Skip to main content
Glama

Search Pulses

search_pulses
Read-onlyIdempotent

Search OTX threat-intel pulses by KEYWORD, campaign, malware family or actor name, e.g. "ransomware" or "APT29". Returns pulse ID, name, description preview, tags, targeted countries, malware families, attack IDs, and indicator count. This matches pulse titles and descriptions, so a bare indicator value (an IP, domain, hash or CVE id) will find nothing here, use lookup_indicator for those.

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": {
      "query": "ransomware"
    },
    "name": "search_pulses"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo1-based page (default 1)
limitNo1-50 (default 20)
queryYesSearch term

Output Schema

NameRequiredDescriptionDefault
totalYesTotal number of pulses matching the query
pulsesYesList of pulse summaries
returnedYesNumber of pulses returned in this response

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "query": "ransomware"
      +  },
      +  {
      +    "limit": 10,
      +    "page": 1,
      +    "query": "emotet"
      +  }
      +]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "pulses": {
      +      "description": "List of pulse summaries",
      +      "items": {
      +        "properties": {
      +          "attack_ids": {
      +            "description": "MITRE ATT&CK IDs",
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "author": {
      +            "description": "Pulse author name",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "created": {
      +            "description": "Creation timestamp",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "description": {
      +            "description": "Pulse description (truncated to 400 chars)",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "id": {
      +            "description": "Pulse ID (hex string)",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "indicators_count": {
      +            "description": "Number of indicators in pulse",
      +            "type": [
      +              "number",
      +              "null"
      +            ]
      +          },
      +          "industries": {
      +            "description": "Targeted industries",
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "malware_families": {
      +            "description": "Associated malware families",
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "modified": {
      +            "description": "Last modification timestamp",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "name": {
      +            "description": "Pulse name",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "otx_url": {
      +            "description": "OTX web URL for pulse",
      +            "type": [
      +              "string",
      +              "null"
      +            ]
      +          },
      +          "tags": {
      +            "description": "Associated tags",
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          },
      +          "targeted_countries": {
      +            "description": "Countries targeted by threat",
      +            "items": {
      +              "type": "string"
      +            },
      +            "type": "array"
      +          }
      +        },
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "returned": {
      +      "description": "Number of pulses returned in this response",
      +      "type": "number"
      +    },
      +    "total": {
      +      "description": "Total number of pulses matching the query",
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "total",
      +    "returned",
      +    "pulses"
      +  ],
      +  "type": "object"
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, open-world behavior, so the bar is lower; the description still adds meaningful behavior by specifying exactly which fields the match applies to (titles and descriptions) and what a result set contains. It stops short of describing relevance ranking or result ordering, which is the only notable gap.

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?

Three tight sentences, front-loaded with the action and its arguments, with the exclusion clause placed where it prevents wasted calls. Slight redundancy in enumerating returned fields when an output schema already exists, but the list is short and aids selection.

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?

For a filtered search tool with annotations covering safety and an output schema covering return shape, nothing an agent needs to call it correctly is missing: the match target, the argument styles, and the escape hatch to lookup_indicator are all present.

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

Parameters4/5

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

Schema coverage is 100%, so page and limit need no help. The description goes beyond the schema's terse "Search term" by explaining that query is matched against pulse titles and descriptions and by showing valid term shapes, which genuinely constrains how to phrase the argument.

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 ("Search OTX threat-intel pulses") and enumerates what the query can express: keyword, campaign, malware family, actor name, with concrete examples ("ransomware", "APT29"). It also explicitly separates itself from lookup_indicator, so an agent can route without inspecting sibling schemas.

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

Usage Guidelines5/5

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

Gives both when-to-use and when-not-to-use: pulse title/description matching for topical searches, and an explicit exclusion with the correct alternative for bare indicator values. This is a complete routing rule, not an implied one.

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.