How to Use the Conda (Anaconda.org) MCP in Google ADK

Q: How do I configure the Conda (Anaconda.org) MCP Server within my Google ADK agent?

Initialize McpToolset with StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset into the tools parameter of your LlmAgent to let your Gemini model invoke the package tools.

Q: Can I limit which Conda (Anaconda.org) tools my Google ADK agent can execute?

Yes. Use the optional toolnames filter in your McpToolset configuration to restrict access. For example, you can expose only searchcondaforge while blocking user-specific profile modifications.

Give your Google ADK agents direct access to Anaconda package structures and organization channels with zero-config tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Conda (Anaconda.org) MCP to Google ADK

Create your Vinkius account to connect Conda (Anaconda.org) 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 Conda (Anaconda.org) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Anaconda organizations directly to Google ADK

The `list_my_organizations` tool retrieves the exact list of channels your authenticated user belongs to, feeding this structure directly into Google ADK. Your Gemini-powered agent uses this channel list to organize internal software mirrors or manage package distribution pipelines. Because Google ADK handles long contexts, your agent can analyze hundreds of organizational channels at once. It correlates this channel data with your BigQuery datasets to track package usage across your enterprise.

Deep metadata extraction via this MCP Server

The `get_package_details` tool extracts deep metadata, licenses, and dependency trees for any package on Anaconda.org. Your Google ADK agent parses this raw data to ensure compliance with your enterprise software policies. This MCP Server connection lets your agent cross-reference package licensing with your internal databases. The agent flags non-compliant licenses automatically, keeping your software supply chain clean without manual audits.

Search Conda Cloud from Google ADK

The `search_conda_packages` tool queries Anaconda.org directly from your Google ADK agent. Your agent searches for specific binaries and returns structured results, allowing you to automate software builds from your pipeline. You pass the toolset to your LlmAgent constructor to give it instant search access. The agent filters results based on your criteria, selecting the correct package without relying on hardcoded scripts.

Setup guide

Set up Conda (Anaconda.org) 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 Conda (Anaconda.org) 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="Conda (Anaconda.org)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Conda (Anaconda.org) 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 Conda. 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 Conda (Anaconda.org) 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 Conda (Anaconda.org) MCP in Google ADK

Initialize `McpToolset` with `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass this toolset into the `tools` parameter of your `LlmAgent` to let your Gemini model invoke the package tools.

Yes. Use the optional `tool_names` filter in your `McpToolset` configuration to restrict access. For example, you can expose only `search_conda_forge` while blocking user-specific profile modifications.

Gemini models can ingest massive lists of package files returned by `list_package_files`. The agent analyzes thousands of build files in a single turn, finding the exact platform binary you need.

No. This MCP Server focuses on read operations, metadata retrieval, and search tools. Your agent can inspect, search, and list packages, but it cannot upload new binaries.

The server only reads your organization lists, package files, and profile details. All requests route through Vinkius's isolated V8 sandboxes, meaning your private channel names and user profiles are never cached or stored on external servers.

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