How to Use the Cohere (AI Platform) MCP in Google ADK

Q: Can I use Cohere (AI Platform) tools to filter BigQuery data in Google ADK?

Absolutely, just pass your BigQuery results to the rerankdocuments tool. The output is a clean array that your agent can process without worrying about irrelevant records.

Q: Does Google ADK support tool filtering for Cohere (AI Platform)?

You can use the toolnames argument in your McpToolset to restrict exactly which functions are exposed. This keeps your agent's interface clean and minimizes unnecessary API calls.

Q: How do I handle long-context reasoning with these tools?

Use tokenizetext to verify your input size fits within your Gemini model's limits. This avoids cut-offs during high-volume document processing.

Connect Cohere (AI Platform) to Google ADK to process massive datasets in your enterprise agent flow.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cohere (AI Platform) MCP to Google ADK

Create your Vinkius account to connect Cohere (AI Platform) 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 (AI Platform) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map inputs into classes with Google ADK

Run `classify_inputs` to categorize user queries before they hit your Gemini-based logic. This helps you route tasks efficiently across your Google Cloud infrastructure. `tokenize_text` provides the exact structural count needed for large context windows. You'll avoid hitting limits when processing million-token prompts.

Refine search results using Cohere (AI Platform)

Use `rerank_documents` to sort data extracted from BigQuery. Your agent uses these sorted chunks to build better answers from your existing cloud data. `generate_embeddings` lets you create vector representations for your stored documents. This makes it easier to compare new inputs against your historical database.

Inspect model status via Google ADK

Call `list_models` to see which endpoints are ready for your agent's task. You can programmatically switch between models based on availability and cost. `chat_generation` and `generate_text` handle the heavy lifting for your conversational interfaces. These tools bridge the gap between your cloud data and the final user response.

Setup guide

Set up Cohere (AI Platform) 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 (AI Platform) 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 (AI Platform)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Cohere (AI Platform) 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 (AI Platform) 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 (AI Platform) MCP in Google ADK

It is, because the server uses a standard HTTP transport that the ADK McpToolset handles natively. You just pass the server URL to the toolset and include it in your LlmAgent definitions.

Absolutely, just pass your BigQuery results to the `rerank_documents` tool. The output is a clean array that your agent can process without worrying about irrelevant records.

You can use the tool_names argument in your McpToolset to restrict exactly which functions are exposed. This keeps your agent's interface clean and minimizes unnecessary API calls.

Use `tokenize_text` to verify your input size fits within your Gemini model's limits. This avoids cut-offs during high-volume document processing.

Vinkius enforces a zero-trust policy where every request requires an ephemeral token unique to your session. Your data is processed in a transient sandbox and purged immediately after the tool finishes.

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