How to Use the Nimble CRM MCP in Google ADK

Q: How do I install the Nimble CRM toolset in Google ADK?

You install the package and initialize the McpToolset class with the server's HTTP URL. Pass this toolset to your LlmAgent instance to make all ten MCP tools available to Gemini.

Q: Can Gemini search Nimble CRM contacts using Google ADK?

Yes, the agent can call searchcontacts or listcontacts to find specific people. This lets you combine Gemini's reasoning with your actual customer database.

Q: Does this MCP Server support Nimble CRM pipeline analysis in Google ADK?

Yes, the server provides listpipelines and listdeals to let Gemini check your sales pipeline. The agent reads this data to find deals stuck in specific stages.

Q: Can I restrict which tools my Google ADK agent can access?

Yes, you can pass a toolnames filter to the toolset configuration. This lets you limit the MCP agent to read-only tools like getdeal while blocking write tools.

Build enterprise Google ADK agents that query and update your Nimble CRM pipelines using Gemini's long-context reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nimble CRM MCP to Google ADK

Create your Vinkius account to connect Nimble CRM 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 Nimble CRM with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query contact records using Google ADK

The `list_contacts` tool pulls your entire database of relationships so your Gemini agent can analyze them. The agent combines this contact list with your BigQuery data to find high-value targets. It uses `get_contact` to get specific details for the selected accounts. Once the target is identified, `search_contacts` helps the agent check email addresses and phone numbers. This keeps your team from reaching out to outdated leads or sending duplicate messages.

Map pipelines and track revenue

The `list_pipelines` tool gives your agent a bird's-eye view of your sales stages. Gemini maps every active pipeline, while `list_deals` pulls the associated revenue and close dates. Your Google Cloud infrastructure can then run predictive analysis on your pipeline. When the agent detects a bottleneck, it calls `get_deal` to inspect the stalled opportunity. Analyzing the historical data helps the agent suggest the best path forward for the sales rep.

Manage tasks through this MCP Server

The `list_activities` tool exposes all scheduled tasks, calls, and meetings to your agent. Your agent reads these events to build daily agendas or flag missed deadlines. Calling `get_activity` lets the model check specific task descriptions and assignees. To document progress, the agent uses `add_note_to_contact` to log call outcomes directly into the CRM. Running `get_me` ensures the system operates under the correct user profile and permissions.

Setup guide

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

You install the package and initialize the `McpToolset` class with the server's HTTP URL. Pass this toolset to your `LlmAgent` instance to make all ten MCP tools available to Gemini.

Yes, the agent can call `search_contacts` or `list_contacts` to find specific people. This lets you combine Gemini's reasoning with your actual customer database.

Yes, the server provides `list_pipelines` and `list_deals` to let Gemini check your sales pipeline. The agent reads this data to find deals stuck in specific stages.

Yes, you can pass a `tool_names` filter to the toolset configuration. This lets you limit the MCP agent to read-only tools like `get_deal` while blocking write tools.

Your contacts, activities, and deals are processed through an ephemeral, zero-trust V8 sandbox. Vinkius manages the MCP Server connection securely, ensuring your raw API keys never enter your Google Cloud logs.

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