starling-bank-mcp
MCP server for Starling Bank API integration, enabling AI agents to manage accounts, view transactions, and send payments via natural language.
README
starling-bank-mcp
MCP server for Starling Bank API integration, providing tools to interact with Starling Bank's developer API for account management and transactions.
https://github.com/user-attachments/assets/c2b23c22-bd23-487e-a4f5-c62e02280052
This is a 3rd party integration, and is not affiliated with Starling Bank.
[!WARNING] At time of writing, models make frequent mistakes and are vulnerable to prompt injections. As this MCP server gives the model some control of your bank account, mistakes could be costly. Use with caution and at your own risk.
Installation
Step 1: Create a Starling Bank personal access token. To do this:
- Sign up for a Starling Developers account
- Link your Starling Bank account to your Starling Developer account
- Create the access token
- The token name can be anything, e.g. 'Starling Bank MCP Server Token'
- Select the scopes based on what you want the AI system to be able to access
Keep the token handy, you'll need it in the next step. It'll probably begin something like eyJhbGciOiJQUzI1NiIsInppcCI6IkdaSVAifQ., and be moderately long.
Step 2: Follow the instructions below for your preferred client:
(Optional, Advanced) Step 3: See PAYMENT_SIGNING_SETUP.md if you want to be able to send payments.
Claude Desktop
(Recommended) Alternative: Via manual .mcpb installation
- Find the latest mcpb build in the GitHub Actions history (the top one)
- In the 'Artifacts' section, download the
starling-bank-mcp-mcpbfile - Rename the
.zipfile to.mcpb - Double-click the
.mcpbfile to open with Claude Desktop - Click "Install" and configure with your API key
(Advanced) Alternative: Via JSON configuration
- Install Node.js
- Open Claude Desktop and go to Settings → Developer
- Click "Edit Config" to open your
claude_desktop_config.jsonfile - Add the following configuration to the "mcpServers" section, replacing
eyJhb...with your API key:
{
"mcpServers": {
"starling-bank": {
"command": "npx",
"args": [
"-y",
"starling-bank-mcp"
],
"env": {
"STARLING_BANK_ACCESS_TOKEN": "eyJhb...",
}
}
}
}
- Save the file and restart Claude Desktop
Cursor
(Recommended) Via one-click install
(Advanced) Alternative: Via JSON configuration
Create either a global (~/.cursor/mcp.json) or project-specific (.cursor/mcp.json) configuration file, replacing eyJhb... with your API key:
{
"mcpServers": {
"starling-bank": {
"command": "npx",
"args": ["-y", "starling-bank-mcp"],
"env": {
"STARLING_BANK_ACCESS_TOKEN": "eyJhb..."
}
}
}
}
Cline
Via JSON configuration
- Click the "MCP Servers" icon in the Cline extension
- Click on the "Installed" tab, then the "Configure MCP Servers" button at the bottom
- Add the following configuration to the "mcpServers" section, replacing
eyJhb...with your API key:
{
"mcpServers": {
"starling-bank": {
"type": "stdio",
"command": "npx",
"args": ["-y", "starling-bank-mcp"],
"env": {
"STARLING_BANK_ACCESS_TOKEN": "eyJhb..."
}
}
}
}
Advanced: HTTP Transport
By default, the server uses stdio transport (for Claude Desktop, Cursor, etc.). You can also run it as an HTTP server:
STARLING_BANK_ACCESS_TOKEN=eyJhb... MCP_TRANSPORT=http PORT=3000 npx starling-bank-mcp
The MCP endpoint will be available at http://localhost:3000/mcp.
[!WARNING] The HTTP transport has no authentication. Other processes on your machine—including websites in your browser—could potentially access the endpoint and control your bank account. Only use HTTP transport behind a reverse proxy or in another secured setup.
Contributing
Pull requests are welcomed on GitHub! To get started:
- Install Git and Node.js
- Clone the repository
- Install dependencies with
npm install - Run
npm run testto run tests - Build with
npm run build
Releases
Versions follow the semantic versioning spec.
To release:
- Use
npm version <major | minor | patch>to bump the version - Run
git push --follow-tagsto push with tags - Wait for GitHub Actions to publish to the NPM registry.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.