Security & Testing

lazaretto.dev

Provides security scanning and analysis tools to detect malicious code, credential theft, and supply-chain attacks in packages and lockfiles.

x402 supported1 endpoint8 known toolsFirst detected August 6, 2026Last detected September 6, 2026

ENDPOINT 1

https://lazaretto.dev/mcp

No auth detected

MCP server metadata

Name: lazaretto
Version: 1.0.0

Capabilities

tools

Server instructions

Lazaretto verifies skills, tools, and packages before an agent installs them. known_bad_lookup is free. scan_artifact needs an X-API-Key header holding prepaid credits.

Known tools 8

known_bad_lookup

Check a SHA-256 against Lazaretto's known-bad indicator set (refreshed daily from abuse.ch).

Inferred read-only

check_lockfile

Check every EXACTLY-PINNED dependency in a lockfile against published malicious-package advisories (OSV/OpenSSF).

Inferred read-only

scan_artifact

Deterministically analyze a package, repo, skill, or file for malicious behavior (credential theft, data exfiltration, obfuscation, prompt injection aimed at the agent, install scripts) and return a verdict (malicious, flagged, clear, error) with the exact evidence and a hash of what was scanned.

Inferred read-only

scan_lockfile_deep

Behaviorally scan EVERY exactly-pinned dependency in a lockfile, not just their identities: reads the code of each package and reports credential theft, exfiltration, obfuscation, prompt injection and install-time droppers with file-and-line evidence.

Inferred read-only

scan_mcp_server

Check an MCP server BEFORE you connect to it.

Inferred read-only

check_mcp_tools

Check tool definitions you ALREADY HOLD, with no network call to anyone.

Inferred read-only

find_attestation

Ask whether anyone has already attested an artifact, BEFORE you install it or pay to scan it.

Potential side effects

verify_attestation

Verify a Lazaretto scan attestation that another agent (or a README, or a lockfile) handed you, WITHOUT re-scanning or paying.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.lazaretto]
url = "https://lazaretto.dev/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "lazaretto": {
      "type": "http",
      "url": "https://lazaretto.dev/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: lazaretto
Remote MCP URL: https://lazaretto.dev/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "lazaretto": {
      "url": "https://lazaretto.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "lazaretto": {
      "type": "http",
      "url": "https://lazaretto.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "lazaretto",
  "transport": "streamable-http",
  "url": "https://lazaretto.dev/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.