What is mcp-virtual-fs CLAUDE.md?

Project instructions for mcp-virtual-fs, a PostgreSQL-backed virtual filesystem exposed through MCP, a standard way for AI agents to call tools. It describes the TypeScript stack, layered architecture, and key design choices.

Use it when working on virtual file operations, PostgreSQL storage, path matching, database-backed search, Vitest tests, Docker-based PostgreSQL tests, or strict TypeScript and ESLint configuration.

It gives contributors the project context needed to change the filesystem safely without bypassing its storage interface or testing conventions.

How lu-zhengda/mcp-virtual-fs configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lu-zhengda/mcp-virtual-fs. 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/lu-zhengda/mcp-virtual-fs/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lu-zhengda/mcp-virtual-fs

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/lu-zhengda/mcp-virtual-fs/claude-md/github.svg)](https://agentmods.dev/instructions/lu-zhengda/mcp-virtual-fs/claude-md)

Your own site

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

Per session 1,167 This file is loaded in full into every session.

When invoked 1,167 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	$0.01167	$0.01167
Opus 5.5	$0.00467	$0.00467
Sonnet 5.5	$0.00233	$0.00233
Haiku 4.5	$0.00117	$0.00117

Measured 2mo ago against content hash 6e934c5d6aae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-virtual-fs 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides context for AI assistants working on this codebase.

Project Overview

mcp-virtual-fs is a PostgreSQL-backed virtual filesystem exposed via MCP (Model Context Protocol) tools. It gives AI agents persistent, session-isolated file operations.

Tech Stack

Language: TypeScript (ESM, strict mode)
Runtime: Node.js 20+
MCP SDK: @modelcontextprotocol/sdk v1.x, stdio transport
Database: PostgreSQL with pg_trgm extension
Testing: Vitest + testcontainers (real PostgreSQL in Docker)
Linting: ESLint 9 flat config + typescript-eslint strict

Architecture

tools.ts (MCP protocol) → vfs.ts (filesystem semantics) → storage/interface.ts → storage/postgres.ts

Each layer depends only on the one below. VirtualFS never imports postgres.ts directly — it uses the StorageBackend interface.

Key Design Decisions

Materialized paths (not ltree) — filenames like package.json contain dots that ltree can't handle
Glob in-app (picomatch) — **/*.ts can't be expressed as SQL LIKE; allFilePaths() fetches paths, picomatch filters
Grep in-database — PostgreSQL trigram index (pg_trgm) makes regex search fast at the DB level
Session via MCP context — extra.sessionId from transport, NOT a tool parameter. Falls back to VFS_SESSION_ID env var or auto-generated UUID
RLS uses set_config() — PostgreSQL SET variable = $1 doesn't support parameterized queries; SELECT set_config('name', $1, false) does

Commands

npm run build          # Compile TypeScript
npm test               # Run all tests (needs Docker)
npm run test:unit      # Unit tests only (no Docker)
npm run test:integration  # Integration tests (needs Docker)
npm run lint           # ESLint
npm run lint:fix       # Auto-fix

File Map

File	Purpose
`src/index.ts`	Entry point — env config, backend init, MCP server, stdio transport
`src/tools.ts`	11 MCP tool registrations with Zod schemas and annotations
`src/vfs.ts`	`VirtualFS` class — filesystem semantics (read/write/append/stat/ls/mkdir/rm/mv/glob/grep/listStores)
`src/paths.ts`	Pure path utilities — normalize, parent, basename, ancestors, validate
`src/storage/interface.ts`	`StorageBackend` interface + `VfsNode`, `GrepMatch` types
`src/storage/postgres.ts`	PostgreSQL implementation with RLS-aware connection handling
`src/storage/schema.ts`	Embedded SQL constants for auto-init
`src/storage/index.ts`	`createBackend()` factory

Read the full file on GitHub · 90 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 · 90 lines · 1,167 tokens per session scan A 6e934c5d6aae

Subscribe to this mod's changes

mcp-virtual-fs CLAUDE.md is an instructions file published in the GitHub repository lu-zhengda/mcp-virtual-fs (3 stars, last pushed 8mo ago), licensed MIT. It adds 1,167 tokens to every session, about $0.0047 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 2026-08-31.

ai-agent filesystem mcp mcp-server model-context-protocol postgresql

mcp-virtual-fs CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-virtual-fs CLAUDE.mdlu-zhengda/mcp-virtual-fs	Instructions file	3	8mo ago	MIT	A	1,167	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	yesterday	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

mcp-virtual-fs: Instructions file for Claude Code