Custom Tools

Overview

DeerFlow’s tool system is fully extensible. You can add custom tools by:

Configuring built-in tools - Customize existing tools in config.yaml
Creating Python tools - Write custom tool functions
Using MCP servers - Integrate external tools via Model Context Protocol

Tools are the atomic actions the agent can perform. Skills provide higher-level workflows that use these tools.

Tool Architecture

┌─────────────────────────────────────────────────────────────┐
│                     Tool Sources                            │
└─────────────────────────────────────────────────────────────┘

┌──────────────────┐  ┌──────────────────┐  ┌──────────────────┐
│  Built-in Tools  │  │ Configured Tools │  │   MCP Tools      │
│  (src/tools/)    │  │  (config.yaml)   │  │ (extensions.json)│
├──────────────────┤  ├──────────────────┤  ├──────────────────┤
│ - present_file   │  │ - web_search     │  │ - github         │
│ - clarification  │  │ - web_fetch      │  │ - filesystem     │
│ - view_image     │  │ - bash           │  │ - postgres       │
│                  │  │ - read_file      │  │ - brave-search   │
│                  │  │ - write_file     │  │ - ...            │
└──────────────────┘  └──────────────────┘  └──────────────────┘
           │                   │                    │
           └───────────────────┴────────────────────┘
                              │
                              ▼
                 ┌─────────────────────────┐
                 │  get_available_tools()  │
                 │   (src/tools/__init__)  │
                 └─────────────────────────┘

Built-in Tools

DeerFlow includes several built-in tools that are always available:

present_file

Present files to the user as downloadable artifacts

ask_clarification

Ask user for clarification when information is missing

view_image

View and analyze images using vision models

skill

Load additional skills dynamically

Configuring Tools in config.yaml

Tool Groups

Organize tools into logical groups:

config.yaml

tool_groups:
  - name: web          # Web operations
  - name: file:read    # Read-only file operations
  - name: file:write   # Write file operations
  - name: bash         # Shell execution

Adding Tools

Define tools using the use reflection system:

config.yaml

tools:
  # Web search using Tavily
  - name: web_search
    group: web
    use: src.community.tavily.tools:web_search_tool
    max_results: 5
    # api_key: $TAVILY_API_KEY  # Optional override

  # Web content fetching using Jina AI
  - name: web_fetch
    group: web
    use: src.community.jina_ai.tools:web_fetch_tool
    timeout: 10

  # Image search
  - name: image_search
    group: web
    use: src.community.image_search.tools:image_search_tool
    max_results: 5

  # File operations
  - name: ls
    group: file:read
    use: src.sandbox.tools:ls_tool

  - name: read_file
    group: file:read
    use: src.sandbox.tools:read_file_tool

  - name: write_file
    group: file:write
    use: src.sandbox.tools:write_file_tool

  - name: str_replace
    group: file:write
    use: src.sandbox.tools:str_replace_tool

  # Shell execution
  - name: bash
    group: bash
    use: src.sandbox.tools:bash_tool

The `use` Reflection System

The use field uses Python’s reflection to dynamically load tools: Format: module.path:function_or_class_name

Module Path

Python module path using dot notation:

src.community.tavily.tools

Separator

Colon (:) separates module from function/class:

src.community.tavily.tools:web_search_tool

Function/Class

The function or class to import:

# In src/community/tavily/tools.py
def web_search_tool(max_results: int = 5):
    ...

Creating Custom Python Tools

Create Tool File

Create a Python file for your tool:

backend/src/tools/custom/calculator.py

"""Custom calculator tool."""
from langchain_core.tools import tool

@tool
def calculator(expression: str) -> float:
    """Evaluate a mathematical expression.
    
    Args:
        expression: Mathematical expression to evaluate (e.g., "2 + 2", "10 * 5")
        
    Returns:
        The result of the calculation
    """
    try:
        # Safe evaluation of mathematical expressions
        result = eval(expression, {"__builtins__": {}}, {})
        return float(result)
    except Exception as e:
        return f"Error: {str(e)}"

Using eval() can be dangerous. This example restricts it to mathematical operations only. For production use, consider using ast.literal_eval() or a proper expression parser.

Add to config.yaml

config.yaml

tools:
  - name: calculator
    group: utility
    use: src.tools.custom.calculator:calculator

Test the Tool

Restart DeerFlow and test your tool:

make dev

Ask the agent:

“Calculate 25 * 4”
“What is 100 divided by 5?”

Tool with Configuration

Create tools that accept configuration parameters:

backend/src/tools/custom/weather.py

from langchain_core.tools import tool
import os

def create_weather_tool(api_key: str = None, units: str = "metric"):
    """Factory function to create weather tool with config."""
    
    api_key = api_key or os.getenv("WEATHER_API_KEY")
    
    @tool
    def get_weather(location: str) -> str:
        """Get current weather for a location.
        
        Args:
            location: City name or coordinates
            
        Returns:
            Weather information
        """
        # Call weather API with api_key and units
        # Implementation here...
        return f"Weather for {location}: Sunny, 22°C"
    
    return get_weather

Configure in config.yaml:

config.yaml

tools:
  - name: weather
    group: web
    use: src.tools.custom.weather:create_weather_tool
    api_key: $WEATHER_API_KEY
    units: imperial  # or metric

Sandbox-Aware Tools

Tools that interact with the filesystem should use the sandbox:

backend/src/tools/custom/file_analyzer.py

from langchain_core.tools import tool
from src.sandbox.provider import get_sandbox

@tool
def analyze_file(filepath: str, sandbox_id: str = "local") -> dict:
    """Analyze a file and return statistics.
    
    Args:
        filepath: Path to file in sandbox (e.g., /mnt/user-data/uploads/file.txt)
        sandbox_id: Sandbox identifier
        
    Returns:
        File statistics
    """
    sandbox = get_sandbox(sandbox_id)
    
    # Read file through sandbox
    content = sandbox.read_file(filepath)
    
    # Analyze content
    stats = {
        "size": len(content),
        "lines": len(content.splitlines()),
        "words": len(content.split()),
    }
    
    return stats

Always use sandbox methods for file operations to ensure compatibility with both local and Docker sandbox modes.

Tool Parameters and Type Hints

LangChain uses type hints and docstrings to generate tool schemas:

from typing import Optional, List
from langchain_core.tools import tool

@tool
def search_database(
    query: str,
    limit: int = 10,
    filters: Optional[List[str]] = None
) -> dict:
    """Search database with filters.
    
    Args:
        query: Search query string
        limit: Maximum number of results (default: 10)
        filters: Optional list of filter conditions
        
    Returns:
        Search results as dictionary
    """
    # Implementation
    pass

Environment Variables in Tools

Access environment variables securely:

import os
from langchain_core.tools import tool

@tool
def api_call(endpoint: str) -> dict:
    """Make API call to external service."""
    api_key = os.getenv("EXTERNAL_API_KEY")
    
    if not api_key:
        return {"error": "API key not configured"}
    
    # Make API call
    # ...

Set in .env:

.env

EXTERNAL_API_KEY=your-api-key-here

Tool Visibility and Access Control

Control which tools are available:

Tool Groups

Restrict tools by group in skills:

SKILL.md

---
name: data-analysis
allowed-tools:
  - file:read
  - bash
---

Conditional Tool Loading

Load tools based on configuration:

backend/src/tools/__init__.py

from typing import List
from langchain_core.tools import BaseTool

def get_available_tools(config: dict) -> List[BaseTool]:
    """Get available tools based on configuration."""
    tools = []
    
    # Load configured tools
    for tool_config in config.get("tools", []):
        if tool_config.get("enabled", True):
            tool = load_tool(tool_config)
            tools.append(tool)
    
    return tools

Testing Custom Tools

Unit Tests
Integration Tests

backend/tests/test_custom_tools.py

import pytest
from src.tools.custom.calculator import calculator

def test_calculator_addition():
    result = calculator.invoke({"expression": "2 + 2"})
    assert result == 4.0

def test_calculator_multiplication():
    result = calculator.invoke({"expression": "5 * 3"})
    assert result == 15.0

def test_calculator_error():
    result = calculator.invoke({"expression": "invalid"})
    assert "Error" in result

backend/tests/test_tool_integration.py

import pytest
from src.tools import get_available_tools
from src.config import load_config

def test_custom_tool_loaded():
    config = load_config()
    tools = get_available_tools(config)
    
    tool_names = [tool.name for tool in tools]
    assert "calculator" in tool_names

def test_tool_execution():
    config = load_config()
    tools = get_available_tools(config)
    
    calc_tool = next(t for t in tools if t.name == "calculator")
    result = calc_tool.invoke({"expression": "10 / 2"})
    assert result == 5.0

Run tests:

cd backend
uv run pytest tests/test_custom_tools.py -v

Debugging Tools

Add Logging

import logging
from langchain_core.tools import tool

logger = logging.getLogger(__name__)

@tool
def my_tool(param: str) -> str:
    logger.info(f"Tool called with param: {param}")
    # Implementation
    result = process(param)
    logger.info(f"Tool returning: {result}")
    return result

Check Tool Registration

# List available tools via API
curl http://localhost:2026/api/tools

Test Tool Directly

# In Python REPL or script
from src.tools.custom.my_tool import my_tool

result = my_tool.invoke({"param": "test"})
print(result)

Best Practices

Clear Documentation

Write detailed docstrings explaining:

What the tool does
When to use it
Parameter requirements
Return format

The LLM uses these to decide when to call your tool.

Error Handling

Always handle errors gracefully:

@tool
def my_tool(param: str) -> dict:
    try:
        result = risky_operation(param)
        return {"success": True, "data": result}
    except Exception as e:
        return {"success": False, "error": str(e)}

Type Safety

Use type hints and validation:

from pydantic import BaseModel, validator

class ToolInput(BaseModel):
    email: str
    
    @validator("email")
    def validate_email(cls, v):
        if "@" not in v:
            raise ValueError("Invalid email")
        return v

Performance

Cache expensive operations
Set reasonable timeouts
Return early for invalid inputs
Use async for I/O-bound operations

Next Steps

MCP Servers

Integrate external tools via Model Context Protocol

Creating Skills

Combine tools into higher-level workflows

Configuration

Learn about tool configuration options

Examples

Browse built-in tools for reference

Overview

Core Concepts

Configuration

Guides

Deployment

Overview

Tool Architecture

Built-in Tools

present_file

ask_clarification

view_image

skill

Configuring Tools in config.yaml

Tool Groups

Adding Tools

The `use` Reflection System

Creating Custom Python Tools

Tool with Configuration

Sandbox-Aware Tools

Tool Parameters and Type Hints

Environment Variables in Tools

Tool Visibility and Access Control

Tool Groups

Conditional Tool Loading

Testing Custom Tools

Debugging Tools

Best Practices

Next Steps

MCP Servers

Creating Skills

Configuration

Examples

Overview

Core Concepts

Configuration

Guides

Deployment

​Overview

​Tool Architecture

​Built-in Tools

present_file

ask_clarification

view_image

skill

​Configuring Tools in config.yaml

​Tool Groups

​Adding Tools

​The use Reflection System

​Creating Custom Python Tools

​Tool with Configuration

​Sandbox-Aware Tools

​Tool Parameters and Type Hints

​Environment Variables in Tools

​Tool Visibility and Access Control

​Tool Groups

​Conditional Tool Loading

​Testing Custom Tools

​Debugging Tools

​Best Practices

​Next Steps

MCP Servers

Creating Skills

Configuration

Examples

Overview

Tool Architecture

Built-in Tools

Configuring Tools in config.yaml

Tool Groups

Adding Tools

The `use` Reflection System

Creating Custom Python Tools

Tool with Configuration

Sandbox-Aware Tools

Tool Parameters and Type Hints

Environment Variables in Tools

Tool Visibility and Access Control

Tool Groups

Conditional Tool Loading

Testing Custom Tools

Debugging Tools

Best Practices

Next Steps