TokenLighten
Local-first MCP toolkit that provides coding agents focused repository context via read_file, search_files, and edit_file tools, reducing token usage and task cost.
README
<picture> <source media="(prefers-color-scheme: dark)" srcset="media/brand/github-header-dark.png"> <source media="(prefers-color-scheme: light)" srcset="media/brand/github-header-light.png"> <img alt="TokenLighten MCP — hummingbird logo" src="media/brand/github-header-light.png"> </picture>
TokenLighten
<p align="center"><strong>Give coding agents the context they need—not the whole repository.</strong></p>
TokenLighten is a local-first MCP toolkit that gives coding agents focused repository context instead of repeatedly sending whole files.
It exposes exactly three tools: read_file, search_files, and edit_file.
v0.9.1a Public Beta
TokenLighten v0.9.1a is an early public release. Interfaces and supported workflows may change as we incorporate feedback. Keep backups of important work, and do not include private source code, credentials, or customer data in public issue reports.
This release includes:
- the TokenLighten CLI and MCP server;
- source code and package tests for developers; and
- a self-contained VS Code extension distributed as a VSIX.
The desktop application is not included in v0.9.1a.
See it in action

The Control Center keeps setup, workspace status, local measurement, and the on/off switch in one place.
Why TokenLighten
Coding agents often spend multiple turns locating files, reading broad sections, and reopening context before making a small change. TokenLighten performs local repository discovery and returns compact structure, symbols, exact ranges, and bounded edit handles.
Repository indexing and context selection run locally on the CPU. TokenLighten does not add an AI model or upload repository contents on its own. Your editor, MCP client, and AI provider continue to operate under their own configuration and terms.
Savings vary by repository, task, client, and model behavior. Usage and cost figures shown by TokenLighten are local estimates, not provider billing records.
Where TokenLighten can reduce token and task cost
TokenLighten is designed to deliver its largest advantage when an agent must identify and correctly update every affected location across multiple files, packages, or document formats. The benefit is expected to be smaller when a task is limited to one known location.
Symbol and reference search can return relevant definitions and call sites directly. Document readers can extract structured content from spreadsheets and other supported formats without loading each entire file. Together, these capabilities can reduce repeated search and rereading while the agent gathers the context required for repository-wide or cross-document work.
Early developer benchmark observations
In one multi-package code task, the agent added a value to a shared enum and propagated it consistently through a frontend component, backend validation, and category-based aggregation logic. Across six repeated benchmark runs, using TokenLighten reduced verified task cost by approximately 56% compared with the same agent without TokenLighten.
In a cross-document implementation task, the agent combined a rate table maintained in a spreadsheet with calculation procedures described in a separate document, then implemented a new pricing module consistent with both sources. Across six repeated benchmark runs, TokenLighten reduced verified task cost by approximately 48%.
The early results also show where TokenLighten may not help:
- No clear advantage was observed when the main task was to analyze one large spreadsheet in isolation, without combining it with other sources to produce new code.
- Results varied for small, localized changes that only passed an already-known value through an existing code path and did not require broad repository discovery. In these cases, TokenLighten's context-collection overhead can exceed the cost it saves.
These are early, developer-run benchmark results, not guaranteed savings. Actual token use and task cost vary by repository, task, client, model behavior, and provider pricing.
Install the VS Code extension (no build required)
For most users, download tokenlighten-vscode-extension-0.9.2.vsix from the v0.9.1a Public Beta GitHub Release. You do not need Node.js or a source build. The same VSIX is used on Windows, macOS, and Linux because this release does not include OS-specific native binaries.
Then:
- open the VS Code Extensions view;
- choose Install from VSIX…; and
- select the downloaded file.
Or install it from a terminal:
code --install-extension tokenlighten-vscode-extension-0.9.2.vsix
Open a trusted project folder, select the TokenLighten view, and choose Set up this workspace. The packaged VSIX includes the CLI, MCP server, parsers, and required assets; a separate global installation is not required.
See VS Code extension for details.
Client compatibility
| Client | Automatic setup | Manual configuration | v0.9.1 validation |
|---|---|---|---|
| Codex CLI / Codex for VS Code | Yes | Yes | CLI 0.148.0-alpha.9 and VS Code extension 26.810.52044 on macOS |
| Claude Code / Claude Code for VS Code | Yes | Yes | CLI 2.1.211 and VS Code extension 2.1.233 on macOS |
| VS Code / GitHub Copilot | Yes | Yes | VS Code 1.133.0 extension/setup smoke test on macOS; Copilot version not recorded |
| Cursor | Partial: managed instructions only | Yes, through Cursor's MCP settings | Not part of the v0.9.1 release verification |
The versions above record the local clients used for the 2026-08-16 v0.9.1 smoke checks; they are not minimum-version guarantees. Automated tests also verify the generated Codex, Claude Code, VS Code, Copilot, and Cursor configuration/instruction files. Cursor MCP registration itself remains manual.
Build from source
Requirements:
- Node.js 20 or later;
- npm; and
- Git when using write-enabled repository operations.
git clone https://github.com/Takayuki-Ishimaru/tokenlighten.git
cd tokenlighten
npm ci
npm run build
npm link --workspace packages/cli
tl version
tl doctor --json
Set up TokenLighten in another workspace:
cd /path/to/project
tl workspace setup
The MCP server is read-only by default. Enable writes only when you intend to allow workspace changes:
tl mcp start --stdio --workspace /path/to/project
tl mcp start --stdio --allow-write --workspace /path/to/project
Run tl help for the current command reference.
MCP tools
| Tool | Purpose |
|---|---|
read_file |
Returns focused file content, structure, symbols, or a task-oriented context pack. |
search_files |
Finds files, text, symbols, and references in the selected workspace. |
edit_file |
Applies bounded edits using context established by a prior read. Requires --allow-write. |
See MCP tools for behavior and safety notes.
Packages
| Package | Purpose |
|---|---|
@tokenlighten/mcp-server |
Stdio MCP server and the three advertised tools. |
@tokenlighten/cli |
The tl command and workspace/client setup. |
@tokenlighten/skeleton-engine |
Repository maps, symbols, ranges, and route extraction. |
@tokenlighten/agents-md |
Managed agent-instruction blocks with drift detection. |
@tokenlighten/usage |
Local usage and savings estimates. |
@tokenlighten/types |
Shared public TypeScript contracts. |
tokenlighten-vscode-extension |
Self-contained VS Code integration. |
Language and file support
Primary programming-language support currently covers TypeScript, JavaScript, Python, Go, Java, Rust, C, C++, Kotlin, C#, PHP, and Ruby.
TokenLighten can also read supported text, Office, PDF, and archive formats. Some formats are read-only, and PDF support requires a text layer. See Language and file support for the current boundaries.
Development
Run the public developer checks from the repository root:
npm ci
npm run build
npm run test:packages
npm run test:bundle-cli
npm run licenses
npm run doctor
Build the VSIX:
npm run package -w tokenlighten-vscode-extension
See CONTRIBUTING.md before submitting a change.
For v0.9.1, the complete package test suite is a CI gate on Ubuntu and macOS. Windows CI verifies the source build, bundled CLI, dependency licenses and notices, runtime dependency audit, and diagnostics. The complete package suite is not yet a Windows release gate because some test fixtures are not portable to Windows; this does not make Windows or VSIX installation unsupported, and Windows-specific test coverage will be expanded.
Documentation
- Getting started
- MCP tools
- VS Code extension
- Language and file support
- Privacy, security, and support
- Licensing and use policy
Security and support
Dependency audit snapshot
For TokenLighten v0.9.1 dependencies audited on 2026-08-16, npm audit --omit=dev reported 0 Critical, 0 High, and 2 Moderate findings in the dependency set used by the shipped VS Code extension and normal runtime operation.
A full source-development installation, including development dependencies, reported the same 0 Critical, 0 High, and 2 Moderate findings after the v0.9.1 development-toolchain updates.
The two scanner findings represent one transitive uuid advisory through exceljs. The affected uuid APIs are not used by the TokenLighten spreadsheet path. See Dependency security status for the advisory ID, reachability analysis, remediation constraints, and update plan. This is a dated snapshot, not a guarantee that the software has no vulnerabilities.
The server is read-only unless started with --allow-write. Review SECURITY.md before reporting a vulnerability and SUPPORT.md for the best-effort support policy. Do not post credentials, private source code, customer data, or unsanitized logs in public issues.
License
TokenLighten is source-available software, not software under an OSI-approved open-source license. Personal use, individual use for employer or client work, organizational internal use, and properly attributed personal non-organizational redistribution are permitted under the release terms. Product/service integration and organizational or commercial redistribution require prior written permission from Takayuki Ishimaru (GitHub: @Takayuki-Ishimaru).
The LICENSE file distributed with a release is authoritative. See Licensing and use policy for a plain-language summary.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.