How to Use the Humanloop (LLM Prompt Management API) MCP in Google ADK

Q: How do I connect the Humanloop (LLM Prompt Management API) MCP Server to my Google ADK agent?

Install google-adk and define a McpToolset pointing to your Vinkius HTTP endpoint for this MCP Server. Pass this toolset into the LlmAgent constructor to give Gemini direct access to your prompt registry.

Q: Can Gemini handle streaming prompts with Humanloop (LLM Prompt Management API) and Google ADK?

Yes, the agent invokes callpromptstream to receive real-time token streams. This works natively with Gemini's streaming capabilities, keeping response latency to a minimum in your Google ADK applications.

Q: How does Humanloop (LLM Prompt Management API) assist with BigQuery workflows in Google ADK?

Your agent can use getprompt to load templates designed for SQL generation or data analysis. It then populates these templates with active BigQuery schemas before running the model.

Q: What tools are available to update prompt configurations in this environment?

Your agent can use upsertprompt to edit configurations and updatepromptversion to change descriptions. This lets you manage prompt metadata directly from your automated Python scripts.

Manage your Humanloop prompt configurations directly from Gemini-powered agents built with the Google ADK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Humanloop (LLM Prompt Management API) MCP to Google ADK

Create your Vinkius account to connect Humanloop (LLM Prompt Management API) 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 Humanloop (LLM Prompt Management API) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch templates for Google ADK long-context runs

The `get_prompt` tool retrieves specific prompt details and templates to feed into Gemini's massive 1M+ token context window. Your Google ADK agent pulls structured instructions dynamically rather than hardcoding long text blocks into your Python files. By running `list_prompts`, your agent scans your entire organization's prompt inventory to find the exact template needed for a specific task. This keeps your Gemini workflows modular, pulling only the relevant context when executing complex reasoning steps over BigQuery datasets.

Track Gemini outputs using this MCP Server

The `update_monitoring` tool configures active evaluators on your prompt configurations to track model outputs. Your Google ADK agent uses this to toggle automated checks on Gemini's performance during live execution. When your agent processes a run, it calls `log_to_prompt` to record the exact input parameters and generated text. This ensures your enterprise telemetry is preserved in Humanloop, making it easy to run side-by-side comparisons with your historical Vertex AI runs.

Manage enterprise environments from Gemini agents

The `list_prompt_environments` tool displays all environment targets and their currently active prompt versions. Your Google ADK agent checks this data to ensure it runs the correct prompt version for your current GCP deployment stage. If a prompt requires an update, the agent runs `deploy_prompt` to promote a new configuration to production. This decouples prompt changes from your Google Cloud deployment pipelines, letting product teams tweak prompts without triggering a full container rebuild.

Setup guide

Set up Humanloop (LLM Prompt Management API) 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 Humanloop (LLM Prompt Management API) 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="Humanloop (LLM Prompt Management API)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Humanloop (LLM Prompt Management API) 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 Humanloop. 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 Humanloop (LLM Prompt Management API) 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 Humanloop (LLM Prompt Management API) MCP in Google ADK

Install `google-adk` and define a `McpToolset` pointing to your Vinkius HTTP endpoint for this MCP Server. Pass this toolset into the `LlmAgent` constructor to give Gemini direct access to your prompt registry.

Yes, the agent invokes `call_prompt_stream` to receive real-time token streams. This works natively with Gemini's streaming capabilities, keeping response latency to a minimum in your Google ADK applications.

Your agent can use `get_prompt` to load templates designed for SQL generation or data analysis. It then populates these templates with active BigQuery schemas before running the model.

Your agent can use `upsert_prompt` to edit configurations and `update_prompt_version` to change descriptions. This lets you manage prompt metadata directly from your automated Python scripts.

All prompt configurations, version histories, and execution logs are encrypted in transit using TLS 1.3. This MCP Server processes these requests in isolated, zero-trust sandboxes that destroy all state 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