How to Use the FastGPT MCP in Google ADK

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

Yes. Use the toolnames filter parameter when initializing McpToolset to expose only search tools like searchdatasetdata while blocking destructive tools.

Q: How does Google ADK handle the long-context capabilities of Gemini with FastGPT?

Gemini can ingest large chunks returned by searchdatasetdata because of its huge context window. The agent pulls detailed context from FastGPT and processes it without hitting token limits.

Feed BigQuery data directly into FastGPT knowledge bases using Google ADK to power long-context Gemini reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FastGPT MCP to Google ADK

Create your Vinkius account to connect FastGPT 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 FastGPT with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-Context Dataset Syncing

`push_dataset_data` writes structured data extracted from BigQuery tables straight into your FastGPT knowledge base. Google ADK coordinates this transfer, allowing Gemini to analyze millions of tokens of context in a single run. It handles large-scale ingestion without breaking a sweat. You can also use `list_dataset_data` to verify what chunks are already indexed. This ensures your Gemini models always read from the latest enterprise data state. No stale records.

Vertex AI FastGPT MCP Server Integration

`search_dataset_data` executes vector searches across your datasets to pull relevant records directly into the Google ADK context window. This bridge lets you query FastGPT without building a custom vector database connector. It works natively with your Vertex AI workflows. The MCP Server handles the connection details behind a single Vinkius token. Your Gemini agents run semantic queries natively alongside their existing Google Cloud tools. It keeps your architecture clean.

Dynamic Dataset Management

`create_dataset` provisions new knowledge bases on the fly when Google ADK detects a new data source in your cloud bucket. This allows autonomous pipelines to organize incoming documents without developer intervention. It just works. If a data source is retired, the agent runs `delete_dataset_data` via the MCP interface to purge stale records instantly. This keeps your search index clean and reduces vector storage costs. No wasted space.

Setup guide

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

Instantiate the McpToolset class with your Vinkius HTTP transport URL. Pass this toolset instance into your LlmAgent constructor to expose all 12 tools to Gemini.

Yes. Use the tool_names filter parameter when initializing McpToolset to expose only search tools like `search_dataset_data` while blocking destructive tools.

Gemini can ingest large chunks returned by `search_dataset_data` because of its huge context window. The agent pulls detailed context from FastGPT and processes it without hitting token limits.

No. Vinkius hosts the FastGPT server in a managed sandbox, so your Google ADK agent connects to a secure, remote endpoint over HTTP.

Your vector embeddings and text records are processed in memory within secure V8 isolates. The data transfers securely to FastGPT, leaving zero traces on Vinkius servers 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