Python SDK for Claude Code. See the Claude Code SDK documentation for more information.
pip install claude-code-sdk
Prerequisites:
- Python 3.10+
- Node.js
- Claude Code:
npm install -g @anthropic-ai/claude-code
import anyio
from claude_code_sdk import query
async def main():
async for message in query(prompt="What is 2 + 2?"):
print(message)
anyio.run(main)
query()
is an async function for querying Claude Code. It returns an AsyncIterator
of response messages. See src/claude_code_sdk/query.py.
from claude_code_sdk import query, ClaudeCodeOptions, AssistantMessage, TextBlock
# Simple query
async for message in query(prompt="Hello Claude"):
if isinstance(message, AssistantMessage):
for block in message.content:
if isinstance(block, TextBlock):
print(block.text)
# With options
options = ClaudeCodeOptions(
system_prompt="You are a helpful assistant",
max_turns=1
)
async for message in query(prompt="Tell me a joke", options=options):
print(message)
options = ClaudeCodeOptions(
allowed_tools=["Read", "Write", "Bash"],
permission_mode='acceptEdits' # auto-accept file edits
)
async for message in query(
prompt="Create a hello.py file",
options=options
):
# Process tool use and results
pass
from pathlib import Path
options = ClaudeCodeOptions(
cwd="/path/to/project" # or Path("/path/to/project")
)
ClaudeSDKClient
supports bidirectional, interactive conversations with Claude
Code. See src/claude_code_sdk/client.py.
Unlike query()
, ClaudeSDKClient
additionally enables custom tools and hooks, both of which can be defined as Python functions.
A custom tool is a Python function that you can offer to Claude, for Claude to invoke as needed.
Custom tools are implemented in-process MCP servers that run directly within your Python application, eliminating the need for separate processes that regular MCP servers require.
For an end-to-end example, see MCP Calculator.
from claude_code_sdk import tool, create_sdk_mcp_server, ClaudeCodeOptions, ClaudeSDKClient
# Define a tool using the @tool decorator
@tool("greet", "Greet a user", {"name": str})
async def greet_user(args):
return {
"content": [
{"type": "text", "text": f"Hello, {args['name']}!"}
]
}
# Create an SDK MCP server
server = create_sdk_mcp_server(
name="my-tools",
version="1.0.0",
tools=[greet_user]
)
# Use it with Claude
options = ClaudeCodeOptions(
mcp_servers={"tools": server},
allowed_tools=["mcp__tools__greet"]
)
async with ClaudeSDKClient(options=options) as client:
await client.query("Greet Alice")
# Extract and print response
async for msg in client.receive_response():
print(msg)
- No subprocess management - Runs in the same process as your application
- Better performance - No IPC overhead for tool calls
- Simpler deployment - Single Python process instead of multiple
- Easier debugging - All code runs in the same process
- Type safety - Direct Python function calls with type hints
# BEFORE: External MCP server (separate process)
options = ClaudeCodeOptions(
mcp_servers={
"calculator": {
"type": "stdio",
"command": "python",
"args": ["-m", "calculator_server"]
}
}
)
# AFTER: SDK MCP server (in-process)
from my_tools import add, subtract # Your tool functions
calculator = create_sdk_mcp_server(
name="calculator",
tools=[add, subtract]
)
options = ClaudeCodeOptions(
mcp_servers={"calculator": calculator}
)
You can use both SDK and external MCP servers together:
options = ClaudeCodeOptions(
mcp_servers={
"internal": sdk_server, # In-process SDK server
"external": { # External subprocess server
"type": "stdio",
"command": "external-server"
}
}
)
A hook is a Python function that the Claude Code application (not Claude) invokes at specific points of the Claude agent loop. Hooks can provide deterministic processing and automated feedback for Claude. Read more in Claude Code Hooks Reference.
For more examples, see examples/hooks.py.
from claude_code_sdk import ClaudeCodeOptions, ClaudeSDKClient, HookMatcher
async def check_bash_command(input_data, tool_use_id, context):
tool_name = input_data["tool_name"]
tool_input = input_data["tool_input"]
if tool_name != "Bash":
return {}
command = tool_input.get("command", "")
block_patterns = ["foo.sh"]
for pattern in block_patterns:
if pattern in command:
return {
"hookSpecificOutput": {
"hookEventName": "PreToolUse",
"permissionDecision": "deny",
"permissionDecisionReason": f"Command contains invalid pattern: {pattern}",
}
}
return {}
options = ClaudeCodeOptions(
allowed_tools=["Bash"],
hooks={
"PreToolUse": [
HookMatcher(matcher="Bash", hooks=[check_bash_command]),
],
}
)
async with ClaudeSDKClient(options=options) as client:
# Test 1: Command with forbidden pattern (will be blocked)
await client.query("Run the bash command: ./foo.sh --help")
async for msg in client.receive_response():
print(msg)
print("\n" + "=" * 50 + "\n")
# Test 2: Safe command that should work
await client.query("Run the bash command: echo 'Hello from hooks example!'")
async for msg in client.receive_response():
print(msg)
See src/claude_code_sdk/types.py for complete type definitions:
ClaudeCodeOptions
- Configuration optionsAssistantMessage
,UserMessage
,SystemMessage
,ResultMessage
- Message typesTextBlock
,ToolUseBlock
,ToolResultBlock
- Content blocks
from claude_code_sdk import (
ClaudeSDKError, # Base error
CLINotFoundError, # Claude Code not installed
CLIConnectionError, # Connection issues
ProcessError, # Process failed
CLIJSONDecodeError, # JSON parsing issues
)
try:
async for message in query(prompt="Hello"):
pass
except CLINotFoundError:
print("Please install Claude Code")
except ProcessError as e:
print(f"Process failed with exit code: {e.exit_code}")
except CLIJSONDecodeError as e:
print(f"Failed to parse response: {e}")
See src/claude_code_sdk/_errors.py for all error types.
See the Claude Code documentation for a complete list of available tools.
See examples/quick_start.py for a complete working example.
See examples/streaming_mode.py for comprehensive examples involving ClaudeSDKClient
. You can even run interactive examples in IPython from examples/streaming_mode_ipython.py.
MIT