Skip to main content
AgentCash can run as a Model Context Protocol (MCP) server, giving your AI client direct tool access to all AgentCash capabilities: paid API calls, endpoint discovery, wallet management, and authenticated requests. MCP mode is one of three ways to use AgentCash, alongside the CLI and the agent skill.

When to use MCP mode

MCP mode is ideal when your AI client supports MCP and you want:
  • Tool-based access: the agent calls AgentCash tools directly
  • Structured responses: tool responses come back as structured data the agent can parse
  • Automatic integration: the tools are available in the agent’s context with no extra setup

Quick install

The guided installer detects your client:
npx agentcash install
Or install for a specific client:
claude mcp add agentcash --scope user -- npx -y agentcash@latest

Available tools

When running in MCP mode, AgentCash exposes these tools to your agent:
ToolWhat it does
fetchHTTP request with automatic SIWX auth and payment
fetch_with_authDeprecated alias for fetch
get_balanceTotal wallet balance across supported networks
list_accountsPer-network balances, addresses, and deposit links
check_endpoint_schemaProbe pricing and schema without paying
discover_api_endpointsFind all endpoints on an origin
redeem_inviteRedeem an invite code for free USDC

Verify installation

Start a session with your AI client and ask:
What is my AgentCash balance?
The agent should call the get_balance tool and return your total balance. If you later need deposit links or network-specific addresses, the agent should call list_accounts.

Server options

You can pass flags to the MCP server process:
FlagDescription
--verbose / -vEnable debug output on stderr
--quiet / -qSuppress all stderr output
--devUse development endpoints (localhost)