mcp-file-context-server CLAUDE.md

mcp-file-context-server CLAUDE.md is an instructions file for coding agents from bsmi021/mcp-file-context-server. It costs 835 tokens per session, scanned A, original, MIT.

These project instructions describe an MCP server that lets an AI read, search, and analyse files on a computer.

In plain words
What is it for?
They help maintain file reading, code analysis, large-file chunking and compression, file watching, and automatic cache updates across Windows, macOS, and Linux.
Why use it?
They explain how to build, run, test, and configure the server, including limits for file size and cached data.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/bsmi021/mcp-file-context-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/bsmi021/mcp-file-context-server

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.

agentmods badge for mcp-file-context-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bsmi021/mcp-file-context-server/claude-md.svg)](https://agentmods.dev/instructions/bsmi021/mcp-file-context-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bsmi021/mcp-file-context-server/claude-md"><img src="https://agentmods.dev/badge/instructions/bsmi021/mcp-file-context-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 835 This file is loaded in full into every session.
When invoked 835 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00835 $0.00835
Opus 5 $0.00417 $0.00417
Sonnet 5 $0.00167 $0.00167
Haiku 4.5 $0.00084 $0.00084

Measured 5d ago against content hash 59ab43bd132f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-file-context-server 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 5d 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 · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 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.

Development Commands

Build and Run

  • npm run build - Compile TypeScript to JavaScript in /dist
  • npm run dev - Build and run the server in development mode
  • npm start - Start the compiled server from /dist
  • npm test - Run Jest tests

Environment Configuration

  • MAX_CACHE_SIZE - Maximum cached entries (default: 1000)
  • CACHE_TTL - Cache time-to-live in milliseconds (default: 1 hour)
  • MAX_FILE_SIZE - Maximum file size in bytes for reading

Architecture Overview

This is a Model Context Protocol (MCP) server that provides file system context and analysis to LLMs. The server is built using the MCP SDK and provides tools for reading, searching, and analyzing code files.

Core Components

Main Server Class (src/index.ts):

  • FileContextServer - Main server implementation handling MCP protocol
  • Implements streaming, compression, and chunking for large files
  • Provides file watching with automatic cache invalidation
  • Handles cross-platform path compatibility (Windows/macOS/Linux)

Services (src/services/):

  • CodeAnalysisService - Analyzes code complexity, dependencies, and quality metrics
  • FileWatcherService - Real-time file system monitoring with chokidar
  • ProfileService - Context generation profiles for different use cases
  • TemplateService - Template rendering for prompts and context

Type Definitions (src/types.ts):

  • Complete type definitions for file operations, caching, and analysis
  • Error handling with custom FileOperationError class
  • Profile and context specification interfaces

Key Features

File Operations:

  • Cross-platform path handling using POSIX-style paths for globs
  • Streaming support for large files with configurable chunk sizes
  • Automatic encoding detection (UTF-8, UTF-16LE with BOM support)
  • LRU caching with TTL for performance optimization

Code Analysis:

  • Cyclomatic complexity calculation
  • Dependency extraction and analysis
  • Code quality metrics (duplicate lines, long lines, complex functions)
  • Language-specific analysis for TypeScript, JavaScript, Python

Read the full file on GitHub · 103 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.

  1. 5d ago First seen · 103 lines · 835 tokens per session scan A 59ab43bd132f

Subscribe to this mod's changes

mcp-file-context-server CLAUDE.md is an instructions file published in the GitHub repository bsmi021/mcp-file-context-server (39 stars, last pushed 1y ago), licensed MIT. It adds 835 tokens to every session, about $0.0042 per session on Opus 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.

Related

Other instructions, from other repositories

opencontext AGENTS.md

AGENTS.md instructions for slxca/opencontext, covering critical memory system: opencontext protocol, 1. mandatory pre-flight: inspect context, 2. post-implementation: persist changes, 3. execution rules and repository.

slxca/opencontext · 1,146 tokens

opencontext CLAUDE.md

Claude Code instructions for slxca/opencontext, covering critical memory system: opencontext protocol, 1. mandatory pre-flight: inspect context, 2. post-implementation: persist changes and 3. execution rules.

slxca/opencontext · 392 tokens

obsidian-cli-rest CLAUDE.md

Instructions for dsebastien/obsidian-cli-rest, a project described as: Control your Obsidian vault programmatically. This plugin turns all Obsidian CLI commands into a local HTTP API and MCP server, letting you automate your workflow from scripts, tools, and AI assistants.

dsebastien/obsidian-cli-rest · 7 tokens

ida-pro-mcp CLAUDE.md

Instructions for mrexodia/ida-pro-mcp, covering claude.md, what this project is, core implementation rules, ida thread safety and api conventions.

mrexodia/ida-pro-mcp · 1,135 tokens

tableau-mcp CLAUDE.md

Claude Code instructions for tableau/tableau-mcp, covering claude.md, build & development commands, building, running the server and testing.

tableau/tableau-mcp · 2,610 tokens

flyto-core AGENTS.md

AGENTS.md instructions for flytohub/flyto-core, covering flyto-core agent rules, flyto2 project memory contract, flyto2 frontend quality gate and repo notes.

flytohub/flyto-core · 1,121 tokens