mcp

# @getplexa/mcp — Plexa MCP server

![license: MIT](https://img.shields.io/badge/license-MIT-6ee7a8)
![chains: Base · Polygon · Arbitrum](https://img.shields.io/badge/chains-Base%20%C2%B7%20Polygon%20%C2%B7%20Arbitrum-9aa8f0)
![x402](https://img.shields.io/badge/payments-x402-aab4f0)
![MCP](https://img.shields.io/badge/protocol-MCP-c4b5fd)

A [Model Context Protocol](https://modelcontextprotocol.io) server that gives any MCP client
(Claude Desktop, Cursor, your own agent) two economic-safety tools from **[Plexa](https://getplexa.com)** —
the x402-native **economic-safety layer for trading agents** — paid per call in USDC, no accounts:

| Tool | Wraps | Price | Returns |
|---|---|---|---|
| `plexa_quote` | `POST /v1/quote` | $0.02 | **Executable** fill price under size (not mid/spot), price impact (bps), realizable depth, per-leg route, worst-case slippage, confidence — from canonical on-chain quoters on Base, Polygon & Arbitrum. |
| `plexa_pretrade_check` | `POST /v1/pretrade/check` | $0.05 | Economic-safety verdict `ok` / `caution` / `avoid` + reasons + confidence, plus an executable quote. (Base-only today.) |

It is a **thin client of the public API** (`https://api.getplexa.com`) — it pays a `402` automatically,
signs the USDC authorization **locally** with your wallet, and never sees your key. The liquidity engine
stays behind the API.

---

## Why

A generic wallet guard answers *"can I sign this transaction?"*. It can't answer the **economic**
question an automated trader actually needs: *what price will this swap really fill at under my size,
and is this token a trap (rug / honeypot / thin liquidity)?* Plexa answers both. This package puts those
answers one tool-call away inside any MCP-speaking agent.

---

## Install

Nothing to install — point your MCP client at the package via `npx`. It is fetched and run on demand.

### Claude Desktop

Add to `claude_desktop_config.json` (**Settings → Developer → Edit Config**):

```json
{
  "mcpServers": {
    "plexa": {
      "command": "npx",
      "args": ["-y", "@getplexa/mcp"],
      "env": {
        "PLEXA_BASE_URL": "https://api.getplexa.com",
        "AGENT_WALLET_KEY": "0x<your funded wallet private key>",
        "CHAIN": "base"
      }
    }
  }
}
```

### Cursor

Add to `~/.cursor/mcp.json` (or **Settings → MCP → Add**) — the same `mcpServers` block as above.

Restart the client. You should see the `plexa_quote` and `plexa_pretrade_check` tools available.

---

## Configuration

All configuration is via environment variables (set in the `env` block of your MCP config):

| Variable | Default | Notes |
|---|---|---|
| `PLEXA_BASE_URL` | `https://api.getplexa.com` | The public API. The real URL — not a secret. |
| `AGENT_WALLET_KEY` | *(none)* | **Required to pay.** Funded wallet private key — pays per call and signs locally. Plexa never receives it. Without it, tools return a clear `402`. |
| `CHAIN` | `base` | `base` \| `polygon` \| `arbitrum`. The chain your wallet is funded on; quotes and payment default to it. `plexa_pretrade_check` is Base-only today. |

**Funding.** Use a **dedicated, low-balance wallet** with a little USDC on `CHAIN` to pay per call
(quotes $0.02, checks $0.05). The wallet signs an EIP-3009 USDC authorization per request; Plexa returns
the result only after the payment settles on-chain (**settle-before-serve**).

> Your key is a secret. Prefer your MCP client's secret storage if it has one. Never commit it.

---

## How payment works (x402 in MCP)

MCP has no native payment. This server acts as an **x402 client**: it wraps `fetch`, so when Plexa
replies `402 Payment Required` it reads the payment requirements, signs a USDC authorization with your
wallet (locally), and retries. The signed authorization is the only thing that leaves your machine —
**never the key**. Payment is made on `CHAIN`, so you fund **one wallet on one chain**.

If no `AGENT_WALLET_KEY` is set, the tools return an honest `402` error explaining a funded wallet is
needed — they never fabricate a result.

---

## Example

Once configured, just ask your agent naturally — it will call the tools:

> *"Before I buy this token `0x…` on Base, check it with Plexa and get me an executable quote for $500."*

The agent calls `plexa_pretrade_check` (verdict + reasons) and `plexa_quote` (executable price under
$500), pays $0.05 + $0.02 in USDC automatically, and answers with real on-chain economics.

---

## Notes

- **Client-only.** Talks to the public Plexa API over HTTPS. No service internals ship in this package.
- **Honest failures.** A non-2xx response or a network error becomes a loud tool error — never a
  clean-looking empty result. An agent can always tell a failure from a pass.
- Built on the official [`@modelcontextprotocol/sdk`](https://github.com/modelcontextprotocol) +
  [x402](https://x402.org).

## License

MIT — see [LICENSE](./LICENSE).

Questions: **[support@getplexa.com](mailto:support@getplexa.com)** · **[getplexa.com](https://getplexa.com)**

> Informational on-chain data and heuristic economic signals, **not financial advice**. Absence of flags
> is not a guarantee of safety. Verify independently before trading.