What is mcpfs CLAUDE.md?

A set of rules for working on the mcpfs codebase, an HTTP-based version of a file-system server used by Claude Code.

Use it when answering questions about mcpfs or deciding whether and when to modify its architecture, features, APIs, data structures, dependencies, or code.

It prevents changes from being made before the user approves them and keeps technical discussions separate from implementation. It clarifies the project context and approval requirements.

mcpfs CLAUDE.md — Instructions file for coding agents by jeswin: A set of rules for working on the mcpfs…

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/jeswin/mcpfs/claude-md

Clone the repo

git clone --depth 1 https://github.com/jeswin/mcpfs

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/jeswin/mcpfs/claude-md.svg)](https://agentmods.dev/instructions/jeswin/mcpfs/claude-md)

Your own site

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

Per session 960 This file is loaded in full into every session.

When invoked 960 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.

Model	Per session	Once invoked
Fable 5	$0.00960	$0.00960
Opus 5	$0.00480	$0.00480
Sonnet 5	$0.00192	$0.00192
Haiku 4.5	$0.00096	$0.00096

Measured 4d ago against content hash 5964cf17f2f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcpfs 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 4d 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 · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 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 when working with the mcpfs codebase.

Critical Guidelines

NEVER ACT WITHOUT EXPLICIT USER APPROVAL

YOU MUST ALWAYS ASK FOR PERMISSION BEFORE:

Making architectural decisions or changes
Implementing new features or functionality
Modifying APIs, interfaces, or data structures
Changing expected behavior or test expectations
Adding new dependencies or patterns

ONLY make changes AFTER the user explicitly approves. When you identify issues or potential improvements, explain them clearly and wait for the user's decision. Do NOT assume what the user wants or make "helpful" changes without permission.

FINISH DISCUSSIONS BEFORE WRITING CODE

IMPORTANT: When the user asks a question or you're in the middle of a discussion, DO NOT jump to writing code. Always:

Complete the discussion first - Understand the problem fully
Analyze and explain - Work through the issue verbally
Get confirmation - Ensure the user agrees with the approach
Only then write code - After the user explicitly asks you to implement

Project Overview

mcpfs is an HTTP streaming port of the official MCP Filesystem Server. It replaces stdio transport with HTTP Streaming (Streamable HTTP transport) for remote access and web client compatibility.

Key Features

Read/write files
Create/list/delete directories
Move files/directories
Search files
Get file metadata
Dynamic directory access control via MCP Roots
OAuth 2.1 authentication with PKCE support
ChatGPT integration via MCP connectors

Code Principles

NO CLASSES - Use functional style with strict types
PREFER type over interface
USE RESULT TYPES - For error handling where appropriate
ESM MODULES - All imports must include .js extension

Linting and Code Quality Standards

CRITICAL: NEVER weaken linting, testing, or type-checking rules:

NO eslint-disable comments - Fix the actual issues instead of suppressing warnings
NO @ts-expect-error or @ts-ignore - Fix type errors properly
NO relaxing TypeScript strict mode - Maintain full type safety
NO weakening any quality gates - Standards exist for a reason

Read the full file on GitHub · 132 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.

4d ago First seen · 132 lines · 960 tokens per session scan A 5964cf17f2f4

Subscribe to this mod's changes

mcpfs CLAUDE.md is an instructions file published in the GitHub repository jeswin/mcpfs (0 stars, last pushed 8mo ago), licensed MIT. It adds 960 tokens to every session, about $0.0048 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 2026-08-31.

Building agents

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcpfs CLAUDE.md