---
id: crewai-tools
version: "1.15.16"
license: unclear
license_treatment: unclear
maintenance: active
---

# crewai-tools — Set of tools for the crewAI framework

License: unclear · Maintenance: active · Downloads: 11.5M/mo

## What it is and what it does

CrewAI Tools is a companion library to the CrewAI framework that equips AI agents with a toolkit for real-world tasks. It includes built-in tools for file I/O, web scraping, database queries (MySQL, MongoDB, Qdrant, Weaviate), API calls (Serper, Exa), and AI integrations (DALL-E, vision models). You can also define custom tools by subclassing BaseTool or using a @tool decorator.

The library also supports the Model Context Protocol (MCP), allowing agents to access hundreds of community-built tools from MCP servers via a managed adapter. This makes it a bridge between CrewAI agents and external services, reducing boilerplate and letting you focus on agent orchestration rather than tool plumbing.

Use it for:

- Equip a CrewAI agent with web scraping and file-reading tools to gather and process research data automatically.
- Build a multi-agent workflow that queries databases and APIs in parallel to aggregate real-time information.
- Connect a CrewAI agent to an MCP server to unlock domain-specific tools (e.g., PubMed search) without writing custom integrations.
- Create a custom tool by subclassing BaseTool or decorating a function, then inject it into an agent for specialized business logic.
- Automate document processing by combining FileReadTool, PyMuPDF, and python-docx to extract and transform content.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

CrewAI Tools provides a collection of ready-made and custom tools that extend CrewAI agents with capabilities for file management, web scraping, database integration, API access, and AI-powered operations.

Yes, if you are already using CrewAI and need to extend agents with external integrations. The package is actively maintained, has low install friction, and offers both pre-built and custom tool patterns. However, verify the license before production use, as it is currently undeclared in the metadata.

## Install

pip install crewai-tools
uv add crewai-tools
poetry add crewai-tools

## Installing crewai-tools

Before you install: Low install friction with a pure-Python wheel and active maintenance—released 2026-08-14 with 57078 repository stars. Eight runtime dependencies (beautifulsoup4, crewai, pymupdf, python-docx, pytube, requests, tiktoken, youtube-transcript-api) are all widely used libraries.

License in practice: License treatment is unclear; the package has no declared SPDX identifier or raw license field in its metadata. Verify the actual license before deploying in commercial or restricted environments.

Quickstart:

pip install crewai-tools

from crewai_tools import FileReadTool, ScrapeWebsiteTool
from crewai import Agent

tools = [FileReadTool(), ScrapeWebsiteTool()]
agent = Agent(role="researcher", goal="gather data", tools=tools)

Requires Python 3.10 or later (and less than 3.14). CrewAI itself must be installed as a runtime dependency.

Verify before relying:

- Whether the package is distributed under an open-source license and which one (MIT, Apache 2.0, etc.)
- Stability guarantees or breaking-change policy across minor versions
- Performance characteristics when using MCP server integrations with large tool sets

## Package facts

- License: not declared (unclear)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 11.5M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

crewai agent tools, ai agent toolkit, web scraping for agents, file management tools, database integration agents, custom agent tools, mcp server integration, agent-tools, mcp-integration, crewai-ecosystem

[View on SkillFed](https://skillfed.io/packages/crewai-tools) · [View on PyPI](https://pypi.org/project/crewai-tools/)