Is Filesystem MCP server safe?
- Dangerous MCP tool capability
- Node.js filesystem read
- Node.js filesystem write/delete
@modelcontextprotocol/server-filesystem is an AI npm_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 5 risky constructs are reported for review. It can: filesystem read, filesystem write, install time execution and mcp tools detected — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
@modelcontextprotocol/server-filesystem 2026.8.31
Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Filesystem MCP server's authors. Report a false positive.
Behavioral traits
How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.
Findings (5)
An MCP tool exposes a powerful capability (files, shell, network, browser, or credentials).
server.registerTool("read_file", {server.registerTool("write_file", {server.registerTool("edit_file", {server.registerTool("list_directory", {server.registerTool("list_directory_with_sizes", {Why it matters: Wired into an agent, these grant it real access to your machine — confirm each is required.
Fix: Confirm each powerful tool is required and constrained; broad MCP tools (shell/filesystem/network) grant an agent significant host access.
The component reads files from disk.
return await fs.readFile(filePath, encoding);
const content = normalizeLineEndings(await fs.readFile(filePath, 'utf-8'));
Why it matters: Usually legitimate, but worth confirming it can't be steered into reading sensitive files.
Fix: Confirm which files are read and that paths cannot be influenced by untrusted input to reach sensitive locations.
The component writes or deletes files on disk.
await fs.writeFile(filePath, content, { encoding: "utf-8", flag: 'wx' });await fs.writeFile(tempPath, content, 'utf-8');
await fs.unlink(tempPath);
await fs.writeFile(tempPath, modifiedContent, 'utf-8');
await fs.unlink(tempPath);
Why it matters: Usually legitimate, but worth confirming the paths can't be controlled by untrusted input.
Fix: Confirm which files are written/deleted and that paths cannot be influenced by untrusted input.
package.json has a 'prepare' script (runs on git/local installs and before publishing).
"prepare": "npm run build",
Why it matters: Usually a build step, but confirm it doesn't fetch or run remote code.
Fix: Usually a legitimate build step; confirm it only builds and does not fetch or execute remote code.
An MCP tool surface (manifest or tool definitions) was found.
const server = new McpServer({server.registerTool("read_file", {server.registerTool("read_text_file", {server.registerTool("read_media_file", {server.registerTool("read_multiple_files", {server.registerTool("write_file", {server.registerTool("edit_file", {server.registerTool("create_directory", {server.registerTool("list_directory", {server.registerTool("list_directory_with_sizes", {server.registerTool("directory_tree", {server.registerTool("move_file", {server.registerTool("search_files", {server.registerTool("get_file_info", {server.registerTool("list_allowed_directories", {Why it matters: Just context — review which tools it offers and their permissions.
Fix: Review the declared MCP tools and their permissions.
Check your own component
Run the same evidence-backed scan on any MCP server, agent skill, or package.
Scan your own componentHow we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →