Skip to main content
Glama

atlas_technique_search

Read-onlyIdempotent

Search the MITRE ATLAS catalog for AI/ML attack techniques using keyword, tactic, or maturity filters. Returns results with technique IDs, names, and descriptions to identify threats targeting AI systems.

Instructions

Search the MITRE ATLAS catalog of AI/ML attack techniques by keyword, tactic, or maturity. Default response is SLIM (description truncated to 240 chars per row); pass include='full' for the verbose record. Pass exclude_id when chaining from atlas_technique_lookup to skip self in sibling-tactic searches. Use this to discover techniques matching a threat-model question, e.g. 'what techniques target LLM serving infrastructure?'. Drill into atlas_technique_lookup with any returned technique_id for the full description, ATT&CK bridge, and pivot hints. For broader cross-referencing: when a result has attack_reference_id, that bridges to D3FEND mitigations via d3fend_defense_for_attack. Free: 100/hr, Pro: 1000/hr. Returns {query (echoed filters), total, results [{technique_id, name, description (truncated by default), tactics, inherited_tactics, maturity, attack_reference_id, subtechnique_of}], next_calls}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keywordNoSubstring match against technique name + description (case-insensitive). Min 2 chars. Example: 'prompt injection', 'model evasion', 'poisoning'. Omit to list all.
tacticNoFilter by ATLAS tactic id, format 'AML.TA####'. Examples: 'AML.TA0002' (Reconnaissance), 'AML.TA0007' (ML Attack Staging). Omit for all tactics.
maturityNoFilter by maturity: 'demonstrated' (observed in real attacks), 'feasible' (theoretical), or 'realized' (newer ATLAS classification, treat similar to demonstrated). Omit for all.
limitNoMax results to return. Range: 1-200.
includeNoDetail level. Default ('') returns slim records (description truncated to 240 chars; drill via atlas_technique_lookup for full text). Pass 'full' for full description on every row — large catalogs (167 techniques) can return ~100KB at full.
exclude_idNoOptional ATLAS technique id to exclude from results, format 'AML.T####' or 'AML.T####.###'. Useful when chaining from atlas_technique_lookup to fetch siblings without echoing self in the same-tactic search.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

Annotations already declare readOnly, non-destructive, idempotent behavior. The description adds substantial behavioral context: default slim vs full response size (100KB for full catalog), rate limits (free 100/hr, Pro 1000/hr), and return structure. This goes beyond annotations to inform expected performance and output volume.

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 front-loaded with the core purpose and adds details in logical order. It is concise but includes necessary specifics like rate limits and return fields. Minor redundancy (slim vs full behavior mentioned in both description and parameter schema) reduces efficiency slightly.

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?

Given the tool's complexity (6 parameters, rich schema, output schema, annotations), the description covers all essential aspects: purpose, filtering, detail levels, chaining to lookups, rate limits, and expected return shape. It leaves no critical gaps for an agent to understand correct invocation.

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?

Input schema has 100% description coverage, so the baseline is 3. The description adds usage-level context (e.g., chaining with exclude_id, cross-referencing D3FEND) but does not clarify individual parameters beyond what the schema already provides. It meets the baseline without significant additional 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 clearly states it 'Search the MITRE ATLAS catalog of AI/ML attack techniques by keyword, tactic, or maturity', specifying the exact resource and filters. It distinguishes from sibling `atlas_technique_lookup` by describing drill-down usage and from `atlas_case_study_search` via different content (techniques vs case studies).

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 explains when to use this tool (discover techniques for threat-model questions) and provides guidance on parameter use: `include='full'` for verbose records, `exclude_id` for chaining from lookup, and mention of drilling into `atlas_technique_lookup`. It lacks explicit when-not-to-use statements but covers key usage scenarios well.

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/UPinar/contrastapi'

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