Skip to main content
Glama

Search network traffic (Malcolm filters)

malcolm_search
Read-only

Search Malcolm's indexed network traffic with field-based filters and human-readable time ranges, returning matching documents.

Instructions

Search Malcolm's indexed network traffic using Malcolm's simple filter dict.

    Use this for field-based filtering with human-readable time ranges. To
    search with Arkime expression syntax instead, or when you need a session
    id to feed arkime_session_pcap / arkime_add_tags afterward, use
    arkime_sessions (only its rows carry that id). For raw OpenSearch DSL,
    use search_dsl. Confirm field names with malcolm_field_search first —
    Malcolm uses non-standard names. Returns the raw Malcolm /mapi/document
    response (matching documents); when nothing matched and a filter names a
    field Malcolm does not index, the correct field name is reported above
    the response.

    Two defaults to know before the first call: with no time_from this
    searches ALL retained history, where malcolm_aggregate covers only the
    last 24 hours; and filter values are matched exactly, so any wildcard or
    substring has to go to search_dsl instead.
    

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax documents to return.
doctypeNoTarget index. Empty = the Malcolm network index (Zeek/Suricata); "host"/"beat"* = host/beats logs; "arkime"/"session"* = the Arkime sessions index.
filtersNoJSON object in Malcolm filter syntax (NOT OpenSearch DSL). Values are matched EXACTLY — Malcolm compiles this to a terms query, so wildcards are NOT supported and "*example*" matches only the literal string. Use search_dsl for substring/wildcard matching. Examples: {"event.dataset":"conn"}; {"source.ip":"192.0.2.77"}; {"zeek.dns.query":"ntp.ubuntu.com"}; {"!network.transport":"icmp"} excludes; {"network.direction":["inbound","outbound"]} is OR; {"!related.password":null} means the field must exist. Empty = match all.{}
time_toNoEnd time, dateparser format. Empty = now.
time_fromNoStart time, dateparser format ("2024-01-01", "7 days ago"). Empty = ALL history (this tool's default, unlike malcolm_aggregate which defaults to the last 24 hours).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

Even though annotations mark readOnlyHint and non-destructive, the description adds valuable behavioral context: default time range covers ALL history (unlike malcolm_aggregate), filter values are matched exactly (no wildcards), and missing indexed fields report the correct field name above the response. These are critical operational nuances not in annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense yet well-organized: purpose first, alternatives second, defaults and edge behaviors third. Every sentence serves a purpose—no filler. It packs substantial guidance into a compact form without being verbose.

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 search tool with an output schema and zero required parameters, the description covers all needed aspects: return format (raw /mapi/document response), field validation behavior, default time range, exact matching semantics, and explicit distinctions from sibling tools. The agent is fully equipped to select and invoke correctly.

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?

Schema coverage is 100%, but the description enriches parameters well beyond schema descriptions. It explains the filters parameter compiles to a terms query with exact matching, provides examples for exclusion (!), OR lists, and existence checks (!field:null), and clarifies time_from defaults. This is significant added value.

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: 'Search Malcolm's indexed network traffic using Malcolm's simple filter dict.' It clearly distinguishes from siblings by explicitly naming arkime_sessions and search_dsl as alternatives for different cases.

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?

Provides explicit when-to-use guidance: 'Use this for field-based filtering with human-readable time ranges.' It names alternatives directly: arkime_sessions for Arkime syntax/session id, search_dsl for raw DSL, malcolm_field_search for field name confirmation. This goes beyond vague hints.

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/nagameTW/mcp-server-malcolm'

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