How to Use the Freshsales MCP in Google ADK

Q: How do I connect the Freshsales MCP server to Google ADK?

Instantiate an McpToolset using StreamableHttpServerParameters with your Vinkius endpoint. Pass that toolset into the tools array of your LlmAgent.

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

Yes. Use the toolnames argument when setting up the toolset. This prevents the agent from calling createlead if you only want it reading records.

Q: Is my Freshsales pipeline data secure when queried by Google ADK?

When your agent calls listsalesaccounts or listdeals, the financial figures and company names process through an ephemeral V8 Isolate sandbox. Vinkius handles the authorization securely, leaving zero residual data on the server after the request finishes.

Give your Gemini models direct access to Freshsales data using the Google ADK to query deals, leads, and contacts at scale.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshsales MCP to Google ADK

Create your Vinkius account to connect Freshsales 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 Freshsales with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed CRM Data to Gemini

The `list_deals`, `list_leads`, and `list_contacts` tools pull raw sales records straight into Gemini's massive context window. Google ADK lets your agents read thousands of CRM rows and cross-reference them with external datasets like BigQuery in a single reasoning pass. Your agent spots pipeline bottlenecks by comparing the output of these tools against historical data. You get answers based on actual CRM state, not outdated exports or manual spreadsheet uploads.

Filter Freshsales MCP Server Tools

You control exactly what your Google ADK agent can do by passing a `tool_names` filter to the `McpToolset` constructor. If you only want an agent to read data, you expose `get_contact` and `get_lead` while hiding creation endpoints. This restricts the agent's blast radius. When you deploy on Google Cloud, you know the model can only execute the specific CRM operations you explicitly whitelisted during setup.

Map Tasks and Appointments

Tools like `list_appointments`, `list_notes`, and `list_tasks` expose the daily actions of your sales team. The agent fetches these records via HTTP transport and analyzes which activities correlate with closed won deals. You pass the `StreamableHttpServerParameters` to your `LlmAgent` and it handles the rest. The MCP connection stays stable even when pulling heavy pagination loads from the CRM.

Setup guide

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

Instantiate an `McpToolset` using `StreamableHttpServerParameters` with your Vinkius endpoint. Pass that toolset into the `tools` array of your `LlmAgent`.

Yes. Use the `tool_names` argument when setting up the toolset. This prevents the agent from calling `create_lead` if you only want it reading records.

Gemini models feature a massive context window. You can pull extensive output from `list_deals` directly into the prompt for deep cross-referencing with other Google Cloud data.

Yes. The MCP server integrates natively with the ADK, meaning your Vertex-hosted agents can execute CRM queries without custom authentication wrappers.

When your agent calls `list_sales_accounts` or `list_deals`, the financial figures and company names process through an ephemeral V8 Isolate sandbox. Vinkius handles the authorization securely, leaving zero residual data on the server after the request 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