isMalicious threat intelligence for AI agents

List alerts

list_alerts

Read-onlyIdempotent

One page of the isMalicious alert inbox (GET /alerts): the alerts raised on what the account watches, such as a watched domain or IP turning malicious or named on a ransomware leak site, certificate, WHOIS, location and infrastructure changes, lookalike domains, and vulnerability findings (cve.finding). Open and acknowledged alerts by default (set status to change that), most recent activity first; filters by severity, eventType, entityType and a search over title, description and value. Each alert: id (for ack_alert), type, severity, status, entity, title, description (300 characters at most), source, confidence and dates; a CVE alert also names its findingId, cveId and priority (for ack_finding). When hasMore is true, call again with offset + returned. Scope: the inbox of the user the key belongs to, which for an organization API key is the organization owner's; alerts on items another member watches are in that member's inbox. Read-only. Costs no request of the monthly quota (the key's per-minute burst limit applies).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

Name	Required	Description
`limit`	No	Alerts per page (default 20, max 50).
`offset`	No	Alerts to skip (default 0): the previous page's offset + returned.
`search`	No	Text matched in the title, the description or the value (e.g. a domain or a CVE id).
`status`	No	Statuses to list (default OPEN and ACKNOWLEDGED).
`severity`	No	Severities to list, e.g. ["critical", "high"] (default all).
`eventType`	No	Alert types to list (default all).
`entityType`	No	What the alert is about (default all); a CVE alert is `system`.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 8, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already declare readOnlyHint/idempotentHint, and the description adds substantive context beyond them: no monthly quota consumption but the per-minute burst limit applies, the inbox is scoped to the key's user (organization owner for org keys), and other members' watched items are excluded. It also discloses the 300-character truncation of the description field, which is a real behavioral trait an agent must know when parsing results.

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?

Front-loaded with the resource and endpoint, then filters, then result shape, then pagination and scope — a logical order with no filler sentences. It is a dense single paragraph, though, and the long enumeration of alert categories plus the parenthetical CVE field notes make it heavier than it needs to be for scanning.

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?

With no output schema, the description carries the return-value burden and does so: it lists the fields per alert (id, type, severity, status, entity, title, description, source, confidence, dates) plus CVE-specific fields and their follow-up tool. Combined with pagination, scope, and quota behavior, nothing an agent needs 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 coverage is 100%, so defaults, enums, and the offset arithmetic are already documented per parameter. The description restates the status default and search targets but adds no syntax or semantics the schema lacks, so the baseline of 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 ("One page of the isMalicious alert inbox (GET /alerts)") and then enumerates the alert categories it covers, so an agent can tell it apart from siblings like search_indicators or check_indicator. It also names the follow-up tools (ack_alert, ack_finding) tied to returned fields, reinforcing what this tool is and is not.

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 usage conditions: open and acknowledged alerts by default, change via status, most recent first, and an explicit pagination rule ("When hasMore is true, call again with offset + returned"). It also explains scope boundaries for organization keys. It stops short of naming an alternative tool to use when the agent wants alerts for another member's inbox, which is the one routing gap.

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

All isMalicious threat intelligence for AI agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.