How to Use the Cohere MCP in Google ADK

Q: How does Google ADK handle Cohere model discovery?

The agent calls the listmodels tool to inspect available models. This returns context lengths, endpoints, and tokenization details, allowing your Google ADK agent to dynamically select the correct model for your specific task.

Connect Google ADK enterprise agents to Cohere models via MCP Server for high-precision document reranking.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cohere MCP to Google ADK

Create your Vinkius account to connect Cohere 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 Cohere with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery Document Ranking via Google ADK

The `rerank` tool allows your Google ADK agent to sort massive datasets pulled from BigQuery. When your agent queries your warehouse, it passes the raw results to `rerank-v3.5` alongside the user query. The agent receives ranked documents with precise relevance scores, letting you pass only the most relevant rows to Gemini's long-context window. You hook this up by passing `McpToolset` inside the `tools` array of your `LlmAgent`. This keeps your enterprise data pipelines clean because the agent filters out noisy SQL results before generating the final report.

Multi-Model Orchestration with Google ADK MCP Server

The `chat` tool lets your Google ADK agent invoke Cohere's Command models directly alongside Vertex AI services. Your agent can run its primary reasoning loops inside Gemini, then call `chat` with `command-r-plus` to handle external tasks or generate alternative text variations. You configure the connection using `StreamableHttpServerParameters` pointing to your Vinkius URL. This setup lets you mix Google's infrastructure with Cohere's fine-tuned chat capabilities in a single Python script.

Vector Generation for Vertex AI Search

The `embed` tool generates high-dimensional vectors directly from your Google ADK agent workflows. The agent takes raw text inputs from Google Cloud Storage, sends them to `embed-v4`, and stores the resulting embedding vectors in your Vertex AI Vector Search database. This workflow uses the standard HTTP transport supported by this MCP toolset. It eliminates the need to write custom API wrappers, letting your Google ADK agent handle vector ingestion natively.

Setup guide

Set up Cohere 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 Cohere 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="Cohere_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Cohere 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 Cohere. 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 Cohere 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 Cohere MCP in Google ADK

Install the package using pip install google-adk. Then, define your toolset using McpToolset(server_params=StreamableHttpServerParameters(url='...')) and pass it to your LlmAgent in the tools list.

Yes. When configuring McpToolset for your Google ADK agent, use the optional tool_names filter. You can restrict the agent to only see rerank or embed, hiding tools like chat or tokenize to prevent unauthorized model execution.

Absolutely. Your Google ADK agent can retrieve unstructured text from BigQuery, pass those texts to the embed tool to generate vector representations, and then store or compare them within your Google Cloud pipeline.

The agent calls the list_models tool to inspect available models. This returns context lengths, endpoints, and tokenization details, allowing your Google ADK agent to dynamically select the correct model for your specific task.

Yes. All text payloads, queries, and documents sent through the server are processed in an ephemeral, zero-trust V8 Isolate sandbox on Vinkius. Your enterprise data never persists on our platform and goes straight to Cohere's API.

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