mcpField
A
aikido-mcp

aikido-mcp

Local
github.com/BajuzjefeSecurity2Updated 35w ago

About aikido-mcp

aikido-mcp is an MCP server for security analysis of Aiken smart contracts on Cardano. It lets MCP-compatible AI assistants run scans and inspect vulnerability rules and explanations during development.

Key features

  1. 01Scan Aiken projects for vulnerabilities
  2. 02Filter findings by severity
  3. 03Run incremental scans from a Git ref
  4. 04List 75 security detectors
  5. 05Explain detectors and search CWC

Use cases

  1. 01Scan an Aiken project during development
  2. 02Limit scan results to chosen severity
  3. 03Review security rules by category
  4. 04Look up a Cardano weakness classification

MCP support

The server exposes four tools: project analysis, detector listing, detector explanations, and Cardano Weakness Classification lookup. Analysis invokes the aikido binary; CWC lookup uses a static registry.

Configuration

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

mcp.json · Universal config
{
"mcpServers": {
"bajuzjefe-aikido": {
"command": "npx",
"args": [
"-y",
"aikido-mcp"
],
"env": {
"AIKIDO_BINARY": "<AIKIDO_BINARY>"
}
}
}
}
Run commandnpx -y aikido-mcp
Environment variables to set
AIKIDO_BINARYOptional path to the aikido binary (auto-detected if not set)

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
npmaikido-mcp0.1.1

Tools

4

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
diffstringNoGit ref for incremental analysis — only report findings in changed files
configstringNoPath to custom .aikido.toml config file
static_onlybooleanNoSkip multi-lane orchestration (faster but less thorough)
min_severityenumNoMinimum severity threshold to reportinfo | low | medium | high | critical
project_pathstringYesPath to the Aiken project directory (must contain aiken.toml)

Details

From the project README

aikido-mcp

MCP server for Aikido — security analysis for Aiken smart contracts (Cardano).

Lets any MCP-compatible AI assistant (Claude Code, Cursor, Windsurf) run security scans on Aiken projects inline during development.

Setup

Claude Code

Add to ~/.claude/settings.json:

{
  "mcpServers": {
    "aikido": {
      "command": "npx",
      "args": ["-y", "aikido-mcp"]
    }
  }
}
Cursor / Windsurf

Add to .cursor/mcp.json or equivalent:

{
  "mcpServers": {
    "aikido": {
      "command": "npx",
      "args": ["-y", "aikido-mcp"]
    }
  }
}
Prerequisites

The aikido-aiken binary must be available. Install via:

npm install -g aikido-aiken

Or set AIKIDO_BINARY env var to point to the binary.

Tools

aikido_analyze

Scan an Aiken project for security vulnerabilities.

ParameterTypeRequiredDescription
project_pathstringyesPath to Aiken project (must contain aiken.toml)
min_severityenumnoMinimum severity: info, low, medium, high, critical
static_onlybooleannoSkip multi-lane analysis for speed
diffstringnoGit ref for incremental analysis
configstringnoPath to .aikido.toml config
aikido_list_rules

List all 75 detectors with severity, category, CWE mapping, and tier.

ParameterTypeRequiredDescription
severityenumnoFilter by minimum severity
categorystringnoFilter by category
aikido_explain

Detailed explanation of a specific detector.

ParameterTypeRequiredDescription
detectorstringyesDetector name (e.g., missing-signature-check)
aikido_cwc_lookup

Search the Cardano Weakness Classification registry.

ParameterTypeRequiredDescription
querystringyesCWC ID, severity, detector name, or keyword

How it works

The server spawns the aikido binary with --format json and parses the structured output. Binary discovery checks (in order):

  1. AIKIDO_BINARY environment variable
  2. npm sibling (aikido-aiken package)
  3. aikido or aikido-aiken on PATH

The CWC lookup tool uses a static registry and does not require the binary.

License

MIT

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.