Filesystem MCP server: files, processes, sessions, async search, OCR, archives, safe delete.
MCPpedia last refreshed this data
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"filecommander": {
"command": "ellmos-filecommander"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Part of the ellmos-ai family.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'vitest' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked vitest against OSV.dev.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in other
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
Pi Coding Agent extension (CLI-first) — routes bash/read/grep/find/ls through lean-ctx CLI for strong token savings. Optional MCP bridge can register advanced tools.
97% token reduction for AI coding sessions — zero deps, 21 languages, MCP server
One local source for the MCP servers, tools, and memory your AI coding agents share, synced into each tool's native config with a review gate and a receipt for every change. No daemon, no lock-in.
MCP Security Weekly
Get CVE alerts and security updates for io.github.ellmos-ai/ellmos-filecommander-mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Part of the ellmos-ai family.
A comprehensive Model Context Protocol (MCP) server that gives AI assistants full filesystem access, process management, interactive shell sessions, and async file search capabilities.
46 tools in a single server - everything an AI agent needs to interact with the local system.
Discovery keywords: local filesystem MCP server, safe delete MCP, Recycle Bin MCP server, process management MCP, interactive shell MCP, async file search for AI agents, cloud-lock-safe file operations, Markdown to PDF MCP, OCR MCP server, ZIP archive MCP.
Registry status: published on npm, indexed by jsDelivr, visible on LobeHub, listed on Glama, and prepared for the official MCP Registry via server.json. Some third-party directories still show older 43-tool metadata, so the canonical README/npm metadata should remain the source of truth until their reindex catches up.
[!NOTE] For AI Agents & LLM Integrations: FileCommander provides 46 specialized tools accessible via standard stdio transport. All tool names use the
fc_prefix to prevent namespace collisions. For LLMs, compact context and schema overviews are available inllms.txtandserver.json.
Most filesystem MCP servers only cover basic read/write operations. FileCommander goes further:
flowchart TD
subgraph Client["MCP Client Layer"]
Claude["Claude Desktop / Claude Code"]
Custom["Custom LLM Agents / Frameworks"]
end
subgraph Transport["Transport Layer"]
Stdio["Stdio Transport (JSON-RPC)"]
end
subgraph Core["ellmos FileCommande
... [View full README on GitHub](https://github.com/ellmos-ai/ellmos-filecommander-mcp#readme)