Skip to main content
Glama

listObservables

List and filter Mallory observables, returning lean summaries as {items,total,offset,limit}. Each item includes: observable type (e.g. ip.v4, domain, url, hash.sha256), name/value, and verdict/opinion counts. Filter prefixes: type: (e.g. type:ip or type:ip.v4), name:, uuid:. Sort by uuid, created_at, updated_at, type, name, severity_score, confidence_score. Optional fieldFilters: scope=global|tenant, created_at__gte/__lt, severity_score__gte/__lte, confidence_score__gte/__lte, score_scope=tenant|restricted|global (tenant: only observables with the tenant's custom score; restricted: only those with the CrowdStrike combined score, for a tenant with CrowdStrike access). Field operators append to a field name with __: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=&created_at__lt=. Pass an item's identifier to getObservable for the full detail object.

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": "listObservables"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoField to sort by (see this tool's sort fields).
limitNoMax items to return (1-100, default 25).
orderNoSort order (default: desc).
filterNoPrefix filter string (see this tool's filter prefixes). No prefix = default name/text search.
offsetNoItems to skip, for pagination.
fieldFiltersNoAdvanced structured filters as a map of query-param name -> value. Use a bare field for exact match, or a field__operator key for ranges/sets. Field operators append to a field name with `__`: strings support __neq, __in, __not_in, __like, __ilike; numbers support __gt, __gte, __lt, __lte. Timestamps (created_at, updated_at) support __gte and __lt ONLY — there is no __gt, __lte, or bare equality on them, so express a range as the half-open created_at__gte=<start>&created_at__lt=<end>.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

No annotations are supplied, so the description must carry the behavioral burden, and it does: read-only summary listing, the exact response envelope, the empty-prefix default of name/text search, and the non-obvious constraint that timestamps only support __gte/__lt. It never states permissions or rate limits, which is a minor 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?

Dense and front-loaded: return shape first, then item fields, then filters, then sorting, then the sibling handoff. The field-operator block is repeated nearly verbatim from the fieldFilters schema description, which is redundant, but everything else earns its place.

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 six-parameter listing tool with no output schema and a nested fieldFilters object, the description covers return shape, item fields, all filter prefixes, all sort keys, and operator semantics. An agent could call this correctly without further discovery.

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?

The schema's parameter descriptions defer outward ('see this tool's sort fields', 'see this tool's filter prefixes'), and the description fills those holes with enumerated sort fields and filter prefixes (type:, name:, uuid:). It also decodes score_scope values (tenant/restricted/global) and spells out the half-open timestamp range pattern.

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 opens with a specific verb+resource ('List and filter Mallory observables') and immediately states the return shape 'as {items,total,offset,limit}'. It closes by distinguishing itself from the sibling getObservable, which serves full detail.

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?

Clear context for the tool's use: filtered listing with sort and pagination, plus a routing instruction to pass an item's identifier to getObservable for the full record. It does not state exclusions such as when to use referenceObservables instead, so it falls short of full when/when-not 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.

Resources