What can you do with this server?

mcp-toolkit is a general-purpose MCP server for AI agents with the following capabilities: * Web Search — Search the web via DuckDuckGo with optional deep content extraction using Playwright, configurable result count (up to 10), and language support. * URL Fetching — Extract main content from a direct HTTP/HTTPS URL using Playwright. * Generic HTTP Requests — Execute GET, POST, PUT, PATCH, DELETE, HEAD, or OPTIONS requests with optional headers and body. * Time & Date Utilities — Get current time in any timezone, convert between timezones, parse dates, add durations, and calculate differences. * Persistent Memory (Key-Value Store) — Store, retrieve, delete, list, search, and clear key-value pairs persistently via SQLite, with namespace support. * Sandboxed Python Execution — Run Python code in an isolated subprocess with configurable timeout (up to 60s), memory limit (256MB on Linux), optional stdin, and no network access. * Sandboxed JavaScript Execution — Run Node.js code in an isolated subprocess with the same safety restrictions as Python (requires Node.js installed).

Which integrations are available for this server?

Provides web search capabilities using DuckDuckGo, allowing AI agents to search the web and extract content from web pages with configurable parameters like result count and language. Supports installation directly from GitHub repositories and provides development tools for extending the MCP server with custom functionality.

How do I use mcp-toolkit?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-toolkit search for latest Python 3.14 release notes with deep extraction" 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.

de en es ja ko ru zh

mcp-toolkit

by YoshiLoL0526

Overview Schema Related Servers Score Discussions

Python

Hybrid

mcp-toolkit

General-purpose MCP server for AI agents. Built with Python 3.13, FastMCP, and Playwright.

Available tools

Tool	Description
`web_search`	Searches DuckDuckGo and extracts web content with Playwright
`fetch_url`	Extracts the main content from a direct URL
`http_request`	Executes generic HTTP requests without Playwright
`time_now`	Returns the current date and time in a specific timezone
`date_utils`	Converts timezones and calculates dates/durations
`memory_set`	Saves a persistent value in SQLite
`memory_get`	Retrieves a saved value
`memory_delete`	Deletes a key
`memory_list`	Lists all keys (with optional prefix filter)
`memory_clear`	Clears all memory (irreversible!)
`memory_search`	Searches for text in saved keys and values
`run_python`	Executes Python code in a sandboxed environment with a timeout
`run_js`	Executes JavaScript code with Node.js in a sandboxed environment with a timeout

Related MCP server: MCP Server

Installation

Prerequisites

UV installed
Python 3.13 (UV downloads it automatically if not present)
Node.js (optional, only for run_js)

Option A — Install from local folder

git clone https://github.com/YoshiLoL0526/mcp-toolkit
cd mcp-toolkit
uv tool install --python 3.13 .

Option B — Install directly from GitHub

uv tool install --python 3.13 git+https://github.com/YoshiLoL0526/mcp-toolkit

Mandatory step: install Chromium for Playwright

After installing the package, run this command once:

# Obtener la ruta del entorno virtual creado por uv tool
uv tool run --from mcp-toolkit python -m playwright install chromium

Or alternatively, if you know the environment path:

~/.local/share/uv/tools/mcp-toolkit/bin/python -m playwright install chromium

Configuration in MCP clients

Claude Desktop (`~/Library/Application Support/Claude/claude_desktop_config.json`)

{
  "mcpServers": {
    "mcp-toolkit": {
      "command": "mcp-toolkit"
    }
  }
}

On Windows, the path is %APPDATA%\Claude\claude_desktop_config.json

Cursor / VS Code (`.cursor/mcp.json` or `.vscode/mcp.json`)

{
  "servers": {
    "mcp-toolkit": {
      "type": "stdio",
      "command": "mcp-toolkit"
    }
  }
}

HTTP Server (for remote access or multiple clients)

mcp-toolkit --transport http --host 0.0.0.0 --port 8080

The server will listen on http://<host>:<port>/mcp using the streamable-http transport (current MCP standard). You can change the path with --path /other-path.

The --transport sse transport is maintained for compatibility with older clients, but it has been deprecated since FastMCP 2.3.

Using the tools

`web_search`

Parámetros:
  query        (str)  — texto a buscar
  max_results  (int)  — resultados a devolver, default 5, máximo 10
  deep         (bool) — si True, extrae el contenido completo de cada página
  language     (str)  — idioma para las cabeceras HTTP, default "es-ES"

Example (agent):

Busca las últimas noticias sobre Python 3.13 con deep=True

`fetch_url`

Parámetros:
  url (str) — URL absoluta HTTP o HTTPS a leer

Example (agent):

Lee https://example.com/articulo con fetch_url

`http_request`

Parámetros:
  method  (str)  — método HTTP: GET, POST, PUT, PATCH, DELETE, HEAD u OPTIONS
  url     (str)  — URL absoluta HTTP o HTTPS
  headers (dict) — cabeceras opcionales
  body    (str)  — cuerpo opcional como texto
  timeout (int)  — segundos máximos, default 10, máximo 60

Example (agent):

Haz un POST a https://api.example.com/items con http_request

`time_now` / `date_utils`

time_now(timezone_name="UTC")

date_utils(
  action="convert_timezone",
  value="2026-04-21T12:00:00+00:00",
  target_timezone="America/New_York"
)

Actions supported by date_utils: parse, convert_timezone, add, and diff. For dates without an offset, timezone_name is used; timezones must be IANA names like UTC, America/New_York, or Europe/Madrid.

`memory_set` / `memory_get`

memory_set(key="usuario_nombre", value="Carlos", namespace="default")
memory_get(key="usuario_nombre", namespace="default")
memory_list(prefix="usuario_", namespace="default")
memory_search(query="Carlos", namespace="default")

Data is saved in ~/.local/share/mcp-toolkit/memory.db. All memory tools accept a namespace to separate data by project, client, or conversation. If not specified, default is used.

`run_python`

Parámetros:
  code     (str) — código Python a ejecutar
  timeout  (int) — segundos máximos, default 10, máximo 60
  stdin    (str) — entrada estándar opcional

Security restrictions:

Minimal environment: does not inherit secrets or arbitrary variables from the host process
Temporary working directory per execution
HTTP proxies overridden by environment variables
Memory limit: 256 MB (Linux/macOS)
Strict timeout: the process is killed when time runs out
On Windows, there is no per-process memory limit applied from Python
Network blocking is not a guarantee of strong isolation; for untrusted code, it is recommended to run the server inside a container or VM with network policies

`run_js`

Same parameters as run_python. Requires Node.js installed on the system.

Development

git clone https://github.com/YoshiLoL0526/mcp-toolkit
cd mcp-toolkit
uv sync
uv run python -m playwright install chromium

# Ejecutar en modo desarrollo
uv run mcp-toolkit

# Tests
uv run pytest

Adding a new tool

Create mcp_toolkit/tools/my_tool.py with an async def my_tool(...) -> str function
Import and register it in server.py with mcp.tool()(my_tool)
Reinstall: uv tool install --python 3.13 . --reinstall

Project structure

mcp-toolkit/
├── pyproject.toml
├── README.md
├── mcp_toolkit/
│   ├── server.py              # FastMCP app + registro
│   ├── tools/
│   │   ├── web_search.py      # Playwright: buscar + extraer
│   │   ├── fetch_url.py       # Extraer una URL directa
│   │   ├── http_request.py    # Cliente HTTP genérico
│   │   ├── date_time.py       # Fechas, zonas horarias y duraciones
│   │   ├── memory.py          # SQLite KV store con namespaces
│   │   ├── run_python.py      # Sandbox Python
│   │   └── run_js.py          # Sandbox Node.js
│   └── utils/
│       ├── browser.py         # Singleton Playwright
│       └── sandbox.py         # Helpers de subprocess y timeout
└── tests/

License

MIT

Install Server

license - permissive license

quality

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

–Release cycle

–Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Tools

Related MCP Servers

mcp-web-calc
Search Browser Automation Text Summarization
tickernelz
A
license
A
quality
D
maintenance
An MCP server that enables web searching, URL content extraction, and summarization without requiring API keys. It also provides advanced mathematical evaluation and multi-language Wikipedia summary retrieval tools.
Updated 4 months ago (2026-05-03 08:45 UTC)
5
159
6
MIT
MCP Server
File Systems Web Scraping Shell Access
kennetchau
A
license
-
quality
D
maintenance
A modular MCP server providing file operations, web search, URL scraping, and sandboxed command execution for LLM interactions.
Updated 3 months ago (2026-05-16 16:57 UTC)
1
MIT
superhighway-mcp
Search Cryptocurrency Web3 & Decentralized Tech
patwalls
A
license
A
quality
B
maintenance
An MCP server that provides real-time web search to AI agents via a pay-per-search USDC microtransaction system.
Updated 2 months ago (2026-06-11 02:15 UTC)
5
59
2
MIT
NATE-MCP-SERVER
Code Execution File Systems Browser Automation
NateYeh
A
license
-
quality
D
maintenance
A powerful MCP server that enables LLMs to safely execute code, control file systems, search the web, and integrate with services like Gmail and TMDB.
Updated 5 months ago (2026-04-02 07:59 UTC)
MIT

View all related MCP servers

Related MCP Connectors

Kody
Personal assistant MCP server with search, execute, packages, jobs, secrets, and integrations.
Motecloud Memory
Cloud-hosted MCP server for durable AI memory
gread
An MCP server that gives your AI access to the source code and docs of all public github repos

View all MCP Connectors

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/YoshiLoL0526/mcp-toolkit'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

mcp-toolkit

Available tools

Installation

Prerequisites

Option A — Install from local folder

Option B — Install directly from GitHub

Mandatory step: install Chromium for Playwright

Configuration in MCP clients

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json)

Cursor / VS Code (.cursor/mcp.json or .vscode/mcp.json)

HTTP Server (for remote access or multiple clients)

Using the tools

web_search

fetch_url

http_request

time_now / date_utils

memory_set / memory_get

run_python

run_js

Development

Adding a new tool

Project structure

License

Maintenance

Resources

Looking for Admin?

Tools

Related MCP Servers

mcp-web-calc

MCP Server

superhighway-mcp

NATE-MCP-SERVER

Related MCP Connectors

Latest Blog Posts

MCP directory API

Claude Desktop (`~/Library/Application Support/Claude/claude_desktop_config.json`)

Cursor / VS Code (`.cursor/mcp.json` or `.vscode/mcp.json`)

`web_search`

`fetch_url`

`http_request`

`time_now` / `date_utils`

`memory_set` / `memory_get`

`run_python`

`run_js`