mcpField
M
MCP Servers Collection

MCP Servers Collection

Local
github.com/iamkaiaDeveloper Tools0Updated 79w ago

About MCP Servers Collection

MCP Servers Collection bundles five MCP servers for Claude Desktop: LINE messaging, email, web-page fetching, Word document editing, and filesystem access. It provides setup instructions for running and configuring the servers individually.

Key features

  1. 01LINE message tools
  2. 02Email sending and listing
  3. 03Web-page title and snippet retrieval
  4. 04DOCX creation and editing
  5. 05Mounted-directory file operations

Use cases

  1. 01Send messages to LINE chats
  2. 02Send email and list recent messages
  3. 03Fetch page summaries and manage Word files
  4. 04Read and search files in allowed directories

MCP support

The collection consists of five MCP servers configured for Claude Desktop. Each exposes tools for its service, including messaging, email, fetching, document editing, and filesystem operations.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"implement": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem"
],
"env": {
"CHANNEL_ACCESS_TOKEN": "<CHANNEL_ACCESS_TOKEN>",
"DESTINATION_USER_ID": "<DESTINATION_USER_ID>",
"PYTHONPATH": "<PYTHONPATH>"
}
}
}
}
Run commandnpx -y @modelcontextprotocol/server-filesystem
Environment variables to set
CHANNEL_ACCESS_TOKENSecret
DESTINATION_USER_ID
PYTHONPATH

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@modelcontextprotocol/server-filesystem

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Servers Collection

This repository hosts five Model Context Protocol (MCP) servers you can mount into Claude Desktop:

  1. line-bot
  2. email_mcp
  3. fetch
  4. word-document-service
  5. filesystem

🚀 Quick Start

  1. line-bot(in different terminal)
git clone https://github.com/iamkaia/email-mcp-server-simple.git
cd email-mcp-server-simple

## **Set up Python env and install requirement thing(for _email_mcp_, )**  
python -m venv .venv
source .venv/bin/activate      # Windows: .\.venv\Scripts\activate
pip install -r requirements.txt

### Fill `.env`** (for `email_mcp` only—do **not** commit):
# SMTP
SMTP_SERVER=smtp.example.com
SMTP_PORT=587
[email protected]
SMTP_PASSWORD=your_smtp_password

# IMAP
IMAP_SERVER=imap.example.com
IMAP_PORT=993
[email protected]
IMAP_PASSWORD=your_imap_password

## start
uvicorn main:app --reload --host 0.0.0.0 --port 8000
  1. line-bot-mcp(in different terminal) :
# Clone the repository
git clone [email protected]:line/line-bot-mcp-server.git
cd line-bot-mcp-server && npm install && npm run build
  1. fetch(in different terminal):
pip install mcp-server-fetch
python -m mcp_server_fetch
  1. Word-MCP-Server(in different terminal):
# Clone the repository
git clone https://github.com/GongRzhe/Office-Word-MCP-Server.git
cd Office-Word-MCP-Server

# Install dependencies
pip install -r requirements.txt

#start
python setup_mcp.py
  1. filesystem(in different terminal):
# filesystem (via NPX) (you can ignore this step if you have nide and npx)
npx -y @modelcontextprotocol/server-filesystem \
  "/Users/username/Desktop" \
  "/path/to/other/allowed/dir"

🔧 Claude Desktop Configuration

Edit your claude_desktop_config.json to spawn each MCP tool:

{
  "mcpServers": {
    "line-bot": {
      "command": "node",
      "args": [
        "to\\the\\path\\line-bot-mcp-server\\dist\\index.js"
      ],
      "env": {
        "CHANNEL_ACCESS_TOKEN" : "xxx",
        "DESTINATION_USER_ID" : "xxx"
      }
    },
    "email_mcp": {
      "command": "to\\the\\path\\mcp-proxy.exe",
      "args": [
        "http://localhost:9000/mcp"      
      ]
    },
    "fetch": {
      "command": "python",
      "args": ["-m", "mcp_server_fetch"]
    },
    "word-document-server": {
      "command": "to\\the\\path\\python.exe",
      "args": [
        "to\\the\\path\\word_server.py"
      ],
      "env": {
        "PYTHONPATH": "to\\the\\path\\Office-Word-MCP-Server"
      }
    },
    "filesystem": {
      "command": "npx",
      "args": [
        "--yes",
        "@modelcontextprotocol/server-filesystem",
        "/Users/username/Desktop",
        "/path/to/other/allowed/dir"
      ]
    }
  }
}

After saving, quit & restart Claude Desktop. The 🔨 Tools menu will list all available MCP tools.


📦 Servers & Tools

1. line-bot
  • Tools: send_line_message, broadcast_flex_message, broadcast_text_message…
  • Push messages into a Line chat.
2. email_mcp
  • Tools: send_email, list_recent_emails
3. fetch
  • Tools: fetch_page
  • Input: url ⇒ Output: title, headings, snippet.
4. word-document-service
  • Tools:
    • create_document, add_heading, insert_table, format_text, search_replace, …
  • Manipulate DOCX files programmatically.
5. filesystem
  • Tools:
    • read_file, write_file, list_directory, search_files, get_file_info, …
  • Operate only within the mounted directories.
detailed intro of tool_list tools.md

🎯 Example JSON‑RPC Calls (for reference only)

// send_email
{
  "tool":"send_email",
  "input":{"params":{
    "to":["[email protected]"],
    "subject":"Hello",
    "body":"This is a test.",
    "html":false
  }}
}

// list_recent_emails
{
  "tool":"list_recent_emails",
  "input":{"params":{
    "limit":3
  }}
}

// fetch_page
{
  "tool":"fetch_page",
  "input":{"params":{"url":"https://example.com"}}
}

// create a Word doc
{
  "tool":"create_document",
  "input":{"params":{"filename":"report.docx","title":"Sales Report"}}
}

// filesystem read
{
  "tool":"read_file",
  "input":{"params":{"path":"to//the//path//notes.txt"}}
}

📃 License

All servers are MIT‑licensed. See each subfolder’s LICENSE for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.