Zoho-Crm authentication

This connector is optimized for AI agents. For the data replication connector, see Zoho Crm.

This page documents the authentication and configuration options for the Zoho-Crm agent connector.

Hosted mode (most cases)

In hosted mode, create the connector through the Airbyte Agent CLI or API, then execute operations using the CLI, Python SDK, or API. If you need a step-by-step guide, see the developer quickstart.

OAuth

Use the CLI for hosted OAuth connector creation when possible. It opens the hosted setup flow and avoids passing connector secrets through the command line:

airbyte-agent login
airbyte-agent connectors create --json '{
  "workspace": "<your_workspace_name>",
  "name": "zoho-crm"
}'

For API-first use cases, create a connector with OAuth credentials directly.

credentials fields you need:

Field Name	Type	Required	Description
`client_id`	`str`	Yes	OAuth 2.0 Client ID from Zoho Developer Console
`client_secret`	`str`	Yes	OAuth 2.0 Client Secret from Zoho Developer Console
`refresh_token`	`str`	Yes	OAuth 2.0 Refresh Token (does not expire)

Example request:

curl -X POST "https://api.airbyte.ai/api/v1/integrations/connectors" \
  -H "Authorization: Bearer <YOUR_BEARER_TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{
    "workspace_name": "<WORKSPACE_NAME>",
    "connector_type": "Zoho-Crm",
    "name": "My Zoho-Crm Connector",
    "credentials": {
      "client_id": "<OAuth 2.0 Client ID from Zoho Developer Console>",
      "client_secret": "<OAuth 2.0 Client Secret from Zoho Developer Console>",
      "refresh_token": "<OAuth 2.0 Refresh Token (does not expire)>"
    }
  }'

Token

This authentication method isn't available for this connector.

Execution

After creating the connector, execute operations using the CLI, Python SDK, or API. If your Airbyte client can access multiple organizations, set the default organization with airbyte-agent organizations use, include organization_id in AirbyteAuthConfig, or include X-Organization-Id in raw API calls.

CLI

Authenticate with Airbyte:

airbyte-agent login

Create the connector. The CLI opens the hosted setup flow:

airbyte-agent connectors create --json '{
  "workspace": "<your_workspace_name>",
  "name": "zoho-crm"
}'

Describe the connector to see its supported entities and actions:

airbyte-agent connectors describe --json '{
  "workspace": "<your_workspace_name>",
  "name": "zoho-crm"
}'

Execute an action:

airbyte-agent connectors execute --json '{
  "workspace": "<your_workspace_name>",
  "name": "zoho-crm",
  "entity": "<entity>",
  "action": "<action>",
  "params": {}
}'

Python SDK

The connect() factory returns a fully typed ZohoCrmConnector and reads AIRBYTE_CLIENT_ID / AIRBYTE_CLIENT_SECRET from the environment:

The recommended pattern is build_connector_tools, which gives the agent three tools bound to this connector: inspect_connector, read_skill_docs, and execute. The agent can inspect the connector, read only the skill-doc section it needs, and then execute:

inspect_connector() -> read_skill_docs() -> read_skill_docs(section="...") -> execute(entity, action, params)

Pass section IDs verbatim as the outline lists them, prefix included (actions.<entity>.<action>, not <entity>.<action>); anything else returns an error the agent has to recover from.

The builder names its tools inspect_connector, read_skill_docs, and execute, so the tool sets for more than one connector collide when registered on the same agent. Renaming the callables at registration avoids the collision, but the generated execute guidance still names inspect_connector and read_skill_docs, pointing the model at the wrong tools. Use the agent_tool pattern below instead: it weaves your own names into that guidance.

Pydantic AI
LangChain
OpenAI Agents
FastMCP

Pydantic AI
from airbyte_agent_sdk import build_connector_tools
from pydantic_ai import Agent
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector

connector = connect("zoho-crm", workspace_name="<your_workspace_name>")

tools = build_connector_tools(connector, framework="pydantic_ai")
agent = Agent("openai:gpt-4o", tools=tools.as_list())

LangChain
from airbyte_agent_sdk import build_connector_tools
from langchain_core.tools import StructuredTool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector

connector = connect("zoho-crm", workspace_name="<your_workspace_name>")

tools = build_connector_tools(connector, framework="langchain")
langchain_tools = [
    StructuredTool.from_function(
        coroutine=tool,
        name=tool.__name__,
        description=tool.__doc__,
    )
    for tool in tools.as_list()
]

OpenAI Agents
from airbyte_agent_sdk import build_connector_tools
from agents import Agent, function_tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector

connector = connect("zoho-crm", workspace_name="<your_workspace_name>")

tools = build_connector_tools(connector, framework="openai_agents")
openai_tools = [function_tool(tool, strict_mode=False) for tool in tools.as_list()]

agent = Agent(name="Zoho-Crm Assistant", tools=openai_tools)

FastMCP
from airbyte_agent_sdk import build_connector_tools
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector

connector = connect("zoho-crm", workspace_name="<your_workspace_name>")

mcp = FastMCP("Zoho-Crm Agent")

for tool in build_connector_tools(connector, framework="mcp").as_list():
    mcp.tool(tool)

Custom tool bodies

When you need custom tool bodies — or a framework without native support — use ZohoCrmConnector.agent_tool. Register execute, inspect, and docs together so the agent can fetch connector guidance progressively. Pass the framework explicitly when it has a supported failure strategy:

Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector

connector = connect("zoho-crm", workspace_name="<your_workspace_name>")

agent = Agent("openai:gpt-4o")

@agent.tool_plain
@ZohoCrmConnector.agent_tool(
    framework="pydantic_ai",
    inspect_tool="zoho_crm_inspect",
    docs_tool="zoho_crm_read_docs",
)
async def zoho_crm_execute(entity: str, action: str, params: dict | None = None):
    return await connector.execute(entity, action, params or {})

@agent.tool_plain
@ZohoCrmConnector.agent_tool(framework="pydantic_ai")
async def zoho_crm_inspect():
    return await connector.inspect_connector()

@agent.tool_plain
@ZohoCrmConnector.agent_tool(framework="pydantic_ai")
async def zoho_crm_read_docs(section: str | None = None):
    return await connector.read_skill_docs(section)

Use the same three-function pattern with framework="langchain", "openai_agents", or "mcp" and that framework's registration decorator. Each value translates connector failures into the framework's own signal:

`framework=`	Tool failures surface as
`"pydantic_ai"`	`pydantic_ai.ModelRetry`
`"langchain"`	`langchain_core.tools.ToolException` (set `handle_tool_error=True` to feed it back to the model)
`"openai_agents"`	the failure message returned to the model as the tool result
`"mcp"`	`fastmcp.exceptions.ToolError`
`"none"` (default)	`airbyte_agent_sdk.AirbyteToolError`

On a framework the SDK does not support natively — or in a raw LLM dispatch loop — omit framework= and handle AirbyteToolError yourself:

No framework
from airbyte_agent_sdk import AirbyteToolError
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector

connector = connect("zoho-crm", workspace_name="<your_workspace_name>")

@ZohoCrmConnector.agent_tool(
    inspect_tool="zoho_crm_inspect",
    docs_tool="zoho_crm_read_docs",
)
async def zoho_crm_execute(entity: str, action: str, params: dict | None = None):
    return await connector.execute(entity, action, params or {})

@ZohoCrmConnector.agent_tool()
async def zoho_crm_inspect():
    return await connector.inspect_connector()

@ZohoCrmConnector.agent_tool()
async def zoho_crm_read_docs(section: str | None = None):
    return await connector.read_skill_docs(section)

# Advertise all three to the model, using each function's docstring as its description.
handlers = {
    fn.__name__: fn
    for fn in (zoho_crm_inspect, zoho_crm_read_docs, zoho_crm_execute)
}

# `tool_name` and `tool_args` come from the model's tool call in your dispatch loop.
try:
    tool_result = await handlers[tool_name](**tool_args)
except AirbyteToolError as err:
    tool_result = str(err)  # hand the message back to the model as an errored tool result

Each function's docstring carries the guidance the model needs, so pass it through as the tool description wherever you register it.

Legacy alternatives

These examples are kept for existing integrations. The deprecated ZohoCrmConnector.tool_utils pattern loads the connector's full generated catalog into one broad execute tool description instead of letting the agent read skill docs on demand. For new code, use build_connector_tools or ZohoCrmConnector.agent_tool above.

Pydantic AI
LangChain
OpenAI Agents
FastMCP

Pydantic AI
from pydantic_ai import Agent
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector

connector = connect("zoho-crm", workspace_name="<your_workspace_name>")

agent = Agent("openai:gpt-4o")

@agent.tool_plain
@ZohoCrmConnector.tool_utils
async def zoho_crm_execute(entity: str, action: str, params: dict | None = None):
    return await connector.execute(entity, action, params or {})

LangChain
from langchain_core.tools import tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector

connector = connect("zoho-crm", workspace_name="<your_workspace_name>")

@tool
@ZohoCrmConnector.tool_utils
async def zoho_crm_execute(entity: str, action: str, params: dict | None = None):
    """Execute Zoho-Crm connector operations."""
    result = await connector.execute(entity, action, params or {})
    # connector.execute returns a Pydantic envelope for typed actions; fall back to raw data otherwise.
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

OpenAI Agents
from agents import Agent, function_tool
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector

connector = connect("zoho-crm", workspace_name="<your_workspace_name>")

# strict_mode=False because `params: dict` is permissive and the default strict
# JSON schema rejects objects with additionalProperties.
@function_tool(strict_mode=False)
@ZohoCrmConnector.tool_utils(framework="openai_agents")
async def zoho_crm_execute(entity: str, action: str, params: dict | None = None):
    """Execute Zoho-Crm connector operations."""
    result = await connector.execute(entity, action, params or {})
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

agent = Agent(name="Zoho-Crm Assistant", tools=[zoho_crm_execute])

FastMCP
from fastmcp import FastMCP
from airbyte_agent_sdk import connect
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector

connector = connect("zoho-crm", workspace_name="<your_workspace_name>")

mcp = FastMCP("Zoho-Crm Agent")

@mcp.tool
@ZohoCrmConnector.tool_utils
async def zoho_crm_execute(entity: str, action: str, params: dict | None = None):
    """Execute Zoho-Crm connector operations."""
    result = await connector.execute(entity, action, params or {})
    return result.model_dump(mode="json") if hasattr(result, "model_dump") else result

Or pass credentials explicitly (equivalent, useful when you're not loading them from the environment):

Pydantic AI
LangChain
OpenAI Agents
FastMCP

Pydantic AI
from airbyte_agent_sdk import build_connector_tools
from pydantic_ai import Agent
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = ZohoCrmConnector(
    auth_config=AirbyteAuthConfig(
        workspace_name="<your_workspace_name>",
        organization_id="<your_organization_id>",  # Optional for multi-org clients
        airbyte_client_id="<your-client-id>",
        airbyte_client_secret="<your-client-secret>"
    )
)

tools = build_connector_tools(connector, framework="pydantic_ai")
agent = Agent("openai:gpt-4o", tools=tools.as_list())

LangChain
from airbyte_agent_sdk import build_connector_tools
from langchain_core.tools import StructuredTool
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = ZohoCrmConnector(
    auth_config=AirbyteAuthConfig(
        workspace_name="<your_workspace_name>",
        organization_id="<your_organization_id>",  # Optional for multi-org clients
        airbyte_client_id="<your-client-id>",
        airbyte_client_secret="<your-client-secret>"
    )
)

tools = build_connector_tools(connector, framework="langchain")
langchain_tools = [
    StructuredTool.from_function(
        coroutine=tool,
        name=tool.__name__,
        description=tool.__doc__,
    )
    for tool in tools.as_list()
]

OpenAI Agents
from airbyte_agent_sdk import build_connector_tools
from agents import Agent, function_tool
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = ZohoCrmConnector(
    auth_config=AirbyteAuthConfig(
        workspace_name="<your_workspace_name>",
        organization_id="<your_organization_id>",  # Optional for multi-org clients
        airbyte_client_id="<your-client-id>",
        airbyte_client_secret="<your-client-secret>"
    )
)

tools = build_connector_tools(connector, framework="openai_agents")
openai_tools = [function_tool(tool, strict_mode=False) for tool in tools.as_list()]

agent = Agent(name="Zoho-Crm Assistant", tools=openai_tools)

FastMCP
from airbyte_agent_sdk import build_connector_tools
from fastmcp import FastMCP
from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig

connector = ZohoCrmConnector(
    auth_config=AirbyteAuthConfig(
        workspace_name="<your_workspace_name>",
        organization_id="<your_organization_id>",  # Optional for multi-org clients
        airbyte_client_id="<your-client-id>",
        airbyte_client_secret="<your-client-secret>"
    )
)

mcp = FastMCP("Zoho-Crm Agent")

for tool in build_connector_tools(connector, framework="mcp").as_list():
    mcp.tool(tool)

API

curl -X POST 'https://api.airbyte.ai/api/v1/integrations/connectors/<connector_id>/execute' \
  -H 'Authorization: Bearer <YOUR_BEARER_TOKEN>' \
  -H 'X-Organization-Id: <YOUR_ORGANIZATION_ID>' \
  -H 'Content-Type: application/json' \
  -d '{"entity": "<entity>", "action": "<action>", "params": {}}'

Open source mode

In open source mode, provide API credentials directly to the connector.

OAuth

credentials fields you need:

Field Name	Type	Required	Description
`client_id`	`str`	Yes	OAuth 2.0 Client ID from Zoho Developer Console
`client_secret`	`str`	Yes	OAuth 2.0 Client Secret from Zoho Developer Console
`refresh_token`	`str`	Yes	OAuth 2.0 Refresh Token (does not expire)

Example request:

from airbyte_agent_sdk.connectors.zoho_crm import ZohoCrmConnector
from airbyte_agent_sdk.connectors.zoho_crm.models import ZohoCrmAuthConfig

connector = ZohoCrmConnector(
    auth_config=ZohoCrmAuthConfig(
        client_id="<OAuth 2.0 Client ID from Zoho Developer Console>",
        client_secret="<OAuth 2.0 Client Secret from Zoho Developer Console>",
        refresh_token="<OAuth 2.0 Refresh Token (does not expire)>"
    ),
    dc_region="<The Zoho data center region domain suffix: - com (US) - com.au (AU) - eu (EU) - in (IN) - com.cn (CN) - jp (JP)
>"
)

Token

This authentication method isn't available for this connector.

Configuration

The Zoho-Crm connector also needs these configuration values to construct the base API URL.

Hosted CLI: airbyte-agent connectors create doesn't currently accept these configuration fields directly. For hosted connectors that need these values, create the connector with the hosted API replication_config, then use the CLI for describe and execute operations after creation.
Hosted API: pass these values in the connector creation replication_config.
Open source mode: provide these values with your local connector setup so the connector can build the correct API base URL.

Variable	Type	Required	Default	Description
`dc_region`	`string`	Yes	com	The Zoho data center region domain suffix: - com (US) - com.au (AU) - eu (EU) - in (IN) - com.cn (CN) - jp (JP)

Hosted mode (most cases)​

OAuth​

Token​

Execution​

Custom tool bodies​

Legacy alternatives​

Open source mode​

OAuth​

Token​

Configuration​

Hosted mode (most cases)

OAuth

Token

Execution

Custom tool bodies

Legacy alternatives

Open source mode

OAuth

Token

Configuration