Verify a skill, tool, or package for malicious behavior before your agent installs it. Hosted.
Verify a skill, tool, or package for malicious behavior before your agent installs it. Hosted.
Checks every exactly-pinned dependency in your lockfile against published malicious-package advisories. Reads package-lock.json, yarn.lock, or pnpm-lock.yaml from the working directory, so the agent never has to paste a lockfile through its context. One call covers the whole tree.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"lazaretto": {
"url": "https://lazaretto.dev/mcp",
"headers": {
"X-API-Key": "your-prepaid-key (optional; known_bad_lookup is free)"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| LAZARETTO_API_KEY | Credential the server authenticates with. | Yes |
| LAZARETTO_BASE_URL | Endpoint or connection string the server talks to. | Yes |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
MCP Server implementing various tools to execute admin tasks on a Linux system.
Inspector MCP Server was built specifically for the PHP ecosystem; this server provides tools to allow AI coding agents to access production errors data with comprehensive context, to automatically…
A rule-based prose linter that scores text 0--100 for formulaic AI writing patterns. No LLM judge, no API calls. Purely programmatic.
A user-friendly editor tool has been developed to create or edit JSON configuration files: