How to Use the Mambu MCP in Pydantic AI

Q: How do I connect Mambu to Pydantic AI?

Install the slim package with MCP support. Initialize an MCPToolset using your Mambu HTTP endpoint, and pass it in the toolsets array to your agent.

Q: Can Pydantic AI modify Mambu records?

No. The available endpoints like getclient and listdepositaccounts are strictly read-only. Your agent cannot issue loans or change balances.

Build reliable banking agents with Pydantic AI, enforcing strict runtime validation on all Mambu MCP data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mambu MCP to Pydantic AI

Create your Vinkius account to connect Mambu 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 Mambu with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Mambu MCP Server queries

The `get_client` and `list_clients` tools return customer profiles that your Pydantic AI agent validates instantly at runtime. If the banking system returns a missing field or an unexpected string instead of an integer, the framework fails loudly before corrupting downstream processes. You get the same strict guarantees with `get_task` and `list_tasks`. Your agent knows exactly what shape the task data will take, preventing hallucinated fields when making decisions about underwriting queues.

Inspect loans and deposits

The `get_loan_account` and `get_deposit_account` tools provide exact balance and interest figures. Pydantic AI forces the LLM to handle this financial data correctly, rejecting any response that violates your predefined schema. When you need to scan multiple accounts, `list_loan_accounts` and `list_deposit_accounts` pull paginated lists. Because the framework is model-agnostic, you can swap between Anthropic or OpenAI while keeping your banking data structures identical.

Audit transactions safely

The `list_transactions` tool fetches historical ledger entries for any specific account. Your agent reads the exact posting dates and amounts, relying on Pydantic to ensure the transaction payloads match expected formats. For customer history, `list_activities` and `list_communications` expose the log of system events and messages. You connect to these MCP endpoints using the unified toolset approach, avoiding deprecated HTTP server classes entirely.

Setup guide

Set up Mambu 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": {
        "mambu-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Mambu 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 Mambu. 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 Mambu 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 Mambu MCP in Pydantic AI

Install the slim package with MCP support. Initialize an `MCPToolset` using your Mambu HTTP endpoint, and pass it in the `toolsets` array to your agent.

No. The available endpoints like `get_client` and `list_deposit_accounts` are strictly read-only. Your agent cannot issue loans or change balances.

The framework throws a validation error immediately. It prevents the agent from processing malformed JSON from `list_transactions` or any other tool.

No. You can use OpenAI, Gemini, Anthropic, or local models. The toolset standardizes the inputs and outputs regardless of which model powers the reasoning.

The integration processes raw banking ledgers and customer communication logs. We run every request inside an isolated sandbox that requires a single endpoint token, stripping authorization details from the logs and destroying the container 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