How to Use the Bland AI MCP in Google ADK

Q: How do I configure Bland AI inside a Google ADK application?

Install the library, define your StreamableHttpServerParameters with your Vinkius URL, and wrap it in an McpToolset. Pass this toolset into the tools parameter of your LlmAgent.

Q: Can I use Gemini's long context to analyze Bland AI transcripts in Google ADK?

Yes. Use gettranscript to retrieve the full conversation, then pass the raw text to Gemini. The model can analyze hours of voice calls at once thanks to its large token limit.

Run phone campaigns and analyze voice transcripts using Gemini and the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bland AI MCP to Google ADK

Create your Vinkius account to connect Bland AI to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Bland AI with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Place voice calls directly from Google ADK agents

`send_call` initiates an outbound phone call using Bland AI's API, driven by the reasoning capabilities of Gemini. Your enterprise agent can pull customer records from BigQuery, format the prompt, and start a call in a single execution loop. You initialize this by passing `McpToolset` with your Vinkius HTTP URL directly to your `LlmAgent`. The Google ADK handles the transport, making these voice tools available to models with massive context windows.

Extract call logs and transcripts into Vertex AI

`get_transcript` pulls the complete text record of any finished phone conversation for immediate analysis. Your agent can feed this transcript directly into Gemini's 1M+ token context window to extract sentiment, action items, or compliance scores. This integration uses the MCP Server to bridge the gap between live telephony and your Google Cloud infrastructure. You can run batch analysis pipelines that query `list_calls` and feed the results straight into your data warehouse.

Manage active phone agents and voice pathways

`list_agents` returns your entire roster of virtual phone agents, allowing your Google ADK agent to select the correct persona for each task. Once selected, `get_agent` retrieves the configuration details to verify the agent's prompt settings. By using this MCP Server, your enterprise agents can modify conversational flows on the fly. If a call goes off track, the agent can call `stop_call` to end the connection instantly.

Setup guide

Set up Bland AI MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Bland AI tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Bland AI_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Bland AI tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Bland AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Bland AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Bland AI MCP in Google ADK

Install the library, define your `StreamableHttpServerParameters` with your Vinkius URL, and wrap it in an `McpToolset`. Pass this toolset into the `tools` parameter of your `LlmAgent`.

Yes. Use `get_transcript` to retrieve the full conversation, then pass the raw text to Gemini. The model can analyze hours of voice calls at once thanks to its large token limit.

Yes, indirectly. Your agent can read phone numbers or customer profiles from BigQuery, then use `send_call` to contact them, keeping your data pipeline unbroken.

Yes, the ADK supports an optional tool names filter. You can restrict the toolset to only expose `get_transcript` if you want to prevent the agent from making outbound calls.

All phone numbers, voice pathways, and call transcripts are processed within ephemeral V8 isolates. This MCP Server handles the connection with zero-trust architecture, meaning your credentials and call content never persist on Vinkius.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript