Advertise
MCP.so
Sign In

Investec MCP: Banking API for AI Agents

@Nicolaas0411

Repository

Basic information

Category

Developer Tools

Transports

stdio

Author

Nicolaas0411

About Investec MCP: Banking API for AI Agents

MCP server for the Investec Private Banking API

Investec MCP: Banking API for AI Agents config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "investec-mcp": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "-e",
        "."
      ]
    }
  }
}

Investec MCP: Banking API for AI Agents tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Investec MCP: Banking API for AI Agents?

A Model Context Protocol (MCP) server that integrates with the Investec Open Banking API, enabling AI agents to access banking information and perform transactions such as transfers, payments, and document retrieval. It is designed for developers and users of MCP‑compatible clients (e.g., Claude, Windsurf) who need programmatic access to Investec banking services.

How to use Investec MCP: Banking API for AI Agents?

Install dependencies via uv pip install -e . or build a Docker image with docker build -t investec/mcp. Configure a .env file with Investec API credentials (INVESTEC_CLIENT_ID, INVESTEC_CLIENT_SECRET, INVESTEC_API_KEY) and optionally set TRANSPORT to sse or stdio. Run the server using uv run python src/main.py or docker run --env-file .env -p 8050:8050 investec/mcp. Connect MCP clients by adding a JSON configuration block as shown in the README.

Key features of Investec MCP: Banking API for AI Agents

  • Retrieve all accounts, balances, and transactions (including pending).
  • Manage profiles and beneficiaries.
  • Transfer money between own accounts and pay beneficiaries.
  • Batch multiple transfers and payments.
  • Download account documents by type and date range.

Use cases of Investec MCP: Banking API for AI Agents

  • An AI agent automatically checks account balances and recent transactions.
  • An agent initiates a transfer between the user’s own accounts.
  • A batch payment is sent to multiple beneficiaries from a single command.
  • An agent retrieves and provides supporting documents for a specific account.

Frequently asked questions

1

What are the prerequisites to run the server?

Python 3.12+ is required, along with an Investec Developer account with API credentials. Docker is recommended but not mandatory.

2

How do I choose between SSE and stdio transport?

Set the `TRANSPORT` environment variable to `sse` for serving the MCP server as an API endpoint, or to `stdio` for the MCP client to spawn the server process directly.

3

How do I secure my banking credentials?

Keep the `.env` file secure and never commit it to version control. Use private Docker registries if distributing images, and run the server only on secure, trusted networks. Additional rate limiting is recommended.

4

What tools are available for account information?

The server provides `get_accounts`, `get_account_balance`, `get_account_transactions`, and `get_pending_transactions`.

5

Can I make payments to saved beneficiaries?

Yes, using `pay_beneficiary` (single payment) or `pay_multiple` (batch payments) after configuring the beneficiary via `get_beneficiaries`.

Comments

More Developer Tools MCP servers

Launchdog

Devin Starks

Launch your product from your AI agent. Connect Claude Code, Codex, Cursor or ChatGPT to Launchdog over MCP and your agent drafts the listing, picks a launch week and books it. 50 launches a week, ranked only by human vo

Cronwatch

cronwatchdev

CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.

31

GripForge

gripforgeai

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

1

Modelglass

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

1

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

3
Advertise