Lazaretto

Check EXACTLY-PINNED npm dependencies against published malicious-package advisories (OSV/OpenSSF). Free, anonymous, one call for 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.

// inputSchema
{
  "type": "object",
  "properties": {
    "lockfile": {
      "type": "string",
      "description": "The full text contents of a package-lock.json, yarn.lock, or pnpm-lock.yaml."
    },
    "packages": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Exactly pinned packages, as \"name@version\" strings (for example [\"chalk@5.6.1\",\"debug@4.4.2\"]). Use instead of `lockfile` when you know which dependencies you care about, so a whole tree need not pass through your context. Mutually exclusive with `lockfile`."
    }
  },
  "additionalProperties": false
}

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. Metered like scan_artifact.

// inputSchema
{
  "type": "object",
  "required": [
    "tools_json"
  ],
  "properties": {
    "tools_json": {
      "type": "string",
      "description": "The tool definitions as JSON text: a tools/list response, {\"tools\":[...]}, or an array of tool objects."
    }
  },
  "additionalProperties": false
}

Ask whether anyone has already attested an artifact, BEFORE you install it or pay to scan it. Free and anonymous. 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 a free 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.

// inputSchema
{
  "type": "object",
  "required": [
    "subject"
  ],
  "properties": {
    "subject": {
      "type": "string",
      "description": "A package identity (\"chalk@5.6.1\"), an MCP server endpoint URL, or a sha256 content hash, optionally sha256: prefixed."
    }
  },
  "additionalProperties": false
}

Get a free developer key for the metered tools on this server, without leaving this session. No payment, no account, no card. The key holds a small daily allowance that refills every day, and one credit is consumed per verdict, nothing on an error. Present it as the X-API-Key header on this MCP connection, or hand it to whoever configures your client. Throttled exactly as the equivalent HTTP endpoint is: one key per source per window, so calling this again shortly after will be refused rather than minting a second key. Store the key when you get it: it is shown once and cannot be recovered.

// inputSchema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Check a SHA-256 against Lazaretto's known-bad indicator set (refreshed daily from abuse.ch). Free and anonymous. A miss only means this exact hash is not in the indicator set; it is not a clean verdict on the artifact.

// inputSchema
{
  "type": "object",
  "required": [
    "sha256"
  ],
  "properties": {
    "sha256": {
      "type": "string",
      "description": "64 hex chars, optionally sha256: prefixed"
    }
  },
  "additionalProperties": false
}

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. Metered: present an X-API-Key holding credits. If you hold a wallet instead of an account, pay per call over x402 at POST https://lazaretto.dev/v1/scan ($0.03 USDC on Base, no signup). A free key with a daily allowance is available at POST https://lazaretto.dev/v1/trial. For checks that are always free, use check_lockfile or known_bad_lookup.

// inputSchema
{
  "type": "object",
  "required": [
    "type"
  ],
  "properties": {
    "ref": {
      "type": "string",
      "description": "The locator: an npm spec (name@version), a PyPI spec (name==version), a GitHub repo URL, a ClawHub skill id, or a raw file URL. Omit for type=inline."
    },
    "name": {
      "type": "string",
      "description": "Filename for type=inline, for example SKILL.md or index.js. Which rules run depends on the kind of file, so pass the real name when you have it; without it the kind is inferred from the content."
    },
    "type": {
      "enum": [
        "github_repo",
        "raw_url",
        "clawhub_skill",
        "npm_package",
        "pypi_package",
        "mcp_server",
        "mcp_tools",
        "inline"
      ],
      "type": "string",
      "description": "What kind of artifact ref points at."
    },
    "depth": {
      "enum": [
        "lookup",
        "full"
      ],
      "type": "string",
      "default": "full",
      "description": "lookup = known-bad match only; full = full behavioral analysis."
    },
    "content": {
      "type": "string",
      "description": "Raw file content, required when type=inline."
    }
  },
  "additionalProperties": false
}

Behaviorally scan the exactly-pinned dependencies in a lockfile, not just their identities: reads the code of each package and screens for credential theft, exfiltration, obfuscation, prompt injection and install-time droppers. Each result carries a verdict, a risk level, the ids of the rules that fired and a risk summary. It does not carry file-and-line evidence: for that, run scan_artifact on the package you want to look at. This is the paid counterpart to check_lockfile, which only matches names and versions against advisories. Metered: one credit per package that returns a verdict, nothing for one that errors. Capped at 25 packages per call, in lockfile order, so calling it again with the same lockfile rescans the same first 25. To continue, pass the not_scanned.packages list from the result (name@version strings) as `packages` instead of `lockfile`. Use it before installing a tree you have not vetted.

// inputSchema
{
  "type": "object",
  "properties": {
    "lockfile": {
      "type": "string",
      "description": "The full text contents of a package-lock.json, yarn.lock, or pnpm-lock.yaml. Give this or packages."
    },
    "packages": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Exactly pinned name@version strings, for example [\"chalk@5.6.1\", \"@scope/name@1.0.0\"]. Use it to continue a capped run with the not_scanned.packages list from the previous result. Give this or lockfile."
    }
  },
  "additionalProperties": false
}

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. Metered like scan_artifact: an X-API-Key with credits, or pay per call over x402 at POST https://lazaretto.dev/v1/scan with target type mcp_server ($0.03 USDC on Base, no signup).

// inputSchema
{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The server's https endpoint, e.g. https://example.com/mcp. Streamable HTTP and SSE replies are both read."
    }
  },
  "additionalProperties": false
}

Verify a Lazaretto scan attestation that another agent (or a README, or a lockfile) handed you, WITHOUT re-scanning or paying. Free and anonymous. Returns whether the signature is valid and Lazaretto's, the attested claims (verdict, risk, and the subject the verdict is about), and a `contradicted` flag if a previously-clear subject is now known-bad. You MUST still confirm the artifact you are about to run matches `claims.sub` (its sha256, or its package identity).

// inputSchema
{
  "type": "object",
  "required": [
    "attestation"
  ],
  "properties": {
    "attestation": {
      "type": "string",
      "description": "The compact-JWS attestation string from a scan report."
    }
  },
  "additionalProperties": false
}