MCP.so
ログイン
F

Fsext Mcp Server Typescript

@kurtzhi

リポジトリ

Fsext Mcp Server Typescript について

A high-performance, secure, and production-grade Model Context Protocol (MCP) server built with TypeScript, providing comprehensive filesystem operations, advanced text search & replace, image processing, and Tesseract OCR capabilities. Designed for LLM agent integration, it deli

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

公開者

kurtzhi

投稿者

Kurt Zhi

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "fsext-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "fsext-mcp-server"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Fsext Mcp Server Typescript?

Fsext Mcp Server Typescript is a high-performance, secure, production-grade Model Context Protocol (MCP) server built with TypeScript. It provides comprehensive filesystem operations, advanced text search and replace, image processing via Sharp, and cross‑platform Tesseract OCR. Designed for LLM agent integration, it offers strict input validation, standardized responses, and multi‑transport remote deployment support.

How to use Fsext Mcp Server Typescript?

Run without installation using npx -y fsext-mcp-server (add --lock-root /your/workspace to restrict the accessible directory). For persistent use, install globally (npm install -g fsext-mcp-server) or locally (npm install fsext-mcp-server). Start with commands fsext-mcp-server-ts, fsext-mcp-server, fsext-ts, or fsext. Choose a transport via --transport stdio, --transport http, or --transport sse and optionally set host, port, and origin.

Key features of Fsext Mcp Server Typescript

  • Full filesystem CRUD with recursive directory replication
  • Streaming I/O for GB‑level files without full memory loading
  • Recursive text search with regex, preview lines, and in‑place replace
  • Image resize (aspect‑ratio lock), crop, and arbitrary‑angle rotation
  • WASM‑first Tesseract OCR without local engine installation
  • Strict input validation and unified success/error response structures

Use cases of Fsext Mcp Server Typescript

  • LLM agents performing safe file operations on a restricted workspace
  • Processing and searching large log files or codebases line by line
  • Editing text in multiple files with previews before applying changes
  • Extracting text from images via OCR for downstream AI analysis
  • Remote deployment with Streamable HTTP or SSE transports

FAQ from Fsext Mcp Server Typescript

What transports does Fsext Mcp Server Typescript support?

It natively supports three MCP transports: stdio (for local clients), SSE (legacy remote stream), and Streamable HTTP (modern bidirectional remote transport).

How do I install Fsext Mcp Server Typescript?

Install globally with npm install -g fsext-mcp-server or locally in a project with npm install fsext-mcp-server. You can also run it directly via npx -y fsext-mcp-server without installation.

Does Fsext Mcp Server Typescript require a local Tesseract installation?

No. The built‑in OCR uses a WASM‑first approach, so no local Tesseract binary or tessdata path is needed by default. Custom paths can be given if desired.

Can Fsext Mcp Server Typescript handle very large files?

Yes. It uses segmented text reading and chunked binary streaming for both reading and writing, avoiding full memory loading and supporting GB‑level files.

How do I restrict the server to a specific workspace?

Pass the --lock-root /path/to/workspace flag at startup. The server will reject operations outside that root directory.

コメント

「AI とエージェント」の他のコンテンツ

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768

Mcp Agent

lastmile-ai

Build effective agents using Model Context Protocol and simple workflow patterns

8.4K

Sequential Thinking Multi-Agent System (MAS)

FradSer

An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.

306

欢迎来到 智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages

utensils

MCP-NixOS - Model Context Protocol Server for NixOS resources

739