MCP App Store
by KeenEthics
Lazaretto icon

Lazaretto MCP Server for Claude

By Lazaretto

Overview

Lazaretto checks what an AI agent is about to trust. Give it a remote MCP server URL and it reads the advertised tool names, descriptions, parameters and server instructions for tool poisoning. It looks for hidden directives, attempts to extract secrets, instructions targeting another server's tools, and invisible Unicode. Paste an existing tool list to check a local server without contacting it. Check exact npm package versions or a lockfile against published OSV / OpenSSF malicious-package advisories. Look up a SHA-256 in a daily known-bad indicator set, find remote MCP servers from the official registry with inspection results, or retrieve and verify signed Lazaretto attestations. Checks use fixed rules and published evidence. Findings identify the matching rule and affected tool or line. No match is not a guarantee of safety. Unchecked items and stale attestations are identified. No account or sign-in is required. All seven tools are read-only. They do not install packages, execute target tools, change files or move money. Lazaretto receives the inputs supplied to its tools; it does not request your chat history. Do not include credentials or personal information in those inputs.

How to connect

  1. Claude: Open the Lazaretto listing in the Claude connectors directory and choose Connect. Claude listing Lazaretto exposes 7 tools here.

Tools

check_lockfile

Claude
Check EXACTLY-PINNED npm dependencies against published malicious-package advisories (OSV/OpenSSF). One call covers the whole set. Give EITHER lockfile, the full text of a package-lock.json, yarn.lock or pnpm-lock.yaml, OR packages, a list of "name@version" strings, which is the one to reach for when you only care about a few dependencies or when an 800-package tree would not fit in your context. Give one or the other, never both. Only exact versions can be answered: a range like ^5.0.0 has no definitive answer because a compromised release usually sits between clean ones. Fail-closed: anything that could not be checked is returned in unverified, so an empty malicious list is an all-clear only when unverified is empty too AND truncated is false. truncated: true means the lockfile ran past the per-request package limit and the packages past it went into NEITHER list: they were never looked at, checked counts only the ones that were, and the rest are unchecked rather than clean. When that happens, send the remainder as packages (name@version strings) in a second call, or split the lockfile by workspace, before telling anyone the tree is clean.

check_mcp_tools

Claude
Check tool definitions you ALREADY HOLD, with no network call to anyone. Most MCP servers run locally over stdio and have no endpoint that can be reached, so this is the only way to check them, and your client already read their tool list at startup. Paste that JSON: a whole tools/list response, a {"tools":[...]} object, or a bare array. Analyzes the same text as scan_mcp_server and applies the same rules, so a payload cannot be caught over the wire and missed here. Detects tool poisoning (hidden directive blocks, orders pointing the agent at private keys or an agent config file), parameters whose real purpose is to carry secrets or your conversation out, standing orders about ANOTHER server's tools, and invisible-unicode payloads.

find_attestation

Claude
Ask whether anyone has already attested an artifact, before installing it. Give a package identity like "chalk@5.6.1", an MCP server endpoint URL, or a sha256 content hash. Returns the signed verdict if one exists, which you can verify offline against https://lazaretto.dev/.well-known/jwks.json, plus freshness: whether the corpus has since contradicted it and whether it was attested under an older rules version. A miss is not a verdict, it only means nobody has scanned this yet. When nobody has attested an npm package identity, the answer falls back to an identity check against published advisories: answer: "identity_check" with an identity_check object, and found still false, because an identity check is unsigned, looks at the identity rather than the code, and absence from the corpus is not a verdict. identity_check.listed_as_malware: true comes back as an error result, so a published malware version cannot be read as "nothing found"; null there means the corpus could not be consulted, which is unchecked and never clear.

find_mcp_servers

Claude
Find a remote MCP server for a job: describe what is needed ("postgres", "send slack messages", "browser automation") and get matching servers from the official MCP registry, each with its endpoint, its tools, and what Lazaretto's latest read of those tools found. Only servers whose tools we read with nothing matching our tool-poisoning rules, or live servers that ask the user to sign in before listing tools (said plainly), are returned; servers we flagged or could not reach are left out. Remote servers only: for a local stdio server, check its tool list with check_mcp_tools.

known_bad_lookup

Claude
Check a SHA-256 against Lazaretto's known-bad indicator set (refreshed daily from abuse.ch). Use it when the user has a file hash and wants to know whether it is a known malware sample. A miss only means this exact hash is not in the indicator set; it is not a clean verdict on the file.

scan_mcp_server

Claude
Check an MCP server BEFORE you connect to it. Asks the server to introduce itself and list its tools, then analyzes the text it hands an agent: tool names, descriptions, parameter schemas and server instructions. Catches tool poisoning (hidden directives that point the agent at private keys or at an agent config file), parameters whose real purpose is to carry secrets or your conversation out, standing orders about ANOTHER server's tools (cross-server shadowing), and invisible-unicode payloads. Returns a verdict with the exact tool and line as evidence, plus a hash of what was advertised, so a server that changes its tools later does not inherit the old verdict.

verify_attestation

Claude
Verify a Lazaretto scan attestation that another agent (or a README, or a lockfile) handed you, without re-scanning it. Returns signature validity and the signed claims, including verdict, risk and subject. For a clear or flagged SHA-256 subject only, checks the current known-bad indicator set and includes contradicted when it matches. That field is otherwise omitted; its absence is not a freshness or safety verdict. Package identities are not rechecked here. A valid signature authenticates an earlier claim, not current safety. The artifact's hash or package identity must match claims.sub for the claim to apply.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/lazaretto"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/lazaretto)