Skip to main content
Glama

ContrastAPI

by com.contrastcyber

ATLAS Technique Search

atlas_technique_search
Read-onlyIdempotent

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: 30/hr, Pro: 500/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
limitNoMax results to return. Range: 1-200.
tacticNoFilter by ATLAS tactic id, format 'AML.TA####'. Examples: 'AML.TA0002' (Reconnaissance), 'AML.TA0007' (ML Attack Staging). Omit for all tactics.
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.
keywordNoSubstring match against technique name + description (case-insensitive). Min 2 chars. Example: 'prompt injection', 'model evasion', 'poisoning'. Omit to list all.
maturityNoFilter by maturity: 'demonstrated' (observed in real attacks), 'feasible' (theoretical), or 'realized' (newer ATLAS classification, treat similar to demonstrated). Omit for all.
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

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses critical behavioral traits: default SLIM responses with 240-char truncation, include='full' toggle with size warning (~100KB), rate limits (30/hr free, 500/hr Pro), and the return structure including next_calls. There is no contradiction with 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 but logically ordered: purpose, default behavior, usage guidance, rate limits, and return format. Every clause adds operational value without restating schema fields verbatim. Length is appropriate given the richness of context provided.

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 6-parameter tool with all optional inputs, the description covers discovery use cases, drill-down paths, cross-reference bridges, rate limits, and the full output schema. It leaves no ambiguity about what the agent will receive or how to chain subsequent calls.

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 the baseline is 3. The description adds value by explaining the purpose of exclude_id ('skip self in sibling-tactic searches'), the exact truncation length, and the performance impact of include='full' on a 167-technique catalog. These nuances are not present in the schema, earning a 4.

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 ('Search') and names the resource ('MITRE ATLAS catalog of AI/ML attack techniques') with clear search facets (keyword, tactic, maturity). It effectively distinguishes from the sibling lookup tool by positioning this as the discovery entry point and explicitly directing users to atlas_technique_lookup for full details.

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?

It explicitly states when to use this tool ('Use this to discover techniques matching a threat-model question') and provides concrete chaining guidance (exclude_id, drill into atlas_technique_lookup). It also names the downstream cross-reference path via d3fend_defense_for_attack, covering both tool selection and follow-up steps.

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

All ContrastAPI toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, with differences between lookup/search/scan/audit for each domain. However, some overlap exists (e.g., email_mx vs email_security_posture, scan_headers vs contrast_scan) which could cause occasional confusion. Overall, boundaries are well-defined.

Naming Consistency5/5

Tool names follow a consistent verb_noun pattern (e.g., cve_lookup, check_headers, bulk_cve_lookup) with all lowercase underscores. Variations like kev_detail or ssl_check are minor and still predictable. No chaotic mixing of conventions.

Tool Count4/5

54 tools is high but justified by the broad cybersecurity scope (CVE, ATLAS, D3FEND, Sigma, domain, email, IOC, scanning). Some redundancy exists (e.g., three email-related tools), but the count is not excessive given the API's comprehensive feature set.

Completeness5/5

The tool set thoroughly covers the threat intelligence and domain investigation lifecycle: CVE/KEV/exploit/CWE, ATLAS/D3FEND/Sigma, DNS/WHOIS/SSL/subdomains, email security, IOC enrichment, and active scanning. No significant gaps are apparent for the stated cybersecurity purpose.

Resources