agent (Claude Code, Codex, Gemini, Cursor, ...)"]        task["Implement user authentication"]        first["Sub-agent"]        second["Sub-agent"]        task --> first        task --> second        first --- second    end
    subgraph server["tokensave MCP Server"]        search["Search: auth"]        callers["Callers: login()"]        context["Context for task"]        db[("libSQL Graph DB<br/>Instant lookups<br/>FTS5 search")]        search --> db        callers --> db        context --> db    end
    first --> search    first --> callers    second --> context

Without tokensave: Agents use grep, glob, and Read to scan files -- many API calls, high token usage.

With tokensave: Agents query the graph via MCP tools -- instant results, local processing, fewer tokens.

Key Features


Smart Context Building	Semantic Search	Impact Analysis
One tool call returns everything the agent needs -- entry points, related symbols, and code snippets.	Find code by meaning, not just text. Search for "authentication" and find `login`, `validateToken`, `AuthService`.	Know exactly what breaks before you change it. Trace callers, callees, and the full impact radius of any symbol.
80+ MCP Tools	50+ Languages	12+ Agent Integrations
From call graph traversal to dead code detection, atomic edit primitives, code-health metrics, test mapping, and complexity analysis.	Rust, Go, Java, Python, TypeScript, C, C++, Swift, Svelte, Astro, and 48 more including WGSL/HLSL/Metal shaders, CUDA/HIP, and Markdown. Three tiers (lite/medium/full) control binary size.	Claude Code, Codex CLI, Gemini CLI, Qwen Code, Kiro, Cursor, OpenCode, Copilot, Cline, Roo Code, Zed, Antigravity, Kilo CLI, Kimi CLI, Mistral Vibe, Grok Build, Factory Droid, OMP, Pi, Plank.
Multi-Branch Indexing	100% Local	Always Fresh
Per-branch databases, tracked automatically as you check out branches. Cross-branch diff and search without switching your checkout.	No data leaves your machine. No API keys. No external services. Everything runs on a local libSQL database.	On-demand staleness check on every MCP call (30 s cooldown) plus catch-up sync when the server connects. Multi-agent work is expected to use git worktrees — each agent gets its own checkout and the index diverges are merged by git, not by a file watcher.
Subprocess-Isolated Extraction	Code-Health Analytics	Atomic Edit Primitives
A native crash in any tree-sitter grammar (abort, segfault, anything) kills only the worker; the pool respawns it and sync continues. Sync never dies on a malformed file.	Composite health score (0-10000), Gini inequality, file-DAG depth, design-structure matrix, risk-weighted test gaps, and session deltas.	Edit files without regex or shell-quoting hazards: unique-anchor `str_replace`, atomic multi-replace, AST-rewrite, anchored insert. Auto re-indexes after writes.

Quick Start

1. Install

Choose one installation method:

Platform	Command
Any platform (Cargo)	`cargo install tokensave` or, with cargo-binstall, `cargo binstall tokensave`
macOS (Homebrew)	`brew install aovestdipaperino/tap/tokensave`
Windows (Scoop)	`scoop bucket add tokensave https://github.com/aovestdipaperino/scoop-bucket` `scoop install tokensave`

You can also download a prebuilt binary and add it to your PATH.

To build unreleased code from the upstream master branch, see Installing from upstream master.

Installation alternatives and language tiers

The default Cargo build includes all supported languages. For a smaller build:

bash

cargo install tokensave --no-default-features --features mediumcargo install tokensave --no-default-features    # lite (smallest binary)

cargo install tokensave --no-default-features --features mediumcargo install tokensave --no-default-features    # lite (smallest binary)

Prebuilt release archives:

Platform	Archive
macOS (Apple Silicon)	`tokensave-vX.Y.Z-aarch64-macos.tar.gz`
Linux (x86_64)	`tokensave-vX.Y.Z-x86_64-linux.tar.gz`
Linux (ARM64)	`tokensave-vX.Y.Z-aarch64-linux.tar.gz`
Windows (x86_64)	`tokensave-vX.Y.Z-x86_64-windows.zip`

2. Configure your agent

Run the setup command to auto-detect your installed agents:

To choose an agent, use --agent (for example, codex, claude, or cursor):

Setup registers the MCP server and the agent's integration for Claude Code, Codex CLI, Gemini CLI, Cursor, Copilot, Kiro, Pi, Zed, and more than a dozen other agents. It also offers global Git hooks to keep initialized projects up to date. You can safely run setup again after upgrading. See Agent Integrations for project-local installs, several agents at once, and what setup writes for each agent.

3. Index your project

This creates a .tokensave/ directory with the knowledge graph database. A repository you create with git init is initialized automatically on its first commit or agent session (auto_init, on by default). After that, tokensave sync updates the index incrementally, and a connected agent keeps it fresh automatically. Commands work from any subdirectory of the project. See Indexing and Freshness for details.

Documentation

The full documentation lives in docs/guide/ and is mirrored to the GitHub Wiki.

Topic	What it covers
Installation and Upgrades	Language tiers, self-upgrade and channels, versioning, building from source
Agent Integrations	Supported agents, project-local setup, what install writes
Indexing and Freshness	Project discovery, index freshness, crash-resilient sync, custom extensions
MCP Tools	The 80+ tools by category, cross-project queries, MCP resources
Multi-Branch Indexing	Per-branch graphs, automatic tracking, branch quality regressions
Token Tracking and Cost	Savings ledger, cost reports, live monitor, memory diagnostics
Performance Profiling	Opt-in latency attribution for database operations, MCP tool phases and indexing
CLI Reference	Every command at a glance
Supported Languages	50+ languages and their feature tiers
Network Calls and Privacy	What leaves your machine and how to opt out
Troubleshooting	`tokensave doctor` and common problems
Benchmarks	Retrieval-savings and performance benchmarks
Comparisons	tokensave compared with CodeGraph and alternatives

The long-form User Guide walks through everyday use in more depth. To contribute, see CONTRIBUTING.md.

Origin

This project is a Rust port of the original CodeGraph TypeScript implementation by @colbymchenry. The port maintains the same architecture and MCP tool interface while leveraging Rust for performance and native tree-sitter bindings.

Building

To build from source, see Building from source and CONTRIBUTING.md.

Star History

[Star history]

License

MIT License -- see LICENSE for details.

tokensave.dev

Source: README.md at commit 068aa3c

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v4.0.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts