mcpField
L
lucent

lucent

Local
github.com/beepboop2025Security
Repository

About lucent

Lucent is an ERC-7730 Clear Signing descriptor toolkit and call-scoped preflight service for EVM signing agents. It combines presentation, comprehension, and danger checks, with transaction-bound results that do not authorize execution.

Key features

  1. 01Preflight unsigned EVM calls
  2. 02Audit and grade signing descriptors
  3. 03Assess comprehension and danger risks
  4. 04Check screens against mined transactions
  5. 05Create ERC-8176 attestations

Use cases

  1. 01Preflight a pending transaction before signing
  2. 02Review a descriptor during authoring
  3. 03Check recipient labels against actual transfers
  4. 04Scan a deployed contract before building a call

MCP support

Lucent provides a stdio MCP server with tools for transaction preflight, descriptor checks, signature explanations, and contract scans. Use `preflight_transaction` for pending calls; its result is a presentation assessment, not execution approval.

Configuration

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

mcp.json · Universal config
{
  "mcpServers": {
    "beepboop2025-lucent": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/beepboop2025/lucent-mcp:v0.2.1"
      ]
    }
  }
}
Run commanddocker run -i --rm ghcr.io/beepboop2025/lucent-mcp:v0.2.1

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
ocighcr.io/beepboop2025/lucent-mcp:v0.2.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

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.