Skip to main content
Glama
Sign In
greynoise-mcp-server

greynoise-mcp-server

Official
by GreyNoise-Intelligence
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

GNQL Query

gnql-query
Read-only

Search GreyNoise threat intelligence with GNQL queries to retrieve full IP context, raw scan data, and paginated results for investigating malicious, benign, or unknown devices.

Instructions

Search GreyNoise data using GNQL (GreyNoise Query Language). Returns full IP context results including raw scan data.

GNQL is a domain-specific query language that uses Lucene deep under the hood.

Facets:

  • "ip" - The IP address of the scanning device

  • "classification" - Whether the device has been categorized as unknown, benign, or malicious

  • "first_seen" / "last_seen" - Date the device was first/most recently observed

  • "actor" - The benign actor the device has been associated with (Shodan, Censys, etc)

  • "tags" - Tags assigned to the device over the past 90 days

  • "cve" - CVEs associated with the device

  • "vpn" / "vpn_service" / "bot" / "tor" - Boolean/string indicators

  • "metadata.category" - Network category (business, isp, hosting, education, mobile)

  • "metadata.source_country" / "metadata.source_country_code" - Source location

  • "metadata.organization" / "metadata.asn" / "metadata.rdns" - Network info

  • "raw_data.scan.port" / "raw_data.scan.protocol" - Scan targets

  • "raw_data.web.paths" / "raw_data.web.useragents" - HTTP activity

  • "raw_data.ja3.fingerprint" / "raw_data.hassh.fingerprint" - TLS/SSH fingerprints

Examples:

  • "classification:malicious last_seen:1d" - Malicious IPs seen in last day

  • "tags:Mirai" - Devices tagged as Mirai

  • "raw_data.scan.port:445 metadata.os:Windows*" - Windows hosts scanning port 445

  • "cve:CVE-2021-30461" - Devices associated with a CVE

  • "source_country:Iran destination_country:Ukraine single_destination:true" - Targeted scanning

Results are paginated. Use the scroll parameter to retrieve additional pages.

Input Schema

NameRequiredDescriptionDefault
sizeNoResults per page (default: 25, max: 10000)
queryYesGNQL query string
scrollNoPagination scroll token from a previous response

Output Schema

NameRequiredDescriptionDefault
dataYes
request_metadataYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.5
    • changedOutput schema / properties / data / items / properties / business_service_intelligence / anyOf
      Previous value: -[
-  {
-    "additionalProperties": {},
-    "properties": {
-      "found": {
-        "anyOf": [
-          {
-            "type": "boolean"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "name": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "trust_level": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      }
-    },
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": {},
+    "properties": {
+      "found": {
+        "type": [
+          "boolean",
+          "null"
+        ]
+      },
+      "name": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "trust_level": {
+        "type": [
+          "string",
+          "null"
+        ]
+      }
+    },
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
  2. Addedv0.5.4
  3. Removedv0.5.3
  4. First observedv0.4.0

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds useful behavioral context: it returns full IP context with raw scan data and results are paginated via the scroll parameter. It does not discuss rate limits or authentication, but goes meaningfully beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well structured: purpose first, then facets, examples, and pagination guidance. The facet list is extensive, but it is useful reference material for a query language rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema and annotations, the description supplies the key missing context an agent needs: GNQL syntax guidance, representative fields, examples, and pagination behavior. Nothing essential for correct invocation appears absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description substantially enriches the query parameter by explaining GNQL facets and giving concrete query examples. It also reinforces the scroll parameter's pagination role, adding meaning beyond the schema's brief descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: search GreyNoise data using GNQL, returning full IP context including raw scan data. It is clear what the tool does, though it does not explicitly distinguish itself from nearby query tools like gnql-metadata-query, gnql-stats, or lookup-ip-context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The examples imply when GNQL is useful for targeted IP-context searches, but the description does not explicitly say when to use this tool versus sibling query or lookup tools. It gives strong query examples but no explicit alternatives or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools