Skip to main content
Glama

Lookup Indicator

lookup_indicator
Read-onlyIdempotent

Look up a threat indicator in OTX: an IPv4 or IPv6 address, a domain or hostname, a URL, an MD5/SHA1/SHA256 file hash, or a CVE id such as CVE-2021-4034. Returns the threat-intel pulses referencing that indicator plus observed-context fields, so it answers questions like which campaigns exploit a given CVE or whether an IP is known-malicious. type is auto-detected when omitted.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "indicator": "192.0.2.1"
    },
    "name": "lookup_indicator"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoForce a type instead of auto-detecting. Case-insensitive and forgiving, "ip"/"ipv4"/"ip_address" all mean IPv4, "CVE" means cve, "md5"/"sha256"/"hash" all mean file. Leave it off unless auto-detection gets it wrong.
indicatorNoThe value to look up: IPv4, IPv6, domain, hostname, URL, MD5/SHA1/SHA256 hash, or a CVE id such as CVE-2021-4034. Auto-detected, you do not need to pass `type`.

Output Schema

NameRequiredDescriptionDefault
hintNoWhat to try instead, when found is false
typeYesDetected or specified indicator type
foundYesFalse when OTX has no record of this indicator
pulsesYesPulses containing this indicator
reasonNoWhy nothing was returned, when found is false
contextNoAdditional context fields from OTX API response
indicatorYesThe indicator being looked up
pulse_countYesNumber of pulses referencing this indicator

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / indicator / description
      Previous value: -"The value to look up: IPv4, IPv6, domain, hostname, URL, MD5/SHA1/SHA256 hash, or a CVE id such as CVE-2021-4034. Auto-detected — you do not need to pass `type`."New value: +"The value to look up: IPv4, IPv6, domain, hostname, URL, MD5/SHA1/SHA256 hash, or a CVE id such as CVE-2021-4034. Auto-detected, you do not need to pass `type`."
    • changedInput schema / properties / type / description
      Previous value: -"Force a type instead of auto-detecting. Case-insensitive and forgiving — \"ip\"/\"ipv4\"/\"ip_address\" all mean IPv4, \"CVE\" means cve, \"md5\"/\"sha256\"/\"hash\" all mean file. Leave it off unless auto-detection gets it wrong."New value: +"Force a type instead of auto-detecting. Case-insensitive and forgiving, \"ip\"/\"ipv4\"/\"ip_address\" all mean IPv4, \"CVE\" means cve, \"md5\"/\"sha256\"/\"hash\" all mean file. Leave it off unless auto-detection gets it wrong."
  2. Changed6 schema fields changed
    • changedInput schema / properties / type / description
      Previous value: -"Force a type instead of auto-detecting"New value: +"Force a type instead of auto-detecting. Case-insensitive and forgiving — \"ip\"/\"ipv4\"/\"ip_address\" all mean IPv4, \"CVE\" means cve, \"md5\"/\"sha256\"/\"hash\" all mean file. Leave it off unless auto-detection gets it wrong."
    • addedOutput schema / properties / found
      Added value: +{
      +  "description": "False when OTX has no record of this indicator",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / hint
      Added value: +{
      +  "description": "What to try instead, when found is false",
      +  "type": "string"
      +}
    • addedOutput schema / properties / reason
      Added value: +{
      +  "description": "Why nothing was returned, when found is false",
      +  "type": "string"
      +}
    • changedOutput schema / properties / type / enum
      Previous value: -[
      -  "IPv4",
      -  "IPv6",
      -  "domain",
      -  "hostname",
      -  "url",
      -  "file"
      -]New value: +[
      +  "IPv4",
      +  "IPv6",
      +  "domain",
      +  "hostname",
      +  "url",
      +  "file",
      +  "cve"
      +]
    • changedOutput schema / required
      Previous value: -[
      -  "indicator",
      -  "type",
      -  "pulse_count",
      -  "pulses",
      -  "context"
      -]New value: +[
      +  "found",
      +  "indicator",
      +  "type",
      +  "pulse_count",
      +  "pulses"
      +]
  3. Changed3 schema fields changed
    • changedInput schema / properties / indicator / description
      Previous value: -"IPv4, domain, URL, or file hash (md5/sha1/sha256)"New value: +"The value to look up: IPv4, IPv6, domain, hostname, URL, MD5/SHA1/SHA256 hash, or a CVE id such as CVE-2021-4034. Auto-detected — you do not need to pass `type`."
    • changedInput schema / properties / type / enum
      Previous value: -[
      -  "IPv4",
      -  "IPv6",
      -  "domain",
      -  "hostname",
      -  "url",
      -  "file"
      -]New value: +[
      +  "IPv4",
      +  "IPv6",
      +  "domain",
      +  "hostname",
      +  "url",
      +  "file",
      +  "cve"
      +]
    • removedInput schema / required
      Removed value: -[
      -  "indicator"
      -]
  4. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
      -  {
      -    "indicator": "192.0.2.1"
      -  },
      -  {
      -    "indicator": "example.com",
      -    "type": "domain"
      -  },
      -  {
      -    "indicator": "d41d8cd98f00b204e9800998ecf8427e",
      -    "type": "file"
      -  }
      -]New value: +[
      +  {
      +    "indicator": "192.0.2.1"
      +  },
      +  {
      +    "indicator": "example.com",
      +    "type": "domain"
      +  },
      +  {
      +    "indicator": "d41d8cd98f00b204e9800998ecf8427e",
      +    "type": "file"
      +  },
      +  {
      +    "indicator": "CVE-2021-4034",
      +    "type": "cve"
      +  }
      +]
  5. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "indicator": "192.0.2.1"
      +  },
      +  {
      +    "indicator": "example.com",
      +    "type": "domain"
      +  },
      +  {
      +    "indicator": "d41d8cd98f00b204e9800998ecf8427e",
      +    "type": "file"
      +  }
      +]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "context": {
      +      "description": "Additional context fields from OTX API response",
      +      "type": "object"
      +    },
      +    "indicator": {
      +      "description": "The indicator being looked up",
      +      "type": "string"
      +    },
      +    "pulse_count": {
      +      "description": "Number of pulses referencing this indicator",
      +      "type": "number"
      +    },
      +    "pulses": {
      +      "description": "Pulses containing this indicator",
      +      "items": {
      +        "properties": {
      +          "attack_ids": {
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "author": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "created": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "description": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "id": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "indicators_count": {
      +            "type": [
      +              "number",
      +              "null"
      +            ]
      +          },
      +          "industries": {
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "malware_families": {
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "modified": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "name": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "otx_url": {
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "tags": {
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "targeted_countries": {
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "type": {
      +      "description": "Detected or specified indicator type",
      +      "enum": [
      +        "IPv4",
      +        "IPv6",
      +        "domain",
      +        "hostname",
      +        "url",
      +        "file"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "indicator",
      +    "type",
      +    "pulse_count",
      +    "pulses",
      +    "context"
      +  ],
      +  "type": "object"
      +}
  6. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds value beyond that by describing the response shape (pulses plus observed-context fields) and the auto-detection fallback for omitted type, though it says nothing about rate limits, empty-result behavior, or lookup cost.

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?

Two sentences plus a short clause, front-loaded with the verb and resource and followed by the return value and the type-omission rule. The final auto-detection sentence is somewhat redundant with the schema's parameter description, costing a point.

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?

An output schema exists and annotations cover the safety profile, so the description only needs to establish input scope and the nature of the result — both of which it does. Nothing an agent needs in order to call this correctly is missing.

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

Parameters3/5

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

Schema description coverage is 100% and the schema already documents both fields, including the forgiving type aliases and the auto-detect default. The description's closing note that "type is auto-detected when omitted" restates the schema rather than adding new semantics, so the baseline 3 applies.

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

Purpose5/5

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

States a specific verb and resource ("Look up a threat indicator in OTX") and enumerates the exact accepted indicator classes: IPv4/IPv6, domain/hostname, URL, MD5/SHA1/SHA256 hash, and CVE id. It also says what comes back (threat-intel pulses plus observed-context fields), so an agent can tell this apart from pulse-oriented siblings like get_pulse without opening a schema.

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

Usage Guidelines4/5

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

Gives concrete motivating questions ("which campaigns exploit a given CVE", "whether an IP is known-malicious"), which tells the agent when this is the right call. It does not name an alternative tool or state when not to use it, so it falls short of explicit routing guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.