agentmods.dev

filesystem

filesystem is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from timothywarner-org/claude-architect. Its token cost is not measured, scanned A, original, MIT.

A configuration for a local MCP server that gives an AI agent access to selected filesystem directories. MCP is a standard way for an AI agent to call external tools.

In plain words
What is it for?
Use it to let an agent read and write files within a specified project directory. Set the PROJECT_ROOT environment variable to define the allowed location.
Why use it?
It lets the agent work with project files while limiting access to the directory supplied as the project root. The server runs locally with the user’s filesystem permissions.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

One of 6 entries in .mcp.json — they are configured in one file and arrive together.

not rated 80 +2 1mo ago A scan tokens not measured original MIT
View the source file timothywarner-org/claude-architect
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 mcp/timothywarner-org/claude-architect/filesystem
Clone the repo
git clone --depth 1 https://github.com/timothywarner-org/claude-architect

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

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 filesystem

README.md
[![agentmods](https://agentmods.dev/badge/mcp/timothywarner-org/claude-architect/filesystem.svg)](https://agentmods.dev/mcp/timothywarner-org/claude-architect/filesystem)
Your own site
<a href="https://agentmods.dev/mcp/timothywarner-org/claude-architect/filesystem"><img src="https://agentmods.dev/badge/mcp/timothywarner-org/claude-architect/filesystem.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

filesystem 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.

.mcp.json · 14 lines

What it actually says

{
  "filesystem": {
    "_comment": "stdio transport. Local subprocess launched via npx. No auth needed because the server runs as your user with your file-system permissions. Scope the allowed paths in args, never expose the whole drive.",
    "command": "npx",
    "args": [
      "-y",
      "@modelcontextprotocol/server-filesystem",
      "${PROJECT_ROOT}"
    ],
    "env": {
      "PROJECT_ROOT": "${PROJECT_ROOT}"
    }
  }
}
Same file

What else .mcp.json configures

This page is one entry in a file that holds 6. Installing the file brings all of them; each is measured and scanned on its own page.

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 · 14 lines scan A 4a7936170a76

Subscribe to this mod's changes

filesystem is an MCP server published in the GitHub repository timothywarner-org/claude-architect (80 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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.

agent-sdkagentic-aianthropiccertificationclaudeclaude-api
Related

Other mcp servers, from other repositories

inventory

MCP server "inventory" as configured in aderegil/claude-certified-architect. Runs mcp_server/inventory_server.py with python. Needs 1 environment variable to run.

aderegil/claude-certified-architect · not measured

fetch

MCP server "fetch" as configured in aderegil/claude-certified-architect. Runs mcp_server_fetch with python.

aderegil/claude-certified-architect · not measured

db

Minimal, token-efficient Database MCP Server for PostgreSQL, MySQL, SQL Server, SQLite, MariaDB. Runs locally from the @bytebase/dbhub npm package.

ding113/claude-code-hub · not measured

chrome-devtools

Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.

ding113/claude-code-hub · not measured

rncp

MCP server "rncp", hosted remotely at mcp-rncp.com, as configured in ALDEBERTArnaud/mcp-rncp.

ALDEBERTArnaud/mcp-rncp · not measured

architect-ai

MCP server "architect-ai" as configured in aviraldua93/architect-ai. Runs dist/mcp/server.js with node. Needs 1 environment variable to run.

aviraldua93/architect-ai · not measured