Connects AI assistants to InFlow for authorized wallet, payment, transaction, policy, and approval operations.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Inflow.
The inflow MCP server gives compatible AI assistants an authorized connection to InFlow, a platform for managing payments, wallets, and digital transactions. Rather than requiring a user to work through the InFlow dashboard for each request, an MCP client can call supported InFlow operations through natural-language instructions.
Typical tasks include checking balances across currencies and wallets, reviewing transaction history, inspecting transaction details, viewing deposit addresses, creating withdrawal addresses, and initiating withdrawals. The connection also exposes account-level controls for transaction policies and approval requests, along with account and profile information.
The inflow MCP server uses the Streamable HTTP transport at https://app.inflowpay.ai/mcp. An MCP client connects to that endpoint and uses the available tools on behalf of an authorized InFlow user. The server does not require a locally installed process when the client supports Streamable HTTP directly.
Authentication uses OAuth 2.1 with PKCE. During setup, the client redirects the user to InFlow to sign in and approve access. After authorization, the client manages the session. The tools exposed to the assistant are determined by the permissions associated with the user’s InFlow account role, so two accounts may not see identical capabilities.
An InFlow account and an MCP-compatible client are required. Add the following remote server endpoint when configuring a client:
Clients with a connector marketplace may allow you to search for InFlow and complete authorization from their settings. For manual configuration, add an HTTP MCP server using the endpoint above. Cursor can connect through mcp-remote, while Visual Studio Code supports adding the endpoint as an HTTP server. Claude supports custom connectors, and Claude Code can add the server with its HTTP transport command.
If a client cannot connect directly to Streamable HTTP, the documented fallback is:
The OAuth flow opens InFlow for login and consent. If authorization stalls, verify that the InFlow account is logged in and consider clearing browser cookies for app.inflowpay.ai before retrying.
The inflow MCP server groups its available operations into these areas:
The exact tool list is permission-dependent. An account role may provide access to only a subset of these areas.
This connection is intended for InFlow accounts and requires authorization through InFlow’s OAuth flow. It is not a general payment provider connector; the supported operations are the InFlow capabilities exposed by the MCP endpoint.
Tool visibility follows account role. If an expected operation is missing, the account may not be authorized for it. The README directs users to InFlow support at support@inflowpay.ai for access issues.
Clients that do not offer a marketplace entry can still use manual configuration. Direct Streamable HTTP support is preferred; mcp-remote provides the documented alternative for clients that need a bridge.
Factual signals from GitHub, npm, and our automated checks — not a rating.
No reviews yet — be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/inflow-2)<a href="https://allmcps.com/mcp/inflow-2"><img src="https://allmcps.com/api/badge/inflow-2?style=directory" alt="Inflow on AllMCPs" /></a>