How to Use the Chainlit MCP in Google ADK

Q: Can Google ADK agents filter specific Chainlit tools?

You can use the optional toolnames filter when setting up the toolset. This restricts the exposed tools, so your agent only sees liststeps or getstats if that is all it needs.

Feed Chainlit conversational histories directly into Google ADK to analyze massive chat topologies 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 Chainlit MCP to Google ADK

Create your Vinkius account to connect Chainlit 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 Chainlit with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Chainlit threads using this MCP Server

Enterprise agents on Google Cloud thrive on massive datasets. Your Gemini agent queries `list_threads` to grab conversational boundaries inside deployed projects. It then cross-references these user interactions with enterprise data already sitting in BigQuery. Long-context reasoning changes how you audit chat histories. By calling `get_thread`, the agent loads the exact node topologies for an entire session into its massive token window. It analyzes the complete conversational flow without chunking or losing context.

Analyze raw prompts and generation steps

Drilling down into programmatic interactions requires precise tool execution. The agent uses `list_steps` to pull raw prompts and generations from a single thread. It feeds these explicit steps into Vertex AI pipelines for deeper evaluation. You do not have to manually parse complex chat logs anymore. Gemini natively understands the data structures returned by the toolset. It spots anomalies in the prompt chain and flags them for your engineering team.

Track project consumption and user feedback

Managing independent app tracking spaces takes constant oversight. Your agent hits `list_projects` to discover globally configured Chainlit Cloud environments. From there, it pulls traffic boundaries using `get_stats`. User ratings dictate the success of any LLM app. The agent runs `list_feedbacks` to aggregate conversational accuracy scores across deployments. You get a clear view of resource consumption and user satisfaction directly inside your Google Cloud environment.

Setup guide

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

Run pip install google-adk in your terminal. Initialize an McpToolset using StreamableHttpServerParameters with your Vinkius URL, then pass it as tools=[mcp_toolset] to your LlmAgent.

You can use the optional tool_names filter when setting up the toolset. This restricts the exposed tools, so your agent only sees list_steps or get_stats if that is all it needs.

Gemini models can hold over a million tokens in context. When the agent pulls massive conversation payloads via get_thread, it processes the entire node topology at once without losing information.

The Vinkius implementation relies on Streamable HTTP for cloud connections. Your agent communicates with the managed endpoint securely, bypassing the need for local Stdio setups.

Every connection to the managed endpoint requires a single auth token. When your agent pulls explicit conversational accuracy ratings via list_feedbacks, the request runs through an ephemeral, zero-trust sandbox that drops the data immediately after execution.

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