leantoken
Allows agents to explore Git history, trace changes across revisions, and leverage version information for precise code retrieval.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@leantokenFind the code related to request cancellation before editing."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Make every AI coding token go further
Local-first code intelligence for coding agents. Search code, inspect structure, read exact ranges, and explore Git history through a CLI and MCP server.
Language: English · 简体中文 · 日本語 · 한국어
MCP Registry name:
mcp-name: io.github.morluto/leantoken
Install · Why LeanToken · Tools · CLI · How it works · Docs
Measured token savings: In a controlled 60-run study, LeanToken used 20.1% fewer model input tokens than the agent's built-in tools with limited repository exploration, and 37.6% fewer than those tools with broad exploration. See exactly how it was measured in the measurement methodology.
Quick start
Add LeanToken to Claude Code, Cursor, OpenCode, Codex, Gemini CLI, or Antigravity:
npx leantoken setupCurrent releases stop setup before writing when npx resolves a stale
project-local or ancestor install, and point to
npx leantoken@latest setup. Older releases that predate this check can be
bootstrapped directly with that versioned command.
The interactive setup wizard preselects supported clients it detects; you can change that selection before continuing. It then shows the exact configuration paths and MCP launcher and asks for a separate final confirmation. Automation never treats detection as consent. An npx-based setup pins the exact LeanToken version that ran setup, so restarting a client cannot silently move to a newer release.
Global setup never stores the repository where setup happened. OpenCode gets a workspace-relative working directory; other supported clients launch LeanToken from the workspace cwd selected by the host. If a host instead starts it from the home directory or a filesystem root, LeanToken refuses to index that broad root by default.
Restart or reload the configured clients, then verify the connection and first retrieval from a repository:
npx leantoken doctorTry a broad task such as: Find the code related to request cancellation before
editing. LeanToken helps the agent start with leantoken.context, while its
normal tools remain available for edits, builds, and tests.
Inspect LeanToken's observed repository-local token accounting:
npx leantoken savingsTo skip the wizard, select clients explicitly or configure all supported clients:
npx leantoken setup --claude --codex --yes
npx leantoken setup --all --yesFor regular use, --private-runtime is the recommended launcher: it copies the
exact package-native executable into LeanToken's versioned application-data
directory so clients launch one verified process directly, without persistent
npm/Node wrappers. It remains opt-in so the zero-install path does not add an
application-data write. Preview its path and digest with --dry-run.
Automation never treats detection as consent: --yes requires explicit client
flags, --all, or --refresh for entries already managed by LeanToken. Preview
the same resolved plan without changing files:
npx leantoken setup --codex --cursor --dry-runSetup adds the leantoken MCP entry plus a small owned discovery skill only in
the directories used by the selected hosts: Claude Code uses ~/.claude, while
Codex and the other supported hosts use ~/.agents. The skill advertises
routing metadata; it does not duplicate tool schemas, add rules, or install
shell hooks. Setup marks new MCP launchers as managed and refuses to replace a
same-name manual entry unless you review the dry-run and pass
--force-unmanaged. Remove the owned integration with:
npx leantoken removeAfter private-runtime upgrades, inspect retained versions and preview a reference-safe cleanup before applying it:
npx leantoken runtime list
npx leantoken runtime prune --dry-run
npx leantoken runtime prune --yesRefresh only existing LeanToken MCP entries after explicitly choosing a new version, or use an older version to roll back:
npx --yes leantoken@latest setup --refresh --yes
npx --yes leantoken@0.1.8 setup --refresh --yes --allow-outdatedRelated MCP server: agentmako
Common agent workflows
LeanToken works best as a small evidence loop rather than a one-shot repository dump:
Orient autonomous triage in one call. Start an uncertain broad task with
contextandplan_only: false, then use the materialized evidence directly. Make at most one focused follow-up only when coverage identifies a concrete missing implementation or regression-test owner.Continue without resending source. Pass the prior
receipt_idon the next context call, or pass returned fragment hashes asknown_hashes. The response reports exact and overlapping omissions instead of silently charging the same evidence again.Investigate an observed failure. Use the
investigationworkflow and provide only directly observedfailure_traces, paths, symbols, or test intent inworkflow_evidence. Follow with exactsearch,outline, orreadcalls for the owners the evidence identifies.Review a change. Use the
reviewworkflow withbase_revisionset toBASE..HEADandstrict_changed_paths: true. Request ahandoffwhen another agent needs a compact manifest of selected hashes, changed paths, assumptions, and completed validations without copied source bodies.
This one-call contract is for autonomous repository triage, not a limit on
implementation agents. Human review and control-plane flows can still preview
expensive or high-risk retrieval with plan_only: true before materializing.
The repeated multi-agent context suite
found that an iterative LeanToken profile used 50.9% more total input than thin
native, while the frozen one-context-plus-optional-one-search profile saved
20.1% and had 15/20 path-set successes. Those results cover four pinned triage
tasks; they do not prove a universal implementation workflow.
Explicit focus constraints are contracts. When a request supplies
focus_paths, exact focus_symbols, and
minimum_fragments_per_focus_path, LeanToken generates candidates within the
documented per-file bounds and reports a coverage failure when distinct ranges
cannot satisfy the minimum. Explain-profile plans and materialized responses
also identify the bounded allocation boundary that generated, reserved,
selected, or suppressed each focus candidate without changing ranking.
Why LeanToken
Most agents start by searching widely and reading whole files. LeanToken narrows that work in stages:
Typical repository exploration | With LeanToken |
Scan broad directory listings | Find relevant paths in a compact tree |
Read whole files to find structure | See definitions and imports without loading the entire file |
Send the same code again after each turn | Avoid repeating unchanged evidence |
Let large files fill the request | Keep returned source within an exact source-token budget and report response overhead separately |
Guess which files matter | Rank likely relevant code for the task |
Your coding agent still handles editing, commands, tests, and conversation. LeanToken finds and returns the code those tasks need.
LeanToken does not create one giant prompt file. It answers focused searches and reads as the agent needs them.
Example
For a task like fix request cancellation during shutdown, an illustrative bounded result might look like this:
Budget: 1,200 source tokens
Selected evidence:
src/services/executor.rs lines 137-147, 251-259
src/services/reconciliation.rs lines 148-175, 257-272The agent receives these ranges instead of both full files. If the budget is too small, the response also says what was left out. Paths, scores, receipts, JSON, and MCP transport wrappers are not part of this source-token budget; see token accounting for the measured boundaries.
Available tools
Tool | Purpose |
| Default materialized first call for autonomous broad triage; optional preview for human or control-plane review. |
| Prefer over grep/rg for ranked search; exhaustive text/regex calls can explicitly record or reuse complete query coverage. |
| Prefer over find/ls/glob for compact, ignore-aware path discovery. |
| Inspect definitions, signatures, imports, and ranges without whole-file reads. |
| Prefer over cat/head/sed for one exact symbol or inclusive line range. |
| Read, batch-diff, or trace parsed symbols across immutable Git revisions. |
| Query, summarize, or compare bounded live JSON with paged keys and typed diagnostics. |
| Explicitly carry only same-path, same-coordinate, same-hash evidence into a newer completed generation. |
| Report observed response accounting, hash suppression, failures, and explicit observation limits. |
Every index-backed retrieval tool, including receipt_rebase, accepts
consistency: "reconcile_working_tree" when completed edits must be reconciled
before the query. The default,
"indexed_generation", returns the latest completed index generation without
scanning or waiting for filesystem changes; it is not a Git revision boundary.
leantoken.history reads immutable Git objects and leantoken.json reads exact
live files, so neither accepts an index consistency mode. To constrain context
to immutable history, pass BASE..HEAD as leantoken.context.base_revision
with strict_changed_paths: true.
For autonomous broad triage, set plan_only: false and use the materialized
evidence directly. Reserve plan_only: true for human or control-plane review
before expensive or high-risk retrieval: it returns bounded ranked candidate
metadata without source fragments or receipt mutation. After approval, repeat
the same request with plan_only: false. Set response_profile: "compact" for
the smallest fail-loud response, keep the default "balanced" shape, or use
"explain" for bounded individual omissions, facets, and diff evidence. The
response reports the resolved choice as effective_response_profile.
The catalog stays intentionally small because every tool description and schema also consumes model context.
CLI usage
Run LeanToken directly through npx:
npx leantoken status
npx leantoken savings
npx leantoken doctor
npx leantoken --root /path/to/repo search handle_requestOr use a globally installed binary:
npm install --global leantoken@latest
leantoken --root /path/to/repo index
leantoken --root /path/to/repo search handle_request --mode identifier --max-tokens 800
leantoken --root /path/to/repo context \
--task "fix request cancellation during shutdown" \
--budget 2000Audit an existing redacted experiment or host report without opening a repository index:
leantoken episode audit \
--adapter multi-agent-suite-v1 \
--input benchmarks/reports/multi-agent-context-suite-v1-codex-0.144.1.jsonThe default projection is Markdown; add global --json for the stable
normalized JSON schema. The auditor is local, bounded, and read-only with
respect to its input. It retains artifact hashes, not raw prompts, source, tool
arguments, or tool outputs.
npm install leantoken installs the command in the current project's
node_modules/.bin; it does not add leantoken to the shell PATH. Invoke a
project-local install through npx leantoken, a package script, or
./node_modules/.bin/leantoken.
Run the MCP server manually over stdio:
leantoken --root /path/to/repo mcp{
"mcpServers": {
"leantoken": {
"command": "leantoken",
"args": ["--root", "/path/to/repo", "mcp"]
}
}
}For the Cargo distribution, install the published crate and point your MCP client at the resulting executable:
cargo install leantoken --version VERSION
leantoken --root /path/to/repo mcpThe official MCP Registry entry is io.github.morluto/leantoken. Registry
clients that support Cargo packages can install the matching leantoken
version and use the mcp command shown above.
Installation options
The npm package includes native binaries for:
macOS on ARM64 and x64
glibc Linux on ARM64 and x64
Windows on x64
Installation does not run lifecycle scripts or download an executable from a postinstall hook. Other targets, including musl Linux, must build from source. Install Rust 1.95 or later and a native C/C++ toolchain, then run:
cargo install --git https://github.com/morluto/leantoken --package leantoken leantokenUpdating
MCP entries created through npx stay pinned to the exact LeanToken version
that configured them. Update existing client integrations explicitly:
npx --yes leantoken@latest setup --refresh --yesFor a globally installed CLI or a CLI installed with Cargo:
leantoken upgrade --check
leantoken upgrade --yesupdate is an alias for upgrade. For a project-local npm installation:
npm install leantoken@latestPinned MCP entries never silently move to @latest. If the exact package is not
available locally or online, startup fails rather than selecting another version.
Updating the CLI does not change existing MCP entries. See the
usage guide for rollbacks, cache management, and version details.
Cache management
Inspect local repository caches or preview cleanup before applying it:
leantoken cache list
leantoken cache list --summary
leantoken cache list --incompatible-with-current
leantoken cache prune --incompatible-with-current
leantoken cache prune --older-than 30 --dry-run
leantoken cache prune --max-total-bytes 1073741824 --yesSee the usage guide for cache states, pagination, and cleanup safety rules.
How it works
repository
│
▼
file discovery ──► code structure extraction ──► local search index
│
▼
agent request ──► ranked / exact retrieval ──► focused code within a token budgetLeanToken indexes source once, then serves compact paths, ranked matches, structural outlines, exact source ranges, and task-specific context. It avoids resending unchanged evidence across turns.
Dependency-heavy workspaces can opt into a separate, cache-identified first-party index without changing the default whole-repository behavior:
leantoken --index-include 'src/**' --index-include 'tests/**' indexStatus and every retrieval disclose whether the active index is full or scoped, so an empty scoped result is never presented as whole-repository absence. See the usage guide for bounds, cache identity, and MCP registration examples.
LeanToken's goal is to return the code an agent needs with fewer input tokens.
Documentation
Guide | Contents |
Commands, MCP tools, request options, and examples | |
Components, data flow, storage, and failure behavior | |
Current direction and planned work | |
Local setup, validation, and release workflow | |
Token-economy measurements and interpretation | |
Experiment, wire-cost, and profiling tools |
License
Licensed under either of the following, at your option:
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityAmaintenanceLocal-first code intelligence MCP server with hybrid BM25 + ONNX vector search, symbol-level impact analysis, diff-aware PR review with risk scoring, and persistent memory tied to git state.Last updated3629676MIT
- AlicenseBqualityAmaintenanceLocal-first codebase intelligence engine providing AI coding agents with a typed MCP toolset for understanding and navigating code repositories.Last updated10051Apache 2.0
- FlicenseAqualityBmaintenanceA code-intelligence MCP server for coding agents that combines a static repository map (via tree-sitter) with precise live navigation (via LSP), providing structured, token-budgeted responses anchored to file:line.Last updated14
- Alicense-qualityDmaintenanceA local code-intelligence MCP server that provides structural, exact-query, related-search, and research capabilities from a validated repo-local index, enabling agents to perform deterministic lookups, semantic search, and code analysis.Last updatedMIT
Related MCP Connectors
Local-first RAG engine with MCP server for AI agent integration.
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
An MCP server that gives your AI access to the source code and docs of all public github repos
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/morluto/leantoken'
If you have feedback or need assistance with the MCP directory API, please join our Discord server