MCP Server

The Localpayment MCP Server gives any MCP-compatible AI tool direct access to the live API specification and documentation. Once configured, your AI assistant can discover endpoints, read parameter schemas, search guides, and generate accurate integration code — grounded in the current spec, not in potentially outdated training data.

⚡
Quick start: The Localpayment MCP Server is available at https://docs.localpayment.com/mcp. It is public and requires no authentication.

What is MCP?

Model Context Protocol (MCP) is an open standard that works like a USB port for AI — it gives AI assistants a standardized way to connect to external data sources and tools. Instead of relying on a static, potentially outdated training snapshot of the API, your AI tool queries the live Localpayment documentation in real time.

Connect to the MCP Server

Select your AI tool to get the configuration:

Install in Cursor

Or add manually to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "localpayment": {
      "url": "https://docs.localpayment.com/mcp"
    }
  }
}

Restart Cursor and open the AI chat. The Localpayment tools will be available automatically.

Install in VS Code

Or add manually to your VS Code settings.json or .vscode/mcp.json:

{
  "mcp": {
    "servers": {
      "localpayment": {
        "type": "http",
        "url": "https://docs.localpayment.com/mcp"
      }
    }
  }
}

Requires GitHub Copilot Chat with MCP support enabled.

Add the following to your claude_desktop_config.json:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "localpayment": {
      "url": "https://docs.localpayment.com/mcp"
    }
  }
}

Restart Claude Desktop to apply the configuration.

Run the following command in your terminal:

claude mcp add localpayment --url https://docs.localpayment.com/mcp

⚡
This is the fastest setup option — a single command adds the Localpayment MCP server to your Claude Code project permanently.

The MCP server will be available in all future Claude Code sessions in this project.

Add the following to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "localpayment": {
      "url": "https://docs.localpayment.com/mcp"
    }
  }
}

Restart Windsurf to apply the configuration.

OpenHands is an open-source AI software development platform with native MCP support.

Via the OpenHands UI:

Open OpenHands and go to Settings → MCP.
Add a new server with:
- Transport: Streamable HTTP
- URL: https://docs.localpayment.com/mcp
Save. The Localpayment tools will be available to the agent automatically.

Via config.toml:

[mcp]
[[mcp.servers]]
name = "localpayment"
transport = "streamable_http"
url = "https://docs.localpayment.com/mcp"

OpenCode is an open-source AI coding agent for the terminal with native MCP support.

Add the following to your opencode.jsonc config file (project root or ~/.config/opencode/opencode.jsonc):

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "localpayment": {
      "type": "remote",
      "url": "https://docs.localpayment.com/mcp",
      "enabled": true
    }
  }
}

Once added, the Localpayment MCP tools are automatically available to the LLM alongside built-in tools. Reference them in your prompts: use the localpayment tool to...

ℹ️
OpenCode is open-source (MIT) and supports Claude, OpenAI, Google, and local models. See the OpenCode MCP docs for additional configuration options including per-agent tool management.

Any MCP-compatible tool that supports HTTP transport can connect using:

{
  "mcpServers": {
    "localpayment": {
      "url": "https://docs.localpayment.com/mcp"
    }
  }
}

Refer to your tool's documentation for the exact configuration format.

Available Tools

Once connected, your AI assistant has access to the following tools:

Tool	Description	Example use
`list-endpoints`	Lists all API paths and their HTTP methods with summaries, organized by path	"What endpoints are available for virtual accounts?"
`get-endpoint`	Returns full details for a specific endpoint: parameters, request body, response schemas, and security	"Show me the full spec for the Create Virtual Account endpoint"
`search-endpoints`	Deep search through paths, operations, and component schemas by keyword — use to discover endpoints by capability or data model	"Find all operations related to aliases"
`search`	Searches guide pages by query, returning a list of results with ID, title, and URL	"Find the guide about CVU aliases in Argentina"
`fetch`	Retrieves the complete content of a guide page by ID — use `search` first to obtain the ID	"Get the full content of the Virtual Accounts Overview"

ℹ️
The execute-request tool is not enabled on the Localpayment MCP Server. The server is read-only — it provides access to documentation and spec information, but does not execute API calls on your behalf. To run live requests during development, use Postman Collection or your own HTTP client with Stage credentials.

Verify Your Setup

Once configured, open your AI tool's chat or agent interface and use the following prompt to confirm the MCP server is connected and get a complete overview of the Localpayment API:

Using the Localpayment MCP tools, explore the full API and give me a 
complete overview of everything available: list all endpoints organized 
by product area (PayIns, PayOuts, Virtual Accounts, Treasury/FX, etc.), 
explain what each major feature does, identify which countries are 
supported, and explain the key integration patterns. I want a full map 
of the API as my starting point before building my integration.

Your AI assistant will invoke the MCP tools (list-endpoints, search, fetch) and return a structured summary from the live Localpayment documentation.

💡
The fetch tool requires a guide ID, not a URL. Use search first to find the guide and obtain its ID, then pass that ID to fetch to retrieve the full content. Example: search for "virtual accounts overview" → get ID localpayment/virtual-accounts-overview → fetch with that ID.

Troubleshooting

The MCP server is not connecting

Verify the URL is exactly https://docs.localpayment.com/mcp with no trailing slash variations.
Ensure your editor or tool supports HTTP transport for MCP (as opposed to stdio-only). All configurations on this page use HTTP.
Restart your editor after saving the configuration file.
Check your network connection and confirm you can reach https://docs.localpayment.com in a browser.

The AI assistant is not using the MCP tools

Some editors require you to explicitly enable MCP tools in the chat settings or agent mode.
In Cursor, ensure you are using Agent mode (not Ask mode) for tool calls to be available.
In VS Code with Copilot, verify that the MCP extension is installed and the server appears as connected in the settings.

The tools return outdated or unexpected information

The MCP server reflects the current published version of the Localpayment documentation. If you believe there is a discrepancy, contact [email protected].

Next Steps

Prompt Library

Ready-to-use prompts for building integrations, debugging errors, and generating tests — organized by country and use case.

AI Agents

Deploy the Localpayment Integrator Agent in your preferred AI framework.