4,000+ servers built on vurb.ts
Vinkius

Roboflow MCP Server for Google ADKGive Google ADK instant access to 29 tools to Add Projects To Folder, Auto Label, Cancel Training, and more

MCP Inspector GDPR Free for Subscribers

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Roboflow as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Ask AI about this MCP Server for Google ADK

The Roboflow MCP Server for Google ADK is a standout in the Developer Tools category — giving your AI agent 29 tools to work with, ready to go from day one.

Built for AI Agents by Vinkius

Vinkius delivers Streamable HTTP and SSE to any MCP client

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
python
from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="roboflow_agent",
    instruction=(
        "You help users interact with Roboflow "
        "using 29 available tools."
    ),
    tools=[mcp_tools],
)
Roboflow
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Roboflow MCP Server

Connect Roboflow to your AI agent to streamline your computer vision pipeline. From dataset management to model training and inference, handle your entire CV lifecycle through natural language.

Google ADK natively supports Roboflow as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 29 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

  • Workspace & Project Management — List projects, create new ones, or fork from Roboflow Universe to jumpstart your development.
  • Dataset Operations — Upload images (via URL or Base64), manage versions, and download datasets in various formats like COCO or YOLO.
  • Model Training — Start training runs, monitor results, and retrieve precise performance metrics (mAP, precision, recall) for any version.
  • Image Search — Search and filter images within your workspace to audit your data and improve model accuracy.
  • Inference & Results — Run inference on images and retrieve results to verify model behavior in real-time.

The Roboflow MCP Server exposes 29 tools through the Vinkius. Connect it to Google ADK in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 29 Roboflow tools available for Google ADK

When Google ADK connects to Roboflow through Vinkius, your AI agent gets direct access to every tool listed below — spanning computer-vision, dataset-management, model-training, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.

add

Add projects to folder on Roboflow

Add projects to a folder (Enterprise)

auto

Auto label on Roboflow

Start an auto-labeling job using foundation models

cancel

Cancel training on Roboflow

Cancel an active training job

create

Create annotation job on Roboflow

Assign a batch of images to a labeler and reviewer

create

Create folder on Roboflow

Create a project folder (Enterprise)

create

Create project on Roboflow

Create a new project in a workspace

delete

Delete images on Roboflow

Delete multiple images from a project

delete

Delete project on Roboflow

Delete a project or version (moves to Trash)

download

Download dataset on Roboflow

Retrieve a download link for a zipped dataset in a specific format

fork

Fork universe project on Roboflow

Fork a public project from Roboflow Universe

get

Get async task on Roboflow

Track long-running operations like forking or large exports

get

Get dataset health on Roboflow

Check dataset health (class distribution, missing annotations, etc)

get

Get image on Roboflow

Get details for a specific image

get

Get project on Roboflow

Get project details, metadata, and versions

get

Get root on Roboflow

Verify authentication and retrieve default workspace

get

Get training results on Roboflow

Retrieve metrics and status for a version training run

get

Get version on Roboflow

Retrieve metadata for a specific dataset version

list

List folders on Roboflow

List project folders in a workspace (Enterprise)

list

List trash on Roboflow

List items in the workspace trash

list

List workspace projects on Roboflow

List information about a workspace and its projects

manage

Manage image tags on Roboflow

Add, remove, or set tags on an image

restore

Restore trash on Roboflow

Restore an item from the trash

run

Run inference on Roboflow

Run inference on an image using hosted models

search

Search project images on Roboflow

Search and filter images within a specific project

search

Search workspace images on Roboflow

Search and filter images within a workspace

start

Start training on Roboflow

Start training a model on a dataset version

stop

Stop training on Roboflow

Early stop an active training job

upload

Upload annotation on Roboflow

Attach an annotation file to an existing image

upload

Upload image on Roboflow

Upload an image to a project

Connect Roboflow to Google ADK via MCP

Follow these steps to wire Roboflow into Google ADK. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.

01

Install Google ADK

Run pip install google-adk
02

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token
03

Create the agent

Save the code above and integrate into your ADK workflow
04

Explore tools

The agent will discover 29 tools from Roboflow via MCP

Why Use Google ADK with the Roboflow MCP Server

Google ADK provides unique advantages when paired with Roboflow through the Model Context Protocol.

01

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

02

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Roboflow

03

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

04

Seamless integration with Google Cloud services means you can combine Roboflow tools with BigQuery, Vertex AI, and Cloud Functions

Roboflow + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Roboflow MCP Server delivers measurable value.

01

Enterprise data agents: ADK agents query Roboflow and cross-reference results with internal databases for comprehensive analysis

02

Multi-modal workflows: combine Roboflow tool responses with Gemini's vision and language capabilities in a single agent

03

Automated compliance checks: schedule ADK agents to query Roboflow regularly and flag policy violations or configuration drift

04

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Roboflow

Example Prompts for Roboflow in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Roboflow immediately.

01

"List all projects in my Roboflow workspace 'industrial-safety'."

02

"Upload this image URL to the 'Hard Hat Detection' project in workspace 'industrial-safety'."

03

"Show me the training metrics for version 5 of the 'Forklift Tracking' project."

Troubleshooting Roboflow MCP Server with Google ADK

Common issues when connecting Roboflow to Google ADK through Vinkius, and how to resolve them.

01

McpToolset not found

Update: pip install --upgrade google-adk

Roboflow + Google ADK FAQ

Common questions about integrating Roboflow MCP Server with Google ADK.

01

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.
02

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.
03

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.

Explore More MCP Servers

View all →