Skip to main content
Glama
CoveoSec
by CoveoSec

indicators_insert_csv

Upload CSV of indicators (IOCs) from external threat intelligence sources into Cortex XDR to insert multiple indicators at once. New data only; historical data is not scanned.

Instructions

Insert Simple Indicators, CSV

Upload IOCs in CSV format that you retrieved from external threat intelligence sources.

Note: Cortex XDR does not scan historic data, but rather only new incoming data.

Required license: Cortex XSIAM Premium or Cortex XSIAM Enterprise or Cortex XSIAM Enterprise Plus

[POST /public_api/v1/indicators/insert_csv] · Rules

Example request body:

{
  "request_data": "indicator,type,severity,expiration_date, comment,reputation,reliability,class,vendor.name,vendor.reputation, vendor.reliability\n B2c74bf609159f27dd89a829501ec34d6596d8b39a2cce7add73a8207088817a, HASH,HIGH,1587054895000,This is an example IOC,BAD,D,Malware,IBM, GOOD,B\n A2c74bf609159f27dd89a829501ec34d6596d8b39a2cce7add73a8207088817a, HASH,LOW,1587054895000,This is an example IOC,GOOD,D,Malware,PANW, BAD,A\n"
}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
validateNoIndicates whether to return an array of errors in the case of an unsuccessful update indicator API request.
request_dataYesThe body of this request contains a JSON object with a single field: `request_data`. This field is required. Its value is as string containing two or more comma-separated lines. The first line must contain the CSV header. All subsequent lines must represent IOC data. Each line must include at a minimum the required CSV fields, which are identified below. To help you validate the upload, you can send a separate validate field to view an array of errors with an unsuccessful call. | Field | Description | | ----------- | ----------- | | indicator | (Required) String that identifies the indicator you want to insert into Cortex XDR. | | type | (Required) Keyword identifying the type of indicator. Valid values are: `HASH`, `IP`, `PATH`, `DOMAIN_NAME`, or `FILENAME` | | severity | (Required) Keyword identifying the indicator's severity. Valid values are: `INFO`, `LOW`, `MEDIUM`, `HIGH`, or `CRITICAL` | | expiration_date | Integer representing the indicator's expiration timestamp. This is a Unix epoch timestamp value, in milliseconds. If this indicator has no expiration, use `Never`. If this value is NULL, the indicator receives the indicator's type value with the default expiration date. Valid values are: 7 days, 30 days, 90 days, or 180 days | | comment | Comment string. | | reputation | Keyword representing the indicator's reputation. Valid values are: `GOOD`, `BAD`, `SUSPICIOUS`, or `UNKNOWN` | | reliability | Character representing the indicator's reliability rating. Valid values are A-F. A is the most reliable, F is the least. | | class | String representing the indicator class (for example, "Malware") | | vendor.name | String representing the name of the vendor who reported this indicator. | | vendor.reputation | Keyword representing the vendor's reputation. Valid values are: `GOOD`, `BAD`, `SUSPICIOUS`, or `UNKNOWN` | | vendor.reliability | Character representing the vendor's reliability rating. Valid values are A-F. A is the most reliable, F is the least. |
Behavior4/5

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

With no annotations, the description carries the full behavioral burden. It discloses a critical limitation ('Cortex XDR does not scan historic data, but rather only new incoming data'), required licenses, and the endpoint. It does not detail side effects like overwriting, but insertion is reasonably clear. The validate parameter is mentioned as a way to see errors.

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 moderately long but efficiently structured: title, action, note, license, endpoint, and example. Every section contributes value, and the example is essential. It is not overly verbose despite the amount of context.

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

Completeness4/5

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

For a CSV upload tool with no output schema, the description provides a comprehensive example, license requirements, a behavioral limitation, and the endpoint. It could be more complete by specifying the response format, but the schema and example cover most needs.

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 baseline is 3. The description adds a concrete example request body demonstrating the exact CSV format, which is practical and goes beyond the schema's table. This helps the agent construct the request_data correctly.

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?

The description clearly states the tool's purpose with a specific verb ('Insert'), resource ('Simple Indicators'), and format ('CSV'). It distinguishes itself from sibling tools by explicitly naming the CSV format, which sets it apart from indicators_insert_jsons and indicators_insert.

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?

The description gives clear usage context: 'Upload IOCs in CSV format that you retrieved from external threat intelligence sources.' It also includes an important caveat about historic data not being scanned and license requirements. However, it does not explicitly mention alternatives or when not to use this tool, though the format is implied.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CoveoSec/xsiam-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server