mcpField
W

weakspot

Local
weakspot.devSecurity
Visit website

About weakspot

Audit Solidity and Rust smart contracts from your editor. Pays per audit in USDC over x402

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "dev-weakspot-weakspot": {
      "command": "npx",
      "args": [
        "-y",
        "weakspot-mcp"
      ],
      "env": {
        "WEAKSPOT_PRIVATE_KEY": "<WEAKSPOT_PRIVATE_KEY>",
        "WEAKSPOT_MAX_USD": "<WEAKSPOT_MAX_USD>",
        "WEAKSPOT_URL": "<WEAKSPOT_URL>",
        "WEAKSPOT_RPC_URL": "<WEAKSPOT_RPC_URL>"
      }
    }
  }
}
Run commandnpx -y weakspot-mcp
Environment variables to set
WEAKSPOT_PRIVATE_KEYSecretPrivate key of a funded Base wallet. This server SPENDS REAL USDC from it with no human in the loop — use a fresh wallet funded with only what you are willing to lose, never a personal or deployer key. Only weakspot_audit needs it; the pricing, status and wallet-status tools work without one.
WEAKSPOT_MAX_USDHard cap in USD on any single audit (default 4, the highest tier). Checked twice: against the tier price, and again against the amount the server actually quotes. An LLM decides when to call the paying tool, so this is the main spend control.
WEAKSPOT_URLBase URL of the Weakspot deployment to use. Defaults to https://weakspot.dev; override to point at staging or a self-hosted instance.
WEAKSPOT_RPC_URLBase RPC endpoint, used only to read the wallet's USDC balance in weakspot_wallet_status. Nothing else needs it.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmweakspot-mcp0.1.1

Tools

4

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
fileCountintegerYesHow many .sol/.rs files to audit.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.