CrewAI

Build sophisticated multi-agent AI systems where specialized agents collaborate to complete complex business tasks using StackOne’s infrastructure of thousands of turnkey tools, RPC orchestration, and MCP/A2A entry points.

Supported languages: Python.

CrewAI may have compatibility issues with StackOne’s LangChain tools depending on your CrewAI and pydantic versions. If you encounter a ValidationError for BaseTool, check for version updates or use the OpenAI integration instead.

Multi-agent collaboration with business data access
Specialized agents for different business functions
Complex workflow automation with task dependencies
Enhanced error handling and monitoring

Calling actions

Install

# Requires Python 3.10 or higher
# uv or pip

# Using uv (recommended)
uv add 'stackone-ai[mcp]' crewai

# Using pip
pip install 'stackone-ai[mcp]' crewai

# Optional: install with example dependencies
uv add 'stackone-ai[mcp,examples]'
pip install 'stackone-ai[mcp,examples]'

export STACKONE_API_KEY=your_api_key_here

Fetch Tools

Fetch StackOne tools for the linked account and convert them for CrewAI (via LangChain format). By default this fetches every tool enabled for the account — narrow it by passing providers or actions filters (see Tool Filtering):

from stackone_ai import StackOneToolSet

# Get account ID from your app's auth context or StackOne dashboard
account_id = "your-account-id"

# Initialize toolset
toolset = StackOneToolSet()

# Fetch tools dynamically for this account.
# Optionally narrow the fetch with filters:
#   providers=["hibob", "workday"]    — only these connectors
#   actions=["*_list_*", "*_get_*"]   — glob patterns, e.g. read-only actions
tools = toolset.fetch_tools(
    account_ids=[account_id]
).to_langchain()

Run the agent loop

Give the tools to your agents, then run the crew:

from crewai import Agent, Crew, Task

# Create specialized agents
hr_manager = Agent(
    role="HR Manager",
    goal="Manage employee data and handle HR requests",
    backstory="Expert in human resources with experience in employee management",
    tools=tools,
    llm="gpt-5.4",
    verbose=True
)

recruiter = Agent(
    role="Recruiter",
    goal="Find and evaluate candidates for open positions",
    backstory="Experienced recruiter with talent acquisition expertise",
    tools=tools,
    llm="gpt-5.4",
    verbose=True
)

# Create collaborative tasks
employee_analysis_task = Task(
    description="Analyze current employee distribution by department",
    agent=hr_manager,
    expected_output="Employee distribution report with staffing recommendations"
)

# Execute multi-agent crew
crew = Crew(
    agents=[hr_manager, recruiter],
    tasks=[employee_analysis_task],
    verbose=True
)

result = crew.kickoff()
print(result)

Example

Multi-account usage

Each tool execution runs against a specific customer account. Set account IDs once on the toolset, or pass them per request.

# Set accounts on the toolset for all subsequent calls
toolset.set_accounts(["account-123", "account-456"])
tools = toolset.fetch_tools()

# Or pass account IDs per request
tools = toolset.fetch_tools(account_ids=["account-123", "account-456"])

# Loop over customer accounts dynamically
customer_accounts = ["account-1", "account-2", "account-3"]

for account_id in customer_accounts:
    tools = toolset.fetch_tools(
        actions=["workday_list_workers"],
        account_ids=[account_id],
    )
    employee_tool = tools.get_tool("workday_list_workers")
    if employee_tool:
        employees = employee_tool.call()
        print(f"Found {len(employees['data'])} employees")

Error handling

from stackone_ai.models import StackOneError, StackOneAPIError

try:
    result = employee_tool.call(id="employee-123")
    print("Success:", result)
except StackOneAPIError as e:
    print(f"API error: {e.message}")
except StackOneError as e:
    print(f"StackOne error: {e.message}")
except Exception as e:
    print(f"Unexpected error: {e}")

File downloads (binary responses)

Actions that download a file (for example googledrive_unified_download_file, documents_download_file, or any *_unified_download_file) return raw bytes plus metadata, not parsed JSON. The SDK decides from the response Content-Type: JSON is parsed as usual, and anything else is treated as a file download.call() and execute() both return the dict directly (it isn’t wrapped in a result object), so read its values with dict keys like result["content"].

tools = toolset.fetch_tools(actions=["googledrive_*"], account_ids=["your-account-id"])
download = tools.get_tool("googledrive_unified_download_file")

result = download.execute({"id": "file-id"})

# result describes the file. Write the bytes straight to disk:
with open(result["file_name"] or "download.bin", "wb") as f:
    f.write(result["content"])

The returned dict, from both call() and execute():

Key	Type	Description
`content`	`bytes`	Raw file bytes. Not JSON-serializable (see note).
`content_type`	`str`	File MIME type (for example `application/pdf`), or `application/octet-stream`.
`status_code`	`int`	HTTP status of the download response.
`headers`	`dict`	Response headers.
`file_name`	`str \| None`	Filename from `Content-Disposition` (RFC 5987 `filename*` aware), else `None`.

content is raw bytes and is not JSON-serializable. If you forward tool results to an LLM (or anything that re-serializes to JSON), handle or strip the content key. For example, base64-encode it on the LLM-facing path.

Troubleshooting

Execute a tool

Direct execution is useful for testing and debugging. In production, your agent framework handles tool calls automatically.

tools = toolset.fetch_tools(account_ids=["your-account-id"])
employee_tool = tools.get_tool("workday_list_workers")

# call() with keyword arguments
result = employee_tool.call(id="employee-123", include_details=True)
print(result["data"])

# execute() with dictionary payloads
result = employee_tool.execute({"id": "employee-123", "include_details": True})

# execute() with OpenAI-style arguments
payload = {"arguments": {"id": "employee-123"}}
result = employee_tool.execute(payload)

Calling actions

Example

Multi-account usage

Troubleshooting

Execute a tool

Next steps

Observability

Tool Defense

​Calling actions

​Example

​Multi-account usage

​Troubleshooting

​Execute a tool

​Next steps

Observability

Tool Defense

Calling actions

Example

Multi-account usage

Troubleshooting

Execute a tool

Next steps