How to Use the Galxe MCP in Pydantic AI

Type-safe Galxe automation for Web3 communities using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Galxe MCP to Pydantic AI

Create your Vinkius account to connect Galxe to Pydantic AI 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 Galxe with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Validation for Quest Eligibility

Web3 community tools often return messy JSON. If you are building an agent to verify user tasks, you cannot afford silent failures where a user gets approved by mistake. Pydantic AI forces every response from this MCP Server into a strict schema. When your agent runs `check_quest_eligibility` or `check_credential_eligibility`, the framework validates the output instantly. If the API structure changes or returns an unexpected null value, the agent fails loudly with a validation error instead of hallucinating a successful check.

Type-Safe Leaderboard Extraction

Pulling ranking data requires precision. You want exact integers for points and strings for wallet addresses, not whatever loose types a standard LLM decides to invent. The agent executes `get_space_leaderboard` and `get_starboard_leaderboard`, passing the raw data through your defined Pydantic models. You get a clean, validated Python object back. This means your downstream scripts won't crash when trying to parse user scores.

Reliable Credential Mutations

Writing data back to Galxe is where things get risky. You need absolute certainty that the payload matches what the server expects before the agent fires off the request. By using the `mutate_credential_items` tool through this MCP Server setup, your agent validates the input parameters before the network call even happens. You can also fetch the current state with `get_quest` beforehand, ensuring the agent has perfect context before making any state changes.

Setup guide

Set up Galxe MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "galxe-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Galxe tools.",
)

result = await agent.run("List recent Galxe transactions")
print(result.output)

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 Galxe. 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 Galxe 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 Galxe MCP in Pydantic AI

Install the slim package with MCP support. Initialize an MCPToolset with your HTTP URL and pass it to your agent's toolsets parameter.

Basic scripts break when API responses drift. Pydantic AI validates every Galxe response against strict models, so your agent crashes predictably instead of making bad decisions based on malformed data.

Yes. The framework is model-agnostic. You can route Galxe data through OpenAI, Anthropic, or a local Llama model while keeping the exact same type-safe tool execution.

The old MCPServerHTTP class is deprecated. You must use the unified MCPToolset approach to connect the server to your agent.

The MCP Server transmits wallet addresses, loyalty points, and task completion statuses. Pydantic AI keeps this data in memory only for the duration of the validation and agent run, meaning you control exactly where these identity markers get stored.

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