Provides tools for querying and manipulating MongoDB databases, including executing queries and inserting records.
Provides tools for querying and manipulating MySQL databases, including executing queries, inserting records, and managing transactions.
Provides tools for querying and manipulating PostgreSQL databases, including executing queries, inserting records, and managing transactions.
Provides tools for querying and manipulating SQLite databases, including executing queries, inserting records, and managing transactions.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Server Toolkit fetch the latest Hacker News headlines and save them to news.md"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
The fastest way to connect AI agents to the real world.
A production-ready Model Context Protocol server toolkit that gives your AI agents superpowers.
Quick Start · Features · Architecture · Documentation
Every AI agent needs tools. MCP Server Toolkit gives them file system access, web fetching, database queries, and shell commands — all through a single, standardized protocol.
graph LR
A[🤖 AI Agent] -->|MCP Protocol| B[🔌 MCP Server Toolkit]
B --> C[📁 File System]
B --> D[🌐 Web Fetch]
B --> E[🗄️ Database]
B --> F[💻 Shell]Related MCP server: MCP Server Toolkit
Tool | Description | Status |
📁 File System | Read, write, search, and manage files | ✅ Production Ready |
🌐 Web Fetch | Fetch web pages, APIs, and download files | ✅ Production Ready |
🗄️ Database | Query PostgreSQL, MySQL, SQLite, MongoDB | ✅ Production Ready |
💻 Shell | Execute commands with sandboxing | ✅ Production Ready |
🔐 Auth | OAuth2 / API Key / JWT authentication | 🚧 Coming Soon |
📊 Metrics | Prometheus-compatible metrics endpoint | 🚧 Coming Soon |
pip install mcp-server-toolkitfrom mcp_server import MCPServer, tools
# Create server with default tools
server = MCPServer(
name="my-agent-tools",
tools=[tools.FileSystem(), tools.WebFetch(), tools.Database(), tools.Shell()]
)
# Start serving
server.run(port=8080)# config.yaml
server:
name: my-mcp-server
port: 8080
auth: none
tools:
filesystem:
root: /workspace
allowed_extensions: [.py, .js, .ts, .md]
web_fetch:
timeout: 30
user_agent: "MCP-Toolkit/1.0"
database:
url: postgresql://user:pass@localhost:5432/mydb
shell:
allowed_commands: [ls, cat, grep, python]
sandbox: truemcp-server --config config.yamlmcp-server-toolkit/
├── mcp_server/
│ ├── __init__.py # Public API
│ ├── server.py # Core MCP server
│ ├── protocol.py # MCP protocol handler
│ └── tools/
│ ├── filesystem.py # File operations
│ ├── web_fetch.py # HTTP client
│ ├── database.py # DB connectors
│ └── shell.py # Command executor
├── config.yaml.example # Example config
├── pyproject.toml
└── README.mdfrom mcp_server.tools import FileSystem
fs = FileSystem(root="/workspace")
# Read file
content = await fs.read("src/main.py")
# Write file
await fs.write("output.txt", "Hello, World!")
# Search files
results = await fs.search("**/*.py", pattern="import asyncio")
# List directory
files = await fs.listdir("src/", recursive=True)from mcp_server.tools import WebFetch
web = WebFetch(timeout=30)
# Fetch page
page = await web.fetch("https://api.github.com/user")
# Download file
await web.download("https://example.com/data.csv", "local.csv")
# Parse HTML
text = await web.extract_text("https://news.ycombinator.com")from mcp_server.tools import Database
db = Database(url="postgresql://localhost/mydb")
# Query
rows = await db.query("SELECT * FROM users WHERE active = true")
# Insert
await db.insert("users", {"name": "Alice", "role": "admin"})
# Transaction
async with db.transaction() as tx:
await tx.execute("UPDATE accounts SET balance = balance - 100 WHERE id = 1")
await tx.execute("UPDATE accounts SET balance = balance + 100 WHERE id = 2")We love contributions! See CONTRIBUTING.md for guidelines.
git clone https://github.com/fzs356113-oss/mcp-server-toolkit.git
cd mcp-server-toolkit
pip install -e ".[dev]"
pytestMIT License - see LICENSE for details.
⭐ Star this repo if you find it useful! ⭐
Made with ❤️ by fzs356113-oss
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Governed app access for AI agents: 1,000+ apps & 12,000+ tools via Code Mode MCP.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
