Agent SDK reference - Python

pip install claude-agent-sdk

async def query(
    *,
    prompt: str | AsyncIterable[dict[str, Any]],
    options: ClaudeAgentOptions | None = None,
    transport: Transport | None = None
) -> AsyncIterator[Message]

import asyncio
from claude_agent_sdk import query, ClaudeAgentOptions


async def main():
    options = ClaudeAgentOptions(
        system_prompt="You are an expert Python developer",
        permission_mode="acceptEdits",
        cwd="/home/user/project",
    )

    async for message in query(prompt="Create a Python web server", options=options):
        print(message)


asyncio.run(main())

def tool(
    name: str,
    description: str,
    input_schema: type | dict[str, Any],
    annotations: ToolAnnotations | None = None
) -> Callable[[Callable[[Any], Awaitable[dict[str, Any]]]], SdkMcpTool[Any]]

from claude_agent_sdk import tool
from typing import Any


@tool("greet", "Greet a user", {"name": str})
async def greet(args: dict[str, Any]) -> dict[str, Any]:
    return {"content": [{"type": "text", "text": f"Hello, {args['name']}!"}]}

from claude_agent_sdk import tool, ToolAnnotations
from typing import Any


@tool(
    "search",
    "Search the web",
    {"query": str},
    annotations=ToolAnnotations(readOnlyHint=True, openWorldHint=True),
)
async def search(args: dict[str, Any]) -> dict[str, Any]:
    return {"content": [{"type": "text", "text": f"Results for: {args['query']}"}]}

def create_sdk_mcp_server(
    name: str,
    version: str = "1.0.0",
    tools: list[SdkMcpTool[Any]] | None = None
) -> McpSdkServerConfig

from claude_agent_sdk import tool, create_sdk_mcp_server


@tool("add", "Add two numbers", {"a": float, "b": float})
async def add(args):
    return {"content": [{"type": "text", "text": f"Sum: {args['a'] + args['b']}"}]}


@tool("multiply", "Multiply two numbers", {"a": float, "b": float})
async def multiply(args):
    return {"content": [{"type": "text", "text": f"Product: {args['a'] * args['b']}"}]}


calculator = create_sdk_mcp_server(
    name="calculator",
    version="2.0.0",
    tools=[add, multiply],  # Pass decorated functions
)

# Use with Claude
options = ClaudeAgentOptions(
    mcp_servers={"calc": calculator},
    allowed_tools=["mcp__calc__add", "mcp__calc__multiply"],
)

def list_sessions(
    directory: str | None = None,
    limit: int | None = None,
    include_worktrees: bool = True
) -> list[SDKSessionInfo]

from claude_agent_sdk import list_sessions

for session in list_sessions(directory="/path/to/project", limit=10):
    print(f"{session.summary} ({session.session_id})")

def get_session_messages(
    session_id: str,
    directory: str | None = None,
    limit: int | None = None,
    offset: int = 0
) -> list[SessionMessage]

from claude_agent_sdk import list_sessions, get_session_messages

sessions = list_sessions(limit=1)
if sessions:
    messages = get_session_messages(sessions[0].session_id)
    for msg in messages:
        print(f"[{msg.type}] {msg.uuid}")

def get_session_info(
    session_id: str,
    directory: str | None = None,
) -> SDKSessionInfo | None

from claude_agent_sdk import get_session_info

info = get_session_info("550e8400-e29b-41d4-a716-446655440000")
if info:
    print(f"{info.summary} (branch: {info.git_branch}, tag: {info.tag})")

def rename_session(
    session_id: str,
    title: str,
    directory: str | None = None,
) -> None

from claude_agent_sdk import list_sessions, rename_session

sessions = list_sessions(directory="/path/to/project", limit=1)
if sessions:
    rename_session(sessions[0].session_id, "Refactor auth module")

def tag_session(
    session_id: str,
    tag: str | None,
    directory: str | None = None,
) -> None

from claude_agent_sdk import list_sessions, tag_session

# Tag a session
tag_session("550e8400-e29b-41d4-a716-446655440000", "needs-review")

# Later: find all sessions with that tag
for session in list_sessions(directory="/path/to/project"):
    if session.tag == "needs-review":
        print(session.summary)

class ClaudeSDKClient:
    def __init__(self, options: ClaudeAgentOptions | None = None, transport: Transport | None = None)
    async def connect(self, prompt: str | AsyncIterable[dict] | None = None) -> None
    async def query(self, prompt: str | AsyncIterable[dict], session_id: str = "default") -> None
    async def receive_messages(self) -> AsyncIterator[Message]
    async def receive_response(self) -> AsyncIterator[Message]
    async def interrupt(self) -> None
    async def set_permission_mode(self, mode: str) -> None
    async def set_model(self, model: str | None = None) -> None
    async def rewind_files(self, user_message_id: str) -> None
    async def get_mcp_status(self) -> McpStatusResponse
    async def reconnect_mcp_server(self, server_name: str) -> None
    async def toggle_mcp_server(self, server_name: str, enabled: bool) -> None
    async def stop_task(self, task_id: str) -> None
    async def get_server_info(self) -> dict[str, Any] | None
    async def disconnect(self) -> None

async with ClaudeSDKClient() as client:
    await client.query("Hello Claude")
    async for message in client.receive_response():
        print(message)

import asyncio
from claude_agent_sdk import ClaudeSDKClient, AssistantMessage, TextBlock, ResultMessage


async def main():
    async with ClaudeSDKClient() as client:
        # First question
        await client.query("What's the capital of France?")

        # Process response
        async for message in client.receive_response():
            if isinstance(message, AssistantMessage):
                for block in message.content:
                    if isinstance(block, TextBlock):
                        print(f"Claude: {block.text}")

        # Follow-up question - the session retains the previous context
        await client.query("What's the population of that city?")

        async for message in client.receive_response():
            if isinstance(message, AssistantMessage):
                for block in message.content:
                    if isinstance(block, TextBlock):
                        print(f"Claude: {block.text}")

        # Another follow-up - still in the same conversation
        await client.query("What are some famous landmarks there?")

        async for message in client.receive_response():
            if isinstance(message, AssistantMessage):
                for block in message.content:
                    if isinstance(block, TextBlock):
                        print(f"Claude: {block.text}")


asyncio.run(main())

import asyncio
from claude_agent_sdk import ClaudeSDKClient


async def message_stream():
    """Generate messages dynamically."""
    yield {
        "type": "user",
        "message": {"role": "user", "content": "Analyze the following data:"},
    }
    await asyncio.sleep(0.5)
    yield {
        "type": "user",
        "message": {"role": "user", "content": "Temperature: 25°C, Humidity: 60%"},
    }
    await asyncio.sleep(0.5)
    yield {
        "type": "user",
        "message": {"role": "user", "content": "What patterns do you see?"},
    }


async def main():
    async with ClaudeSDKClient() as client:
        # Stream input to Claude
        await client.query(message_stream())

        # Process response
        async for message in client.receive_response():
            print(message)

        # Follow-up in same session
        await client.query("Should we be concerned about these readings?")

        async for message in client.receive_response():
            print(message)


asyncio.run(main())

import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions, ResultMessage


async def interruptible_task():
    options = ClaudeAgentOptions(allowed_tools=["Bash"], permission_mode="acceptEdits")

    async with ClaudeSDKClient(options=options) as client:
        # Start a long-running task
        await client.query("Count from 1 to 100 slowly, using the bash sleep command")

        # Let it run for a bit
        await asyncio.sleep(2)

        # Interrupt the task
        await client.interrupt()
        print("Task interrupted!")

        # Drain the interrupted task's messages (including its ResultMessage)
        async for message in client.receive_response():
            if isinstance(message, ResultMessage):
                print(f"Interrupted task finished with subtype={message.subtype!r}")
                # subtype is "error_during_execution" for interrupted tasks

        # Send a new command
        await client.query("Just say hello instead")

        # Now receive the new response
        async for message in client.receive_response():
            if isinstance(message, ResultMessage) and message.subtype == "success":
                print(f"New result: {message.result}")


asyncio.run(interruptible_task())

from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions
from claude_agent_sdk.types import (
    PermissionResultAllow,
    PermissionResultDeny,
    ToolPermissionContext,
)


async def custom_permission_handler(
    tool_name: str, input_data: dict, context: ToolPermissionContext
) -> PermissionResultAllow | PermissionResultDeny:
    """Custom logic for tool permissions."""

    # Block writes to system directories
    if tool_name == "Write" and input_data.get("file_path", "").startswith("/system/"):
        return PermissionResultDeny(
            message="System directory write not allowed", interrupt=True
        )

    # Redirect sensitive file operations
    if tool_name in ["Write", "Edit"] and "config" in input_data.get("file_path", ""):
        safe_path = f"./sandbox/{input_data['file_path']}"
        return PermissionResultAllow(
            updated_input={**input_data, "file_path": safe_path}
        )

    # Allow everything else
    return PermissionResultAllow(updated_input=input_data)


async def main():
    options = ClaudeAgentOptions(
        can_use_tool=custom_permission_handler, allowed_tools=["Read", "Write", "Edit"]
    )

    async with ClaudeSDKClient(options=options) as client:
        await client.query("Update the system config file")

        async for message in client.receive_response():
            # Will use sandbox path instead
            print(message)


asyncio.run(main())

@dataclass
class SdkMcpTool(Generic[T]):
    name: str
    description: str
    input_schema: type[T] | dict[str, Any]
    handler: Callable[[T], Awaitable[dict[str, Any]]]
    annotations: ToolAnnotations | None = None

from abc import ABC, abstractmethod
from collections.abc import AsyncIterator
from typing import Any


class Transport(ABC):
    @abstractmethod
    async def connect(self) -> None: ...

    @abstractmethod
    async def write(self, data: str) -> None: ...

    @abstractmethod
    def read_messages(self) -> AsyncIterator[dict[str, Any]]: ...

    @abstractmethod
    async def close(self) -> None: ...

    @abstractmethod
    def is_ready(self) -> bool: ...

    @abstractmethod
    async def end_input(self) -> None: ...

@dataclass
class ClaudeAgentOptions:
    tools: list[str] | ToolsPreset | None = None
    allowed_tools: list[str] = field(default_factory=list)
    system_prompt: str | SystemPromptPreset | None = None
    mcp_servers: dict[str, McpServerConfig] | str | Path = field(default_factory=dict)
    strict_mcp_config: bool = False
    permission_mode: PermissionMode | None = None
    continue_conversation: bool = False
    resume: str | None = None
    max_turns: int | None = None
    max_budget_usd: float | None = None
    disallowed_tools: list[str] = field(default_factory=list)
    model: str | None = None
    fallback_model: str | None = None
    betas: list[SdkBeta] = field(default_factory=list)
    output_format: dict[str, Any] | None = None
    permission_prompt_tool_name: str | None = None
    cwd: str | Path | None = None
    cli_path: str | Path | None = None
    settings: str | None = None
    add_dirs: list[str | Path] = field(default_factory=list)
    env: dict[str, str] = field(default_factory=dict)
    extra_args: dict[str, str | None] = field(default_factory=dict)
    max_buffer_size: int | None = None
    debug_stderr: Any = sys.stderr  # Deprecated
    stderr: Callable[[str], None] | None = None
    can_use_tool: CanUseTool | None = None
    hooks: dict[HookEvent, list[HookMatcher]] | None = None
    user: str | None = None
    include_partial_messages: bool = False
    include_hook_events: bool = False
    fork_session: bool = False
    agents: dict[str, AgentDefinition] | None = None
    setting_sources: list[SettingSource] | None = None
    sandbox: SandboxSettings | None = None
    plugins: list[SdkPluginConfig] = field(default_factory=list)
    max_thinking_tokens: int | None = None  # Deprecated: use thinking instead
    thinking: ThinkingConfig | None = None
    effort: EffortLevel | None = None
    enable_file_checkpointing: bool = False
    session_store: SessionStore | None = None
    session_store_flush: SessionStoreFlushMode = "batched"

options = ClaudeAgentOptions(
    env={
        "API_TIMEOUT_MS": "120000",
        "CLAUDE_CODE_MAX_RETRIES": "2",
        "CLAUDE_ASYNC_AGENT_STALL_TIMEOUT_MS": "120000",
    },
)

# Expected dict shape for output_format
{
    "type": "json_schema",
    "schema": {...},  # Your JSON Schema definition
}

class SystemPromptPreset(TypedDict):
    type: Literal["preset"]
    preset: Literal["claude_code"]
    append: NotRequired[str]
    exclude_dynamic_sections: NotRequired[bool]

SettingSource = Literal["user", "project", "local"]

# Do not load user, project, or local settings from disk
from claude_agent_sdk import query, ClaudeAgentOptions

async for message in query(
    prompt="Analyze this code",
    options=ClaudeAgentOptions(
        setting_sources=[]
    ),
):
    print(message)

from claude_agent_sdk import query, ClaudeAgentOptions

async for message in query(
    prompt="Analyze this code",
    options=ClaudeAgentOptions(
        setting_sources=["user", "project", "local"]
    ),
):
    print(message)

# Load only project settings, ignore user and local
async for message in query(
    prompt="Run CI checks",
    options=ClaudeAgentOptions(
        setting_sources=["project"]  # Only .claude/settings.json
    ),
):
    print(message)

# Ensure consistent behavior in CI by excluding local settings
async for message in query(
    prompt="Run tests",
    options=ClaudeAgentOptions(
        setting_sources=["project"],  # Only team-shared settings
        permission_mode="bypassPermissions",
    ),
):
    print(message)

# Define everything programmatically.
# Pass [] to opt out of filesystem setting sources.
async for message in query(
    prompt="Review this PR",
    options=ClaudeAgentOptions(
        setting_sources=[],
        agents={...},
        mcp_servers={...},
        allowed_tools=["Read", "Grep", "Glob"],
    ),
):
    print(message)

# Load project settings to include CLAUDE.md files
async for message in query(
    prompt="Add a new feature following project conventions",
    options=ClaudeAgentOptions(
        system_prompt={
            "type": "preset",
            "preset": "claude_code",  # Use Claude Code's system prompt
        },
        setting_sources=["project"],  # Loads CLAUDE.md from project
        allowed_tools=["Read", "Write", "Edit"],
    ),
):
    print(message)

@dataclass
class AgentDefinition:
    description: str
    prompt: str
    tools: list[str] | None = None
    disallowedTools: list[str] | None = None
    model: str | None = None
    skills: list[str] | None = None
    memory: Literal["user", "project", "local"] | None = None
    mcpServers: list[str | dict[str, Any]] | None = None
    initialPrompt: str | None = None
    maxTurns: int | None = None
    background: bool | None = None
    effort: EffortLevel | int | None = None
    permissionMode: PermissionMode | None = None

PermissionMode = Literal[
    "default",  # Standard permission behavior
    "acceptEdits",  # Auto-accept file edits
    "plan",  # Planning mode - read-only tools only
    "dontAsk",  # Deny anything not pre-approved instead of prompting
    "bypassPermissions",  # Bypass all permission checks (use with caution)
]

EffortLevel = Literal[
    "low",  # Minimal thinking, fastest responses
    "medium",  # Moderate thinking
    "high",  # Deep reasoning
    "xhigh",  # Extended reasoning (Opus 4.7 only; falls back to "high" on other models)
    "max",  # Maximum effort
]

CanUseTool = Callable[
    [str, dict[str, Any], ToolPermissionContext], Awaitable[PermissionResult]
]

@dataclass
class ToolPermissionContext:
    signal: Any | None = None  # Future: abort signal support
    suggestions: list[PermissionUpdate] = field(default_factory=list)
    blocked_path: str | None = None
    decision_reason: str | None = None
    title: str | None = None
    display_name: str | None = None
    description: str | None = None

PermissionResult = PermissionResultAllow | PermissionResultDeny

@dataclass
class PermissionResultAllow:
    behavior: Literal["allow"] = "allow"
    updated_input: dict[str, Any] | None = None
    updated_permissions: list[PermissionUpdate] | None = None

@dataclass
class PermissionResultDeny:
    behavior: Literal["deny"] = "deny"
    message: str = ""
    interrupt: bool = False

@dataclass
class PermissionUpdate:
    type: Literal[
        "addRules",
        "replaceRules",
        "removeRules",
        "setMode",
        "addDirectories",
        "removeDirectories",
    ]
    rules: list[PermissionRuleValue] | None = None
    behavior: Literal["allow", "deny", "ask"] | None = None
    mode: PermissionMode | None = None
    directories: list[str] | None = None
    destination: (
        Literal["userSettings", "projectSettings", "localSettings", "session"] | None
    ) = None

@dataclass
class PermissionRuleValue:
    tool_name: str
    rule_content: str | None = None

class ToolsPreset(TypedDict):
    type: Literal["preset"]
    preset: Literal["claude_code"]

ThinkingDisplay = Literal["summarized", "omitted"]


class ThinkingConfigAdaptive(TypedDict):
    type: Literal["adaptive"]
    display: NotRequired[ThinkingDisplay]


class ThinkingConfigEnabled(TypedDict):
    type: Literal["enabled"]
    budget_tokens: int
    display: NotRequired[ThinkingDisplay]


class ThinkingConfigDisabled(TypedDict):
    type: Literal["disabled"]


ThinkingConfig = ThinkingConfigAdaptive | ThinkingConfigEnabled | ThinkingConfigDisabled

from claude_agent_sdk import ClaudeAgentOptions, ThinkingConfigEnabled

# Option 1: dict literal (recommended, no import needed)
options = ClaudeAgentOptions(thinking={"type": "enabled", "budget_tokens": 20000})

# Option 2: constructor-style (returns a plain dict)
config = ThinkingConfigEnabled(type="enabled", budget_tokens=20000)
print(config["budget_tokens"])  # 20000
# config.budget_tokens would raise AttributeError

SdkBeta = Literal["context-1m-2025-08-07"]

class McpSdkServerConfig(TypedDict):
    type: Literal["sdk"]
    name: str
    instance: Any  # MCP Server instance

McpServerConfig = (
    McpStdioServerConfig | McpSSEServerConfig | McpHttpServerConfig | McpSdkServerConfig
)

class McpStdioServerConfig(TypedDict):
    type: NotRequired[Literal["stdio"]]  # Optional for backwards compatibility
    command: str
    args: NotRequired[list[str]]
    env: NotRequired[dict[str, str]]

class McpSSEServerConfig(TypedDict):
    type: Literal["sse"]
    url: str
    headers: NotRequired[dict[str, str]]

class McpHttpServerConfig(TypedDict):
    type: Literal["http"]
    url: str
    headers: NotRequired[dict[str, str]]

McpServerStatusConfig = (
    McpStdioServerConfig
    | McpSSEServerConfig
    | McpHttpServerConfig
    | McpSdkServerConfigStatus
    | McpClaudeAIProxyServerConfig
)

class McpStatusResponse(TypedDict):
    mcpServers: list[McpServerStatus]

class McpServerStatus(TypedDict):
    name: str
    status: McpServerConnectionStatus  # "connected" | "failed" | "needs-auth" | "pending" | "disabled"
    serverInfo: NotRequired[McpServerInfo]
    error: NotRequired[str]
    config: NotRequired[McpServerStatusConfig]
    scope: NotRequired[str]
    tools: NotRequired[list[McpToolInfo]]

class SdkPluginConfig(TypedDict):
    type: Literal["local"]
    path: str

plugins = [
    {"type": "local", "path": "./my-plugin"},
    {"type": "local", "path": "/absolute/path/to/plugin"},
]

Message = (
    UserMessage
    | AssistantMessage
    | SystemMessage
    | ResultMessage
    | StreamEvent
    | RateLimitEvent
)

@dataclass
class UserMessage:
    content: str | list[ContentBlock]
    uuid: str | None = None
    parent_tool_use_id: str | None = None
    tool_use_result: dict[str, Any] | None = None

@dataclass
class AssistantMessage:
    content: list[ContentBlock]
    model: str
    parent_tool_use_id: str | None = None
    error: AssistantMessageError | None = None
    usage: dict[str, Any] | None = None
    message_id: str | None = None

AssistantMessageError = Literal[
    "authentication_failed",
    "billing_error",
    "rate_limit",
    "invalid_request",
    "server_error",
    "max_output_tokens",
    "unknown",
]

@dataclass
class SystemMessage:
    subtype: str
    data: dict[str, Any]

@dataclass
class ResultMessage:
    subtype: str
    duration_ms: int
    duration_api_ms: int
    is_error: bool
    num_turns: int
    session_id: str
    stop_reason: str | None = None
    total_cost_usd: float | None = None
    usage: dict[str, Any] | None = None
    result: str | None = None
    structured_output: Any = None
    model_usage: dict[str, Any] | None = None
    permission_denials: list[Any] | None = None
    deferred_tool_use: DeferredToolUse | None = None
    errors: list[str] | None = None
    api_error_status: int | None = None
    uuid: str | None = None