registry

Check an MCP server against the PolicyLayer registry BEFORE installing or allowing it. Accepts a registry slug, an npm package name (scoped or not), a remote server URL (https://…), or a server name. Returns the full published record: identity verification with its evidence, risk grade, auth posture, freshness, and the tool surface listed riskiest-first. A server the registry does not know is queued for scanning by this very call — check back shortly.

{
  "type": "object",
  "properties": {
    "server": {
      "type": "string",
      "description": "Registry slug, npm package name (e.g. @acme/mcp-server), remote URL, or server name."
    }
  },
  "required": [
    "server"
  ]
}

Check a whole MCP stack against the PolicyLayer registry in one call — up to 25 servers, each given as candidate identifiers (npm package name, registry slug, or remote URL) tried in order until one resolves. Returns the published record for every hit — plus a deterministic verdict (attention signals and a suggested action) — and the lookup status for every miss; counts, grades and flagged tools come from the published records only. Costs one rate-limit unit per server.

{
  "type": "object",
  "properties": {
    "servers": {
      "type": "array",
      "maxItems": 25,
      "description": "One entry per server in the stack.",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string",
            "description": "Your label for this server (e.g. its config key) — echoed back on the result."
          },
          "candidates": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "maxItems": 5,
            "description": "Identifiers to try in order: npm package name, registry slug, or remote URL. Most package-like first."
          }
        },
        "required": [
          "candidates"
        ]
      }
    }
  },
  "required": [
    "servers"
  ]
}

Search the PolicyLayer registry of published MCP servers by name, slug or package substring. Returns candidate matches with risk grade, identity confidence (verified / unverified / mismatch — mismatch means it claims to be an official server with no verifiable link to the brand) and tool count — follow up with check_mcp_server on the match you meant.

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Substring to match against slug, name and packages."
    },
    "limit": {
      "type": "number",
      "description": "Max matches to return (1-20, default 10)."
    }
  },
  "required": [
    "query"
  ]
}

One tool's full risk classification on a published MCP server: category, severity, risk analysis and evidence, OWASP classes, parameter schema and the recommended policy default. Use when deciding whether to allow a specific tool call, e.g. "should execute_sql on this server be permitted?"

{
  "type": "object",
  "properties": {
    "server": {
      "type": "string",
      "description": "Registry slug or npm package name of the server."
    },
    "tool": {
      "type": "string",
      "description": "Tool name as the server declares it."
    }
  },
  "required": [
    "server",
    "tool"
  ]
}

The registry change feed: tool-surface drift, auth-posture flips, impostor flags, version bumps — every event the freshness watchers emit, id-cursored so a consumer resumes exactly where it stopped. Requires a Registry Licence key (Authorization: Bearer plr_...); self-serve at https://policylayer.com/registry/pricing.

{
  "type": "object",
  "properties": {
    "after_id": {
      "type": "number",
      "description": "Return events with id greater than this cursor (default 0)."
    },
    "limit": {
      "type": "number",
      "description": "Max events (1-1000, default 200)."
    },
    "severity": {
      "type": "string",
      "enum": [
        "info",
        "notice",
        "warning",
        "critical"
      ],
      "description": "Minimum severity: that level and above."
    }
  }
}