Use Agno to Talk to Your Bitbucket Data via CData Connect AI

Agno is a developer-first Python framework for building AI agents that reason, plan, and take actions using tools. Agno emphasizes a clean, code-driven architecture where the agent runtime remains fully under developer control.

CData Connect AI provides a secure cloud-to-cloud interface for integrating hundreds of enterprise data sources with AI systems. Using Connect AI, live Bitbucket data data can be exposed through a remote MCP endpoint without replication.

In this guide, we build a production-ready Agno agent using the Agno Python SDK. The agent connects to CData Connect AI via MCP using streamable HTTP, dynamically discovers available tools, and invokes them to query live Bitbucket data.

Prerequisites

1. Python 3.9+.
2. A CData Connect AI account – Sign up or log in here.
3. An active Bitbucket account with valid credentials.
4. An LLM API key (for example, OpenAI).

Overview

Here is a high-level overview of the process:

1. Connect: Configure a Bitbucket connection in CData Connect AI.
2. Discover: Use MCP to dynamically retrieve tools exposed by CData Connect AI.
3. Query: Wrap MCP tools as Agno functions and query live Bitbucket data.

Step 1: Configure Bitbucket in CData Connect AI

To enable Agno to query live Bitbucket data, first create a Bitbucket connection in CData Connect AI. This connection is exposed through the CData Remote MCP Server.

1. Log into Connect AI, click Sources, and then click Add Connection.
2. Select "Bitbucket" from the Add Connection panel.
3. Enter the required authentication properties.

   For most queries, you must set the Workspace. The only exception to this is the Workspaces table, which does not require this property to be set, as querying it provides a list of workspace slugs that can be used to set Workspace. To query this table, you must set Schema to 'Information' and execute the query SELECT * FROM Workspaces>.

   Setting Schema to 'Information' displays general information. To connect to Bitbucket, set these parameters:

   • Schema: To show general information about a workspace, such as its users, repositories, and projects, set this to Information. Otherwise, set this to the schema of the repository or project you are querying. To get a full set of available schemas, query the sys_schemas table.
   • Workspace: Required if you are not querying the Workspaces table. This property is not required for querying the Workspaces table, as that query only returns a list of workspace slugs that can be used to set Workspace.

   Authenticating to Bitbucket

   Bitbucket supports OAuth authentication only. To enable this authentication from all OAuth flows, you must create a custom OAuth application, and set AuthScheme to OAuth.

   Be sure to review the Help documentation for the required connection properties for you specific authentication needs (desktop applications, web applications, and headless machines).

   Creating a custom OAuth application

   From your Bitbucket account:

   1. Go to Settings (the gear icon) and select Workspace Settings.
   2. In the Apps and Features section, select OAuth Consumers.
   3. Click Add Consumer.
   4. Enter a name and description for your custom application.
   5. Set the callback URL:
      • For desktop applications and headless machines, use http://localhost:33333 or another port number of your choice. The URI you set here becomes the CallbackURL property.
      • For web applications, set the callback URL to a trusted redirect URL. This URL is the web location the user returns to with the token that verifies that your application has been granted access.
   6. If you plan to use client credentials to authenticate, you must select This is a private consumer. In the driver, you must set AuthScheme to client.
   7. Select which permissions to give your OAuth application. These determine what data you can read and write with it.
   8. To save the new custom application, click Save.
   9. After the application has been saved, you can select it to view its settings. The application's Key and Secret are displayed. Record these for future use. You will use the Key to set the OAuthClientId and the Secret to set the OAuthClientSecret.
   Click Create & Test.
4. Open the Permissions tab and configure user access.

Add a Personal Access Token

A Personal Access Token (PAT) authenticates MCP requests from Agno to CData Connect AI.

1. Open Settings and navigate to Access Tokens.
2. Click Create PAT.
3. Save the generated token securely.

Step 2: Install dependencies and configure environment variables

Install Agno and the MCP adapter dependencies. LangChain is included strictly for MCP tool compatibility.

pip install agno agno-mcp langchain-mcp-adapters

Configure environment variables:

export CDATA_MCP_URL="https://mcp.cloud.cdata.com/mcp"
export CDATA_MCP_AUTH="Base64EncodedCredentials"
export OPENAI_API_KEY="your-openai-key"

Where "Base64EncodedCredentials" is your Connect AI user email and your Personal Access Token joined by a colon (":") and Base64 Encoded: Base64([email protected]:MY_CONNECT_AI_PAT)

Step 3: Connect to CData Connect AI via MCP

Create an MCP client using streamable HTTP. This establishes a secure connection to CData Connect AI.

import os
from langchain_mcp_adapters.client import MultiServerMCPClient

mcp_client = MultiServerMCPClient(
  connections={
    "default": {
      "transport": "streamable_http",
      "url": os.environ["CDATA_MCP_URL"],
      "headers": {
        "Authorization": f"Basic {os.environ['CDATA_MCP_AUTH']}"
      }
    }
  }
)

Step 4: Discover MCP tools

CData Connect AI exposes operations as MCP tools. These are retrieved dynamically at runtime.

langchain_tools = await mcp_client.get_tools()
for tool in langchain_tools:
  print(tool.name)

Step 5: Convert MCP tools to Agno functions

Each MCP tool is wrapped as an Agno function so it can be used by the agent.

NOTE: Agno performs all reasoning, planning, and tool selection.LangChain is used only as a lightweight MCP compatibility layer to consume tools exposed by CData Connect AI.

from agno.tools import Function

def make_tool_caller(lc_tool):
  async def call_tool(**kwargs):
    return await lc_tool.ainvoke(kwargs)
  return call_tool

Step 6: Create an Agno agent and query live Bitbucket data

Agno performs all reasoning, planning, and tool invocation. LangChain plays no role beyond MCP compatibility.

from agno.agent import Agent
from agno.models.openai import OpenAIChat

agent = Agent(
  model=OpenAIChat(
    id="gpt-4o",
    temperature=0.2,
    api_key=os.environ["OPENAI_API_KEY"]
  ),
  tools=agno_tools,
  markdown=True
)

await agent.aprint_response(
  "Show me the top 5 records from the available data source"
)

if __name__ == "__main__":
    asyncio.run(main())

The results below show an Agno agent invoking MCP tools through CData Connect AI and returning live Bitbucket data data.

You can now query live Bitbucket data using natural language through your Agno agent.

---

Get CData Connect AI

To get live data access to hundreds of SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect AI today!