What is lara-mcp CLAUDE.md?

Project instructions for a Lara Translate MCP server, a program that lets other tools use Lara's translation service through a standard connection format. They document setup, development, testing, Docker, and the server's two connection modes.

Use them when installing dependencies, building, running, testing, or changing the translation server.

They give coding agents the repository-specific commands and architecture details needed to work on the project correctly.

How translated/lara-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to translated/lara-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/translated/lara-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/translated/lara-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/translated/lara-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/translated/lara-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/translated/lara-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/translated/lara-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/translated/lara-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/translated/lara-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,218 This file is loaded in full into every session.

When invoked 4,218 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.04218	$0.04218
Opus 5.5	$0.01687	$0.01687
Sonnet 5.5	$0.00844	$0.00844
Haiku 4.5	$0.00422	$0.00422

Measured 3d ago against content hash bdd473215803, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lara-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

Lara Translate MCP Server is a Model Context Protocol (MCP) server that provides translation capabilities through the Lara Translate API. The server supports both STDIO and HTTP transport modes.

It is built on the MCP TypeScript SDK v2 (@modelcontextprotocol/server, @modelcontextprotocol/node) and serves both protocol eras on every transport:

2026-07-28 (stateless: no initialize, per-request _meta envelope, server/discover, Mcp-Method/Mcp-Name headers, cacheable list results)
2025-era (2024-11-05 … 2025-11-25, initialize handshake) for clients that have not upgraded

Development Commands

Setup

# Install dependencies
pnpm install

# Build the project
pnpm run build

Development

# Run in development mode with hot reload
pnpm run dev

# Start the built server
pnpm run start

Testing

# Run all tests once
pnpm test

# Run tests in watch mode
pnpm test:watch

# Run tests with coverage report
pnpm test:coverage

Docker Development

# Build Docker image
docker build -t lara-mcp .

Architecture

Server Modes

The server operates in two transport modes determined by the TRANSPORT environment variable:

STDIO Mode (src/index.ts): serveStdio(factory) negotiates the era on the opening exchange and pins one server instance per connection. Requires LARA_ACCESS_KEY_ID and LARA_ACCESS_KEY_SECRET environment variables.
HTTP Mode (src/rest/routes/mcp.ts): Express server with the MCP endpoint at MCP_MOUNT_PATH (/v1). The route validates the x-lara-access-key-id / x-lara-access-key-secret headers (missing → 400 before the handler runs) and passes them to the SDK as req.auth; the module-level createMcpHandler(factory), wrapped with toNodeHandler, builds a fresh MCP server per request from that pass-through authInfo. GET/DELETE answer 405. The handler is built on the first mounted router (not at module load, so stdio mode does not pay for it) and torn down by closeMcpHandler().

Read the full file on GitHub · 279 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago Changed · +5 lines · +92 tokens per session bdd473215803
13d ago Changed · +7 lines · +195 tokens per session 0acc78b81cf4
21d ago Changed · +73 lines · +1,348 tokens per session 040416e41edf
1mo ago Changed · +20 lines · +891 tokens per session 6651962aeafe
2mo ago First seen · 174 lines · 1,692 tokens per session scan A c3760ed266ab

Subscribe to this mod's changes

lara-mcp CLAUDE.md is an instructions file published in the GitHub repository translated/lara-mcp (100 stars, last pushed yesterday), licensed MIT. It adds 4,218 tokens to every session, about $0.0169 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Localization lara-translate mcp mcp-server model-context-protocol translation

lara-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
lara-mcp CLAUDE.mdtranslated/lara-mcp	Instructions file	100	yesterday	MIT	A	4,218	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

lara-mcp: Instructions file for Claude Code