How to Use the iNaturalist MCP in Google ADK

Q: How do I register the iNaturalist MCP Server inside a Google ADK agent?

Pass the Vinkius HTTP URL to StreamableHttpServerParameters and wrap it in McpToolset. Then, include that toolset in the tools list of your LlmAgent.

Q: Can a Google ADK agent process large volumes of iNaturalist taxon records?

Yes. The searchtaxa tool returns detailed lists of scientific names and ranks, which easily fit into the Gemini long-context window for deep taxonomic analysis.

Q: How do I limit which iNaturalist tools the Google ADK agent can access?

Use the optional toolnames filter when initializing your McpToolset to restrict agent access to specific tools like gettaxon.

Feed verified species observations directly into your Gemini workflows via this iNaturalist MCP Server using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect iNaturalist MCP to Google ADK

Create your Vinkius account to connect iNaturalist 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 iNaturalist with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed biodiversity data into Google ADK pipelines

The `get_species_counts` tool aggregates observation counts grouped by taxon for deep analytical workloads. When you connect this tool to your Google ADK agent, Gemini can ingest thousands of species counts directly into its million-token context window. This lets your agent analyze regional biodiversity shifts by comparing live counts against historical datasets stored in BigQuery. The agent handles the raw JSON output natively, mapping species distributions without manual data cleaning.

Map community projects with this MCP Server

The `get_projects` tool fetches community-curated collections of observations based on specific geographic places. Your Google ADK agent executes this tool to discover local conservation initiatives and pull their associated data. You can combine this tool with Google Cloud services to trigger automated workflows when new projects match your research criteria. The ADK handles the underlying HTTP transport, keeping your agent connected to live community data.

Inspect individual observations in Google ADK

The `get_observation` tool retrieves a single, detailed record containing high-resolution photo URLs and observer details. Your Google ADK agent uses this tool to pull raw evidence for specific biological sightings. This allows your agent to cross-reference physical observations with your enterprise databases in Google Cloud. You can restrict which tools are exposed to the agent by applying a tool name filter during the ADK setup.

Setup guide

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

Pass the Vinkius HTTP URL to `StreamableHttpServerParameters` and wrap it in `McpToolset`. Then, include that toolset in the `tools` list of your `LlmAgent`.

Yes. The `search_taxa` tool returns detailed lists of scientific names and ranks, which easily fit into the Gemini long-context window for deep taxonomic analysis.

Use the optional `tool_names` filter when initializing your `McpToolset` to restrict agent access to specific tools like `get_taxon`.

Yes. Vinkius hosts the server in a secure sandbox, allowing your Google Cloud agents to query it over standard HTTPS without exposing your internal network.

Your query terms, such as taxon names and project IDs, are processed in an isolated V8 sandbox. No search history is saved, and all connections are encrypted in transit.

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