Agentpay MCP Server

Agents spend money. Most don't know how much, or why, until the session ends and the bill arrives.

Local serverstdioPython

What is the Agentpay MCP server?

Agentpay MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Agents spend money. Most don't know how much, or why, until the session ends and the bill arrives.

Setting it up

The server ships on npm as @romudille/agentpay-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What the assistant can call

Once Agentpay is connected, these are the calls the assistant has available:

  • url_reader — url
  • web_search — query
  • market_snapshot — —
  • token_price — symbol (BTC, ETH, SOL…)
  • gas_tracker — —
  • fear_greed_index — limit (days of history, default 1)
  • token_market_data — token_a, token_b
  • wallet_balance — address, chain (ethereum/stellar)
  • whale_activity — token, min_usd (default 100k)
  • defi_tvl — protocol (optional, e.g. "uniswap")
  • token_security — contract_address, chain
  • open_interest — symbol (BTC, ETH…)

Configuration and credentials

You will need 2 environment variables: AGENTPAY_BASE_KEY, AGENTPAY_MAX_SPEND. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Agentpay.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the agentpay mcp server does with a few real requests.

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Agentpay's toolset — url_reader, web_search, market_snapshot and 11 more — is a fair guide to whether it matches your workflow. It is maintained by romudille-bit; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
url_readerurl
web_searchquery
market_snapshot
token_pricesymbol (BTC, ETH, SOL…)
gas_tracker
fear_greed_indexlimit (days of history, default 1)
token_market_datatoken_a, token_b
wallet_balanceaddress, chain (ethereum/stellar)
whale_activitytoken, min_usd (default 100k)
defi_tvlprotocol (optional, e.g. "uniswap")
token_securitycontract_address, chain
open_interestsymbol (BTC, ETH…)
orderbook_depthsymbol (e.g. ETHUSDT)
funding_ratesasset (optional)

How to install the Agentpay MCP server

```json
{
  "mcpServers": {
    "agentpay": {
      "command": "npx",
      "args": ["-y", "@romudille/agentpay-mcp"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
AGENTPAY_BASE_KEYCredential the server authenticates with.Yes
AGENTPAY_MAX_SPENDConfiguration value read at startup.Optional

Example prompts to try

  • Use Agentpay to url reader.
  • Use Agentpay to web search.
  • Use Agentpay to market snapshot.

Frequently asked questions

It connects Agentpay to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (url_reader, web_search, market_snapshot, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agentpay directly.