cubiapi
Customers Bank hosts a remote Model Context Protocol server (the ReadMe generic MCP) that lets AI editors (Cursor, Windsurf, Claude Desktop) browse the API/documentation and execute requests against the embedded-banking platform. The tool set is the ReadMe generic meta-tool surface (spec navigation + HAR execution + docs search), not one tool per API operation.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
list-endpoints— Lists all API paths and their HTTP methods with summaries, organized by path.get-endpoint— Gets detailed information about a specific API endpoint, including security schemes and servers.search-endpoints— Deep search through paths, operations, and parameters to discover relevant endpoints.list-specs— Lists all available OpenAPI specs (the 10 Customers Bank service specifications).execute-request— Executes an API request with a given HAR request object against the live API.search— Searches through documentation with a query, returning matching results.fetch— Gets detailed documentation content by ID returned from the search tool.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.