What is large-file-mcp CLAUDE.md?

Repository instructions for large-file-mcp, an MCP server that gives AI tools ways to read, search, inspect, and navigate files too large to fit in one response. They also describe its TypeScript setup and release commands.

Building, testing, linting, and developing the package, plus reading file chunks, searching with surrounding lines, checking file statistics, and jumping to a line.

They explain how to work on the server and how to access large files without loading the entire file at once.

How willianpinho/large-file-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to willianpinho/large-file-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/willianpinho/large-file-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/willianpinho/large-file-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/willianpinho/large-file-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/willianpinho/large-file-mcp/claude-md)

Your own site

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

Per session 606 This file is loaded in full into every session.

When invoked 606 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	$0.00606	$0.00606
Opus 5.5	$0.00242	$0.00242
Sonnet 5.5	$0.00121	$0.00121
Haiku 4.5	$0.00061	$0.00061

Measured 2mo ago against content hash 937ef2b8ac47, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

large-file-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 2mo 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Large File MCP - MCP Server for Large File Handling

Published npm package (@willianpinho/large-file-mcp) providing MCP tools for reading, searching, and navigating large files that exceed LLM context limits.

Tech Stack

Language: TypeScript 5.9+, Node.js 18+
Framework: MCP SDK 1.28+
Testing: Jest 30 (with ts-jest)
Build: tsc (TypeScript compiler)
Linting: ESLint 9 (flat config)
Package Manager: pnpm
Package: npm (@willianpinho/large-file-mcp)
CI/CD: GitHub Actions with OIDC trusted publisher

Commands

pnpm install
pnpm run build              # Compile TypeScript
pnpm run dev                # Watch mode
pnpm test                   # Jest tests
pnpm run test:coverage      # Coverage report
pnpm run lint               # ESLint 9

# Publish (automated via GitHub Actions OIDC)
npm version patch|minor|major
npm publish --access public

MCP Tools Provided

Tool	Purpose
`read_large_file_chunk`	Read file chunks with intelligent splitting
`search_in_large_file`	Regex search with context lines
`get_file_structure`	File metadata and line statistics
`navigate_to_line`	Jump to specific line with context
`get_file_summary`	Statistical summary (lines, chars, words)
`stream_large_file`	Stream file in byte-based chunks

Architecture

src/
├── index.ts               # MCP server entry point (stdio transport)
├── server.ts              # Tool registration + request handlers
├── fileHandler.ts         # Thin barrel — FileHandler delegates to src/file-handler/*
├── file-handler/
│   ├── metadata.ts        # File type detection, metadata, existence/readability checks
│   ├── reader.ts          # Chunked reading, line-range reading, line navigation
│   ├── search.ts          # Regex/plain-text pattern search with context lines
│   ├── analysis.ts        # File structure and content statistics
│   └── stream.ts          # Byte-based streaming of large files
├── cacheManager.ts        # LRU + TTL cache
└── types.ts               # TypeScript types

__tests__/                 # Jest test suites
dist/                      # Compiled output (npm entry)
Dockerfile                 # Container build

Read the full file on GitHub · 73 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.

2mo ago First seen · 73 lines · 606 tokens per session scan A 937ef2b8ac47

Subscribe to this mod's changes

large-file-mcp CLAUDE.md is an instructions file published in the GitHub repository willianpinho/large-file-mcp (18 stars, last pushed 8d ago), licensed MIT. It adds 606 tokens to every session, about $0.0024 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.

Documents LLM TypeScript ai claude developer-tools mcp

large-file-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
large-file-mcp CLAUDE.mdwillianpinho/large-file-mcp	Instructions file	18	8d ago	MIT	A	606	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

large-file-mcp: Instructions file for Claude Code