How to Use the First Principles Prover MCP in Google ADK

Q: How do I register the First Principles Prover toolset in Google ADK?

Install the package using pip install google-adk. Create an instance of McpToolset pointing to your Vinkius HTTP server URL, and pass it directly to your LlmAgent in the tools list.

Q: Can I limit Google ADK to only use the First Principles Prover tool?

Yes. Use the optional toolnames filter when initializing your McpToolset to expose only the validatefirstprinciples tool. This prevents the agent from getting distracted by other tools during strict reasoning tasks.

Q: How does the 6-pivot trap work inside Gemini?

The validatefirstprinciples tool forces the model through six distinct checks: discarding analogies, isolating fundamental truths, deconstructing assumptions, building from scratch, generating axiomatic proof, and purging jargon. If any step fails, the tool rejects the output.

Force Gemini models in your Google ADK pipelines to drop lazy analogies and reason from physical and logical axioms.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect First Principles Prover MCP to Google ADK

Create your Vinkius account to connect First Principles Prover 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 First Principles Prover with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deep axiomatic reasoning for long-context Gemini agents

The `validate_first_principles` tool uses Gemini's million-token context window to analyze massive engineering specs for logical flaws. It forces the model to ignore industry templates and derive solutions strictly from physical and mathematical axioms. Look, you don't want your agent copy-pasting generic system architectures. Here's the thing: this tool strips out the fluff and ensures that every step of a complex, multi-page proposal is grounded in fundamental truth.

Connect BigQuery data to the Google ADK MCP Server

The `validate_first_principles` tool checks the query logic and data assumptions of your BigQuery datasets before they pollute downstream tables. Feed raw data from BigQuery directly into this MCP Server and run it through the 6-pivot validation trap. You can set up a toolset filtering schema using the `tool_names` parameter to isolate this validation step. It keeps your data pipelines logically sound and mathematically proven without manual auditing.

Validate complex logic across enterprise vertex pipelines

The `validate_first_principles` tool runs within your standard Vertex AI agent workflows to enforce strict reasoning standards. It intercepts model outputs, checks them against the six cognitive pivots, and rejects any response containing analogical jargon. This process guarantees that the decisions your enterprise agents make are based on hard logic rather than patterns picked up from generic web scrapes. It is the fastest way to keep your production models on a tight mathematical leash.

Setup guide

Set up First Principles Prover 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 First Principles Prover 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="First Principles Prover_agent",
    model="gemini-2.0-flash",
    instruction="You have access to First Principles Prover 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 First Principles Prover. 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 First Principles Prover 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 First Principles Prover MCP in Google ADK

Install the package using `pip install google-adk`. Create an instance of `McpToolset` pointing to your Vinkius HTTP server URL, and pass it directly to your `LlmAgent` in the tools list.

Yes. Use the optional `tool_names` filter when initializing your `McpToolset` to expose only the `validate_first_principles` tool. This prevents the agent from getting distracted by other tools during strict reasoning tasks.

The hosted Vinkius marketplace uses streamable HTTP endpoints for this MCP Server, but the Google ADK framework handles this transport natively. You do not need to configure stdio pipes manually.

The `validate_first_principles` tool forces the model through six distinct checks: discarding analogies, isolating fundamental truths, deconstructing assumptions, building from scratch, generating axiomatic proof, and purging jargon. If any step fails, the tool rejects the output.

Yes. Your structured datasets and query propositions are transmitted over TLS directly to an ephemeral, single-tenant V8 sandbox. The server processes the data in memory, performs the validation, and discards all inputs immediately upon returning the result.

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