ContrastAPI

Look up Autonomous System Number (ASN) for a domain or IP: AS number, organization, IPv4/IPv6 prefixes. Use to identify network operator and IP range ownership. Default returns first 50 prefixes per family — set include_full_prefixes=True for full list. Free: 30/hr, Pro: 500/hr. Returns {asn, asn_name, ipv4_prefixes, ipv6_prefixes, ipv4_count, ipv6_count}.

Look up a MITRE ATLAS case study — a documented real-world AI/ML attack incident. Each case study links a sequence of ATLAS techniques (techniques_used) to the incident. Default response is SLIM (description truncated to 240 chars); pass include='full' for the verbose narrative. Use this after atlas_technique_search to find which incidents have exercised a given technique. Drill into the full techniques_used array via bulk_atlas_technique_lookup in a single call (next_calls emits exactly that hint). Returns 404 when the id is not in the synced catalog. Free: 30/hr, Pro: 500/hr. Returns {case_study_id, name, description, techniques_used, next_calls}.

Search ATLAS case studies (real-world AI/ML attack incidents) by keyword or referenced technique. Default response is SLIM (description truncated to 240 chars per row); pass include='full' for the verbose summary. Useful when the user has a technique in hand and wants to see incidents that exercised it. Drill via atlas_case_study_lookup for the full procedure list. Free: 30/hr, Pro: 500/hr. Returns {query, total, results [{case_study_id, name, description (truncated by default), techniques_used}], next_calls}.

Look up a MITRE ATLAS technique — the AI/ML adversarial attack catalog. ATLAS catalogues TTPs targeting machine learning systems: prompt injection, model evasion, training data poisoning, model theft, etc. Roughly 80% of ATLAS techniques are AI/ML-specific (no ATT&CK bridge); 20% mirror an enterprise ATT&CK technique via attack_reference_id — use that to pivot to D3FEND defenses (d3fend_defense_for_attack) and CVE search. Sub-techniques inherit `tactics` from the parent (inherited_tactics=true flag) when ATLAS upstream leaves them empty. Use this tool when the user asks about AI/ML threats, LLM red-teaming, or adversarial ML; for multiple techniques in one call (e.g. drilling into a case study's techniques_used), prefer bulk_atlas_technique_lookup. Returns 404 when the id is not in the synced ATLAS catalog. Free: 30/hr, Pro: 500/hr. Returns {technique_id, name, description, tactics, inherited_tactics, maturity (demonstrated|feasible|realized), attack_reference_id, attack_reference_url, subtechnique_of, created_date, modified_date, next_calls}.

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}.

Perform comprehensive domain audit: combines domain_report + live HTTP security headers + technology fingerprinting. By default report.dns.txt is filtered to security-relevant entries (SPF, DMARC, DKIM, MTA-STS, TLS-RPT) and report.dns.total_txt_records reports the honest pre-filter count; pass include_all_txt=true for the raw TXT list. Use when you need the full picture (recon + active checks); use domain_report for passive-only assessment. Response carries next_calls — chain with subdomain_enum (always emitted) and ssl_check (when an A record resolves) for the residual recon depth (tech_fingerprint already inline as `technologies`). Free: 30/hr (costs 6 tokens), Pro: 500/hr. Returns {domain, report, technologies, live_headers, summary, next_calls}.

Scrape a domain's homepage `<head>` for public brand assets — favicon, og:image, theme-color, og:site_name, JSON-LD `Organization.logo`. Use to enrich CRM records, build company-card UIs, or correlate a lead's site to their visual identity (no manual screenshot required). Strictly homepage-only (path `/`); we do NOT crawl. Ethical floor: target's robots.txt is honoured — `Disallow: /` for ContrastAPI OR `*` returns 403 `error.code = robots_txt_disallow` and we DO NOT fetch. `Cache-Control: no-store` / `private` from the target is respected (response is built but NOT written to our cache; `cache_respected=false` flags this). Per-target eTLD+1 throttle (60 req/min) prevents weaponising via subdomain rotation. All URL fields are absolute and `_untrusted` (DO NOT execute or shell-out — the target controls these strings). Free: 30/hr, Pro: 500/hr. Returns {domain, fetched_url, status_code, favicon_url_untrusted, og_image_url_untrusted, theme_color, site_name_untrusted, logo_url_untrusted, cache_respected, summary}. Returns 502 on DNS/TCP/TLS failure; 403 `robots_txt_disallow` when the target opted out.

Bulk ATLAS technique lookup — retrieve full records for up to 50 techniques in a single request instead of N separate atlas_technique_lookup calls. Designed as the natural follow-up to atlas_case_study_lookup, whose techniques_used array can be passed directly. Each item is the same shape as atlas_technique_lookup, including parent-tactics inheritance for sub-techniques (inherited_tactics=true flag) and per-item next_calls (D3FEND bridge when attack_reference_id present, sibling-technique search by tactic, parent lookup for sub-techniques). Free: 30/hr (1 per item), Pro: 500/hr. Returns {results [{technique_id, status (ok|not_found|invalid_format), technique, error}], total, successful, failed, partial, summary}.

Batch query multiple CVEs (up to 50 per call, same for Free and Pro): retrieve full CVE details for all in 1 request instead of N. By default each CVE's affected_products is truncated to the first 20 entries (total_products reports honest count) and references to the first 10 (total_references reports honest count); pass include_affected_products=true / include_full_references=true to return full lists. Pass include_reference_tags=true to receive references_full=[{url, tags, source}] per CVE in the batch. Pass include_severity_breakdown=true to receive severity_sources/consensus/disagreement per CVE. Use for dependency audits or bulk vulnerability enrichment; use cve_lookup for single CVE. Each successful item carries next_calls — chain with kev_detail (when kev.in_kev=true), cwe_lookup (when cwe_id is present), or exploit_lookup. Free: 30/hr (1 per item), Pro: 500/hr. Returns {results, total, successful, failed, timed_out, partial, summary}.

Batch query multiple IOCs (IP/domain/URL/hash, up to 50 per call, same for Free and Pro) in 1 request: auto-detects type + queries abuse.ch feeds per-indicator. Per-type source coverage matches ioc_lookup: hash → ThreatFox only; IP → ThreatFox + Feodo + URLhaus; domain / URL → ThreatFox + URLhaus. Each result item carries its own verdict.sources_queried / sources_unavailable so partial failures are visible per indicator. Use for SOC alert triage or batch enrichment; use ioc_lookup for single indicator. Free: 30/hr (1 per item), Pro: 500/hr. Returns {results, total, successful, failed, timed_out, partial, summary}.

Bulk Sigma rule lookup — retrieve full records for up to 50 rule UUIDs in a single request instead of N separate sigma_rule_lookup calls. Designed for triage workflows where multiple rule ids are known (e.g., from a SIEM alert batch or a tagged detection bundle). Each item is the same shape as sigma_rule_lookup with status ok/not_found/invalid_format and an error field when applicable. Up to 50 rule ids per call (same cap for Free and Pro). Each rule_id consumes 1 unit of the hourly quota; ids beyond the caller's remaining quota land in skipped_due_to_rate_limit instead of failing the whole batch (parity with bulk_cve/ioc). Free: 30/hr, Pro: 500/hr. Returns {results [{rule_id, status, rule, error}], total, processed, skipped_due_to_rate_limit, successful, failed, partial, summary, next_calls}.

Composite CVE risk score (0-100) — fuses CVSS, EPSS, KEV, and PoC into a single agent-ready triage signal. Formula: CVSS*0.20 + EPSS*0.35 + KEV*0.30 + PoC*0.15 (each component rescaled to 0-100 before weighting). Multiplicative boosters applied in order: KEV+PoC combo (*1.15), critical-severity-with-high-EPSS (CVSS>=9 AND EPSS>0.7, *1.10), recently published (within last 7 days, *1.05). Final score clamped to [0, 100]. Label bands: CRITICAL>=90, HIGH>=70, MEDIUM>=40, LOW<40. Urgency text encodes patch SLA (immediate when KEV; 24h/72h/30d by label). Use to triage a single CVE without orchestrating cve_lookup + exploit_lookup separately. PoC signal here is the local ExploitDB mirror only — for full multi-source exploit detail (GitHub Advisory + Shodan refs + ExploitDB), call exploit_lookup separately. Methodology adapted from mukul975/cve-mcp-server (Apache-2.0): https://github.com/mukul975/cve-mcp-server. Free: 30/hr, Pro: 500/hr. Returns {cve_id, score (0-100), label (CRITICAL/HIGH/MEDIUM/LOW), urgency, has_public_poc, components (cvss_v3, epss_score, in_kev, has_public_poc, weighted_breakdown), boosters_applied, recommendation, summary, verdict, next_calls}.

Audit project dependencies (npm/PyPI/Maven/RubyGems/etc.) against CVE database: find known vulnerabilities in your package list. Bulk query up to 50 packages per call (same for Free and Pro). Use for dependency security scanning; use cve_lookup for single CVE. Free: 30/hr (1 per package), Pro: 500/hr. Returns {findings, total, by_severity, summary}. Each finding includes fixed_in (first patched version per NVD/MITRE version range) when a version range matched — omitted from wire when the range is open-ended or no input version was supplied; remediation copy then says 'Check if ... is affected ... and upgrade if so' instead of 'Upgrade to X.Y.Z or later'.

Validate HTTP security headers you provide (JSON): CSP, HSTS, X-Frame-Options, X-Content-Type-Options, Permissions-Policy, Referrer-Policy against best practices. Use to test header config before deployment or validate non-public servers; use scan_headers to fetch live. Free: 30/hr, Pro: 500/hr. By default header values are truncated to 500 chars; pass include='full' for the full raw value. Returns {total, by_severity, findings}. No external requests.

Scan source code for injection vulnerabilities: SQL injection, command injection, path traversal via unsafe string concatenation/unsanitized input. Supports Python, JavaScript, TypeScript, Java, Go, Ruby, Shell, Bash. Use to detect input-handling bugs; for secrets use check_secrets. Companion code-security tools: check_secrets (hard-coded credential detection), check_dependencies (known-CVE vulnerability audit), check_headers (live HTTP security-header validation), scan_headers (live HTTP scan via domain). Free: 30/hr, Pro: 500/hr. Returns {total, by_severity, findings}. No data stored.

Scan source code (or snippet) for hardcoded secrets — cloud provider keys, API tokens, connection strings, private keys, passwords. Supports Python, JavaScript, TypeScript, Java, Go, Ruby, Shell, Bash. Use to detect leaked credentials before commit; for injection detection use check_injection. Free: 30/hr, Pro: 500/hr. Returns {total, by_severity, findings}. No data stored. The generic password-assignment rule is suppressed when a more-specific credential rule fires on the same line — one targeted finding per leaked secret, not two.

Active website security scan: runs the ContrastScan C engine (11 modules — HTTP security headers, SSL/TLS, DNS, redirect chain, information disclosure, cookie flags, DNSSEC, HTTP methods, CORS, HTML hygiene, deep CSP analysis) against the live site and enriches the raw result with severity-ranked vulnerability findings and a letter grade. Use for a hands-on misconfiguration scan; use audit_domain for passive recon (DNS/WHOIS/SSL/threat intel) and scan_headers for headers only. Active outbound fetch — a per-target eTLD+1 throttle (60 req/min) applies. Free: 30/hr (costs 6 tokens), Pro: 500/hr. Returns {domain, resolved_ip, total_score, max_score, grade, findings, findings_count, headers, ssl, dns, redirect, disclosure, cookies, dnssec, methods, cors, html, csp_analysis, enterprise, summary, next_calls}.

List CVEs indexed from MITRE/GHSA BEFORE NVD publication (early-warning, freshest data). By default each result is slim (no description, no cvss_breakdown, no affected_products list, no references) — pass include='full' for the same payload shape as cve_lookup; for drill-down on a single CVE prefer cve_lookup. Use for threat intelligence on emerging CVEs; use cve_search for published NVD data. Verdict (sources_queried, falsifiable_fields, completeness, data_age) is at the response root — applies to the whole batch, not per-row. Response carries a global hint pointing at cve_lookup — drill into any returned cve_id for full detail and chained pivots (exploit_lookup, kev_detail, cwe_lookup). Free: 30/hr, Pro: 500/hr. Returns {count, total, truncated, offset, summary, results, next_offset, verdict, hint}.

Retrieve detailed CVE data by ID: description, CVSS v3.1 + vector, CVSS v2 (always emitted), EPSS score + percentile, CISA KEV status (expanded: due_date, required_action, ransomware flag, vendor_project, product, vulnerability_name, short_description, notes, cwes, date_removed when in_kev=true), NVD vulnerability_status (Analyzed/Modified/Awaiting Analysis/Deferred/Rejected/Withdrawn), cve_tags ('disputed' triggers [DISPUTED] summary prefix), affected products (CPE), references, patch availability, related CVEs. By default affected_products is truncated to the first 20 entries (total_products reports the honest count) and references to the first 10 (total_references reports the honest count). Pass include_affected_products=true and/or include_full_references=true for the complete lists. Pass include_reference_tags=true to receive structured references_full=[{url, tags, source}] (NVD upstream tags + source provenance) — also activates tag-first patch detection. Pass include_severity_breakdown=true to receive severity_sources/consensus/disagreement (multi-source view of NVD/MITRE/GHSA/OSV severity assessments). Use for single-CVE details; use cve_search for queries by product/severity. Response carries next_calls — chain with kev_detail when kev.in_kev=true, with cwe_lookup on each CWE in cwes (up to 3 pivots), and with exploit_lookup for public PoC availability. Free: 30/hr, Pro: 500/hr. Returns {cve_id, summary, description, severity, cvss_v3, cvss_v2, cvss_v2_vector, cvss_breakdown, cwe_id, cwes, vulnerability_status, cve_tags, published, modified, sources, first_seen_source, first_seen_at, epss, kev (in_kev, date_added, due_date, required_action, known_ransomware_use, vendor_project, product, vulnerability_name, short_description, notes, cwes, date_removed), affected_products (first 20 by default), total_products, references (first 10 by default), total_references, total_references_unique, references_full (only when include_reference_tags=true), severity_sources…

Search CVE database with filters: product/vendor, severity, published date range, EPSS score, CWE, CVSS range, CISA KEV status. Default response is SLIM per-result (cve_id, summary, severity, cvss_v3, cwe_id, epss, kev, total_products, published, modified, sources) — pass include='full' for description, cvss_breakdown, affected_products, references, first_seen_*. Verdict (sources_queried, falsifiable_fields, completeness, data_age) is at the response root — applies to the whole batch, not per-row. Product/vendor filters are EXACT NVD-canonical-token matches (not the common name — e.g. nginx is 'nginx_open_source'/'nginx_plus', vendor 'f5'); a low/zero count for a well-known product means the token differs, so for dependency/package lists use check_dependencies and for a domain's whole stack tech_stack_cve_audit (both auto-normalize tokens). Use for vulnerability discovery by criteria; pass cwe_id (e.g. CWE-79) to enumerate every CVE in our database mapped to a weakness — pair with cwe_lookup for the category description and mitigations. Use cve_lookup for single CVE by ID, kev_detail when kev=true filtering and the agent needs federal patch deadlines per result. Response carries a global hint pointing at cve_lookup — drill into any returned cve_id for full detail and chained pivots (exploit_lookup, kev_detail, cwe_lookup). Free: 30/hr, Pro: 500/hr. Returns {count, total, truncated, offset, summary, results, query_echo, next_offset, verdict, hint}.

Look up MITRE CWE (Common Weakness Enumeration) catalog record from research view 1000. Default response is SLIM (first 3 mitigations, first 3 examples; extended_description is null) — pass include='full' for the verbose record (full mitigations + examples lists, populated extended_description). Returns description, abstract type (Pillar/Class/Base/Variant/Compound), status (Stable/Draft/Incomplete/Deprecated), exploit likelihood, recommended mitigations, observed example CVEs, parent_cwe (walk up the hierarchy), child_cwes (drill down to more specific weaknesses), and cve_count (LOWER BOUND — counts only CVEs whose primary CWE matches; CVEs with multiple CWEs may not be counted). Use after cve_lookup or kev_detail to understand the underlying weakness category; chain with cve_search(cwe_id=...) to enumerate all matching CVEs. Returns 404 when the CWE is not in research view 1000. Free: 30/hr, Pro: 500/hr. Returns {cwe_id, name, description, extended_description (null on slim, populated on include='full'), abstract_type, status, likelihood, mitigations (first 3 by default), total_mitigations, examples (first 3 by default), total_examples, parent_cwe, child_cwes, cve_count, updated_at, verdict, next_calls}.

Batch coverage breakdown: given a list of ATT&CK T-codes, return distinct defense counts per D3FEND tactic + identify which techniques have NO D3FEND mapping (undefended_techniques). Use to assess the defensive posture of an entire attack campaign or threat model in one call. defended_techniques is the subset with at least one D3FEND defense; undefended_techniques are gaps worth flagging. Pair with cve_search per gap to identify exploit availability. Free: 30/hr, Pro: 500/hr. Returns {queried_techniques, coverage_by_tactic, defended_techniques, undefended_techniques, next_calls}.

Reverse lookup: given an ATT&CK T-code, return D3FEND defenses that mitigate it. This is the bridge from offensive intelligence (ATT&CK / ATLAS / CVE) to defensive playbook. Pair with cve_lookup or atlas_technique_lookup output — when those carry an ATT&CK id, call this tool to surface the mitigations. `defenses` is capped at `limit` (default 30) for token efficiency; `total` is the honest pre-truncation count and `truncated=true` flags when the cap was hit. `coverage_by_tactic` always aggregates the FULL set, not the slice. Default response is SLIM (drops `uri` from each row); pass include='full' for the verbose record. Pass exclude_id when drilling from d3fend_defense_lookup to skip self in the 'see also' list. Returns 200 with empty defenses list when the T-code has no D3FEND mapping (the gap is itself a signal). Free: 30/hr, Pro: 500/hr. Returns {attack_technique_id, total, truncated, defenses [{defense_id, label, uri (only when include=full), parent_label, tactic, artifact, attack_label, attack_tactic}], coverage_by_tactic, next_calls}.

Look up a MITRE D3FEND defense technique. D3FEND is the canonical defensive counterpart to ATT&CK — each defense is classified into one of 7 tactics (Model/Harden/Detect/Isolate/Deceive/Evict/Restore) and may target a specific digital artifact (e.g. 'Access Token'). Response includes attack_techniques: the list of ATT&CK T-codes this defense mitigates. Use after d3fend_defense_search for the full record + ATT&CK chain. Returns 404 when the slug is not in the synced D3FEND catalog. Free: 30/hr, Pro: 500/hr. Returns {defense_id, label, uri, parent_label, description, tactic, artifact, attack_techniques, next_calls}.

Search the MITRE D3FEND catalog of defensive techniques by keyword, tactic, or targeted artifact. Default response is SLIM (drops `uri` from each row — saves ~60 chars/row, ~30% on popular drills); pass include='full' for the verbose record. Pass exclude_id when chaining from d3fend_defense_lookup to skip self in sibling-artifact searches. Use to discover defenses applicable to a given threat model — e.g. 'what defenses harden access tokens?' (tactic=Harden + artifact='Access Token'). Drill into d3fend_defense_lookup with any returned defense_id for the ATT&CK technique mappings. Free: 30/hr, Pro: 500/hr. Returns {query, total, results [{defense_id, label, uri (only when include=full), parent_label, tactic, artifact}], next_calls}.

Query all DNS record types (A, AAAA, MX, NS, TXT, CNAME, SOA) for a domain. Use for mail routing inspection, nameserver verification, or SPF/DMARC checks; for full overview use domain_report. TXT records are returned raw (no filter) — `total_txt_records` always carries the honest count (use domain_report for the security-only filtered TXT view). Free: 30/hr, Pro: 500/hr. Returns {domain, records: {a, aaaa, mx, ns, txt, total_txt_records, cname, soa}, summary}.

Query DNS, WHOIS, SSL, subdomains, and threat intel for a domain in one call. By default dns.txt is filtered to security-relevant entries (SPF, DMARC, DKIM, MTA-STS, TLS-RPT) and dns.total_txt_records reports the honest pre-filter count; pass include_all_txt=true for the raw TXT list. Use as a starting point for domain investigations; use audit_domain for live headers + tech stack. Response carries next_calls — chain with subdomain_enum (always emitted), ssl_check + tech_fingerprint (when an A record resolves) for the standard recon depth without re-prompting. Free: 30/hr, Pro: 500/hr. Returns domain report with DNS records, WHOIS data, SSL cert, risk score, email config, threat status, recommendation, and next_calls.

Check if email address uses a known disposable/temporary provider (Guerrilla Mail, Temp Mail, Mailinator, etc.). Use for input validation to detect throwaway signups; for domain reputation use threat_intel. Companion email-investigation tools: email_mx (deliverability + MX trust), domain_report on the email's domain (full recon), threat_intel (malware-distribution signal on the domain). Free: 30/hr, Pro: 500/hr. Returns {disposable, domain, provider}.

Analyze email security: MX records, SPF policy, DMARC policy, DKIM probe across common+date-based selectors, mail provider, grade. Use to verify email-auth setup and phishing risk; for full audit use domain_report. Free: 30/hr, Pro: 500/hr. email_security.dkim_status reports honest evidence: 'verified' iff at least one selector responded, else 'unverifiable' (custom selectors cannot be discovered without prior knowledge). Grade: when DKIM verified, A=SPF+DMARC+DKIM/B=2of3/C=1of3; when DKIM unverifiable, A=SPF+DMARC/B=one/F=neither — DKIM absence is NOT penalized because it is unprovable in DNS. Returns {mx_records, mail_provider, email_security:{spf, dmarc, dkim_selectors, dkim_status, grade, issues}, summary}.

Analyze domain email authentication posture: SPF, DMARC, DKIM with numeric score and findings. Dual-use: red-team (spoofing feasibility) + blue-team (posture audit). Score 0-100, grades A+-F. DKIM probing tests common selectors + recent dates; custom selectors must be supplied. Passive DNS-only; no SMTP probe. Free: 30/hr, Pro: 500/hr.

One-call email validation combining syntax + MX records + disposable check + role-address detection (admin@/info@/...) + free-provider classification (gmail/outlook/yahoo/...). Use BEFORE adding an email to a contact list, sending an outbound message, or auditing a lead-list dump — replaces 2-3 tool calls (email_mx + email_disposable + manual role parse) with one structured response. Deliberately does NOT do SMTP `RCPT TO` deliverability probing — Hunter.io / NeverBounce-style mailbox enumeration is an ethical grey area we declined; use those services if you need that specific signal. role_address=true on `admin@`, `info@`, `noreply@`, `support@`, etc. (Gmail-style `+tag` is stripped before classification). free_provider=true on consumer-mailbox domains (B2B detection signal — a 'work' email at `@gmail.com` likely isn't a corporate user). Free: 30/hr, Pro: 500/hr. Returns {email, domain, syntax_valid, mx_records, disposable, disposable_provider, role_address, role_type, free_provider, summary}.

Search public exploits/PoC for a specific CVE across three sources: (1) GitHub Advisory Database (sources.github.advisories[]), (2) Shodan CVEDB references (sources.shodan_refs.results[] — packetstorm/seclists/vendor URLs cited by Shodan; results capped at SHODAN_REFS_LIMIT default 200, truncated=true when capped, count is the honest upstream total), (3) ExploitDB CSV mirror (exploits[] array, with edb_id + author + verified flag — these are the actual ExploitDB entries). Use to assess if a vulnerability has weaponized exploits in the wild; run after cve_lookup to evaluate real-world risk. When the CVE is also in CISA KEV (kev.in_kev=true on cve_lookup), pair with kev_detail for federal patch deadline; pair with cwe_lookup on cwe_id for the underlying weakness category and mitigations. Response carries next_calls — single cve_lookup pivot for full context (KEV status, CWE chain, CVSS, EPSS); cve_lookup's own next_calls then surface kev_detail and cwe_lookup automatically (this endpoint has no in_kev/cwe_id schema, so blind emission of those pivots is intentionally avoided). Free: 30/hr, Pro: 500/hr. Returns {cve_id, exploits_found, has_public_exploit, sources: {github, shodan_refs: {found, count, truncated, results}}, exploits: [{edb_id, cve_id, date_published, author, type, platform, url, verified, description}], summary, verdict, next_calls}.

Deterministic GEO / AI-visibility readiness audit of a domain's homepage with a 0-100 score + a `missing_signals` fix list. Answers "can AI assistants (ChatGPT, Claude, Perplexity, Google AI) discover, crawl, and recommend this site?" using STRUCTURAL signals ONLY — no LLM is queried, fully deterministic. 7 weighted rules: llms.txt present (15), AI-crawler robots.txt access — 9 crawlers incl. GPTBot/ClaudeBot/PerplexityBot/Google-Extended/CCBot (25 — the dominant signal; blocking = invisible to that AI surface), schema.org @type coverage Organization/Product/FAQPage (20), server-side rendering vs client-only SPA (15 — a JS-only SPA serves AI crawlers empty HTML), discovery signals og/canonical/sitemap (10), semantic headings single-H1 + H2 structure (10), competitor-comparison content (5). Use to triage why a brand is absent from AI recommendations, as a pre-flight before GEO/AEO content work, or to score a prospect's AI-readiness. Strictly homepage-only — we do NOT crawl. Ethical floor: target's robots.txt is honoured — `Disallow: /` for ContrastAPI returns 403 `error.code = robots_txt_disallow` and we DO NOT fetch. `Cache-Control: no-store`/`private` skips our cache write (`cache_respected=false`). Per-target eTLD+1 throttle (60 req/min). Free: 30/hr, Pro: 500/hr. Returns {domain, fetched_url, status_code, llms_txt_present, ai_crawlers_total, ai_crawlers_allowed, ai_crawlers_blocked, schema_types, client_side_rendered, render_framework, has_canonical, og_tag_count, sitemap_count, h1_count, h2_count, comparison_content, score, missing_signals, cache_respected, summary}. Returns 502 on DNS/TCP/TLS failure; 403 `robots_txt_disallow` when the target opted out.

Parse a CVSS v3.x vector string into a per-metric breakdown plus a recomputed base score. Returns the canonicalized vector, version (3.0 or 3.1), base_score, base_severity (NONE/LOW/MEDIUM/HIGH/CRITICAL), and the eight base metrics: attack_vector (NETWORK/ADJACENT_NETWORK/LOCAL/PHYSICAL), attack_complexity (LOW/HIGH), privileges_required (NONE/LOW/HIGH), user_interaction (NONE/REQUIRED), scope (UNCHANGED/CHANGED), and the three impact metrics confidentiality_impact / integrity_impact / availability_impact (NONE/LOW/HIGH each). When temporal/environmental metrics are explicit in the vector, temporal_score and environmental_score are populated separately. Use to translate raw CVSS strings into agent-friendly attributes without re-parsing the vector grammar yourself, and to verify upstream NVD scoring against the recomputed value. v2 vectors (AV:N/AC:L/Au:N/...) are rejected with 400 — read cvss_v2_vector from cve_lookup if you need v2 detail. Free: 30/hr, Pro: 500/hr. Returns {version, vector, base_score, base_severity, metrics: {attack_vector, attack_complexity, privileges_required, user_interaction, scope, confidentiality_impact, integrity_impact, availability_impact}, temporal_score, environmental_score, summary, verdict}.

Query MalwareBazaar for file hash (MD5/SHA1/SHA256): malware family, file type, size, tags, first/last seen, download count. Use to check if file hash is known malware; use ioc_lookup for auto-detection of all IOC types. Companion malware-investigation tools: ioc_lookup (multi-source: ThreatFox + Feodo Tracker + URLhaus), threat_intel (domain-level URLhaus check), exploit_lookup (link a known CVE to PoC code if the hash maps to an exploit binary). Free: 30/hr, Pro: 500/hr. Returns {found, malware_family, file_type, file_size, tags, first_seen, last_seen, signature}.

Enrich Indicator of Compromise (IP/domain/URL/hash) by auto-detecting type and querying abuse.ch feeds. Per-type source coverage: hash → ThreatFox only (Feodo and URLhaus do not index hashes); IP → ThreatFox + Feodo Tracker + URLhaus; domain / URL → ThreatFox + URLhaus. verdict.sources_queried lists what actually ran; verdict.sources_unavailable lists what failed (timeout / upstream error). Use as primary IOC triage tool when type unknown; use threat_intel for domain-only, hash_lookup for richer MalwareBazaar hash data. Free: 30/hr, Pro: 500/hr. Returns {indicator, type, threat_level, sources, summary, verdict}.

Query comprehensive IP intelligence: reverse DNS, ASN + holder name + country inline (RIPE Stat, Phase 1), open ports, hostnames, vulnerabilities (Shodan InternetDB enriched with severity + cvss_v3 from local cve.db — Phase 2 v1.16.0 BREAKING; vulns is now list[VulnInfo] {cve_id, severity, cvss_v3} dicts, pre-1.16 it was list[str] of CVE IDs; unknown CVEs emit severity='UNKNOWN' / cvss_v3=null — do NOT infer benign), cloud provider, Tor exit status, and reputation. cloud_provider uses two-tier detection: published cloud CIDR ranges (AWS/GCP/Cloudflare) first, then an ASN-to-provider fallback map for anycast/public-service IPs outside published ranges (e.g. 8.8.8.8 → AS15169 → 'Google'). Reputation: FireHOL level1 blocklist on Free tier; +AbuseIPDB + Shodan on Pro (Phase 4). Use for IP investigation; for orchestrated IP+reputation use threat_report. Response is null-explicit: every field is always present (cloud_provider=null when neither tier matches; tor_exit=false when not listed or upstream fetch failed — check verdict.sources_unavailable to disambiguate fetch failure from genuine absence). Response carries next_calls (conditional) — asn_lookup when ASN is populated, ioc_lookup when reputation is FireHOL-listed or AbuseIPDB confidence>50, threat_report on Pro tier for orchestrated profile. Free: 30/hr, Pro: 500/hr. Returns {ip, ptr, geo, asn, asn_name, country, ports, hostnames, vulns, cloud_provider, tor_exit, reputation, risk_score, verdict, next_calls}.

Look up CISA KEV (Known Exploited Vulnerabilities) full record for a CVE. Returns federal patch deadline (due_date), CISA-specified required_action remediation, known ransomware association, vendor/product, the CISA-given common name (e.g. 'Log4Shell'), CISA-reported CWE list, plus lifecycle metadata: date_updated (when CISA last revised the entry), date_removed (set when CISA removed the CVE from the catalog — null while still active), and updated_at (our DB sync freshness). Returns 404 when the CVE is not in the KEV catalog — use cve_lookup for non-KEV CVEs. Best follow-up after cve_lookup or cve_search(kev=true) when an in_kev=true CVE is identified; chain with cwe_lookup on each returned CWE to investigate the weakness category. Free: 30/hr, Pro: 500/hr. Returns {cve_id, vendor_project, product, vulnerability_name, date_added, due_date, required_action, known_ransomware_use, notes, cwes, date_updated, date_removed, updated_at, verdict, next_calls}.

Check if SHA-1 hash appears in Have I Been Pwned (HIBP) breach dataset using k-anonymity (5-char prefix only, full hash never leaves tool). Use for password breach audits; read-only, no data stored. Companion OSINT investigation tools: hash_lookup (file-hash malware family lookup, different namespace), email_disposable (throwaway-mail signal on associated accounts), username_lookup (social-platform exposure on associated handles). Free: 30/hr, Pro: 500/hr. Returns {found, count}.

Query URLhaus for a specific URL and its host. is_malicious is True only when there is ACTIVE evidence — exact URL match with url_status='online' (or unknown) OR host has urls_online > 0. URLhaus retains historical records forever, so a host can have url_count > 0 with urls_online == 0; in that case is_malicious=False, is_stale=True, threat_level='low'. Use for URL-level threat assessment; use threat_intel for domain-level checks. Companion threat-investigation tools: ioc_lookup (multi-source IOC: ThreatFox + URLhaus + Feodo Tracker, auto-detect type), hash_lookup (file-hash malware family, MalwareBazaar), threat_intel (domain-level URLhaus only). Free: 30/hr, Pro: 500/hr. Returns {url, host, is_malicious, is_stale, urlhaus_host:{found,urls_online,url_count}, urlhaus_url:{found,threat,tags,status}, threat_level, summary}.

Validate and analyze phone number: country, region, carrier, line type (mobile/landline/VoIP), timezone, formatted versions. Use to verify phone legitimacy and detect fraud risks. Requires E.164 format (+1234567890). Companion OSINT identity-investigation tools: username_lookup (social-platform handle correlation), email_disposable (throwaway-mail signal on associated email). Free: 30/hr, Pro: 500/hr. Returns {valid, country, region, carrier, carrier_status, line_type, timezone, formats}. carrier is omitted from the wire when libphonenumber has no mapping for the region (US/CA/GB and other MNP-restricted regions); always read carrier_status — 'known' means carrier is present, 'unsupported_region' means we cannot identify the carrier (do not infer the number lacks one).

Walk an HTTP redirect chain hop-by-hop, returning per-hop {url, status_code, location, latency_ms}. Use to deobfuscate URL shorteners (bit.ly / t.co / lnkd.in), audit suspicious links from phishing investigations, or trace marketing tracking redirects. SSRF-guarded: each redirect target's resolved IP is re-validated before connecting (private IPs and non-HTTP schemes rejected). Up to 10 hops; loop_detected=true if a hop would revisit a previously-seen URL (we abort before the duplicate fetch); truncated=true if the chain still had a 30x at hop 10. Per-target eTLD+1 throttle (60 req/min) consumed once for the start host AND once per new host reached — a chain across 11 unrelated domains cannot bypass the cap. Free: 30/hr, Pro: 500/hr. Returns {start_url, final_url, hops, hop_count, final_status, loop_detected, truncated, summary}. Returns 502 ErrorResponse on hard fetch failure (timeout / TLS / connect); 429 with Retry-After if a hop's eTLD+1 throttle is exceeded mid-chain.

Fetch + parse the target domain's robots.txt — sitemaps, per-User-agent allow/disallow rules, crawl-delay, Host directive. Use BEFORE crawling/scraping a target site (seo_audit, brand_assets, redirect_chain) to honour the site's published rules. status_code=404 means no robots.txt exists = implicit allow-all per RFC 9309 §2.4. ContrastAPI fetches with `User-agent: ContrastAPI/<version> (+https://contrastcyber.com/bot)` so site operators can identify + opt out via robots.txt; we honour `Disallow: /` for our UA in seo_audit and brand_assets. Per-target eTLD+1 throttle (60 req/min) prevents weaponising this endpoint against a single site; subdomain rotation collapses to the same bucket. Free: 30/hr, Pro: 500/hr. Returns {domain, fetched_url, status_code, sitemaps, user_agents:{ua:{allow,disallow,crawl_delay}}, host, truncated, summary}. Returns 502 ErrorResponse if the target rejected the connection (DNS/TCP/TLS failure); the agent should NOT assume "no robots" in that case — it's an upstream-failure signal.

Perform live HTTP GET and analyze security headers: CSP, HSTS, X-Frame-Options, X-Content-Type-Options, Permissions-Policy, Referrer-Policy. Use to audit live website headers; use check_headers to validate headers you already have. Free: 30/hr, Pro: 500/hr. By default header values are truncated to 500 chars (CSP can exceed 4 KB on large sites); pass include='full' for the full raw value. Returns {headers_present, headers_missing, findings, total_score}.

One-shot SEO audit of a domain's homepage with a 0-100 composite score + a `missing_signals` list of concrete fixes. Use BEFORE pitching SEO work to a prospect, when triaging a lead's marketing maturity, or as a structured pre-flight before deeper auditing tools (Lighthouse / SEMrush). 10 audit rules each worth 10 pts: title present, title length 30-60 chars (Google SERP truncation window), meta description present, meta description length 50-160, exactly one H1, canonical link, >=3 OG tags, JSON-LD present, image alt-text coverage (proportional), HTTPS. Strictly homepage-only — we do NOT crawl the site. Ethical floor: target's robots.txt is honoured — `Disallow: /` for ContrastAPI OR `*` returns 403 `error.code = robots_txt_disallow` and we DO NOT fetch. `Cache-Control: no-store`/`private` skips our cache write (`cache_respected=false` in the response). Per-target eTLD+1 throttle (60 req/min) prevents weaponising via subdomain rotation. All target-derived strings/lists are `_untrusted`. Free: 30/hr, Pro: 500/hr. Returns {domain, fetched_url, status_code, title_untrusted, meta_description_untrusted, canonical_url, h1_untrusted, h1_count, h2_count, h3_count, images_total, images_missing_alt, internal_link_count, external_link_count, og_tags, json_ld_present, score, missing_signals, cache_respected, summary}. Returns 502 on DNS/TCP/TLS failure; 403 `robots_txt_disallow` when the target opted out.

Look up a single Sigma detection rule by UUID from the SigmaHQ corpus (~3,200 rules, refreshed daily at 02:00 UTC). Returns the full rule with title, description, status (stable/test/experimental/deprecated/unsupported), level (informational/low/medium/high/critical), logsource (product/category/service), detection logic, tags (including attack.t#### ATT&CK technique refs and cve.YYYY-#### CVE refs), author, references, and modification date. Use to fetch a known rule for context (e.g., a SIEM detection that fired) or to inspect a rule discovered via REST sigma_rule_search. When a rule tags an ATT&CK technique or CVE, the response next_calls surfaces atlas_technique_lookup / cve_lookup as natural follow-ups. Free: 30/hr, Pro: 500/hr. Returns {rule, next_calls}.

Analyze SSL/TLS certificate: grade (A/B/C/D/F), protocol version, cipher suite, chain, expiry, Subject Alternative Names, and structured validation findings. Invalid certs (expired, self-signed, hostname mismatch, untrusted root) are reported as findings via valid=false + validation_errors[] rather than as endpoint failures, so an unreachable cert still returns useful intel. Grade D = cert readable but invalid; F = expired, legacy TLS, or probe failure. Use to audit certificate validity and detect expiring certs; for full domain audit use audit_domain. Free: 30/hr, Pro: 500/hr. Returns {grade, valid, validation_errors, protocol, cipher, issuer, subject, not_before, not_after, days_remaining, chain, san, warnings}.

Discover subdomains using passive methods: Certificate Transparency logs + DNS brute-force (no active probing). Use to map organization's attack surface; non-intrusive. Response carries next_calls — capped at 5 ssl_check hints (one per first-five subdomain) so triage scales to large enumerations without token bloat; pull tail entries by name when needed. Free: 30/hr, Pro: 500/hr. Returns {domain, count, subdomains, sources, found_via_wordlist, found_via_crtsh, wildcard_status, crtsh_status, warnings, summary, next_calls}. Always check wildcard_status FIRST: 'absent' means the DNS brute-force plane was meaningful; 'present' means the zone answers every name (wildcard DNS) so wordlist results were discarded and count is a certificate-transparency LOWER BOUND — report the surface as UNKNOWN, not small, and never infer low exposure from it; 'undetermined' means a negative-control probe went unanswered, so count is unverified. Then check crtsh_status: 'ok' means the CT lookup completed (so a low count is real); 'timeout' / 'rate_limited' / 'unavailable' / 'error' means CT logs did not respond and the count is wordlist-only — the actual attack surface is likely larger, retry later or surface the limitation to the user.

Detect website technology stack: CMS, frameworks, CDN, analytics tools, web servers, languages (via HTTP headers + HTML analysis). Use for passive reconnaissance; for full audit use audit_domain. Free: 30/hr, Pro: 500/hr. Returns {technologies: [{name, category, confidence%, version}]}.

Composite tech-stack + CVE audit (MCP-only, no REST endpoint). Detects technologies on the target domain, queries CVE database for known vulnerabilities per product, enriches top-10 CVE candidates with CISA KEV federal patch deadlines, and checks public exploit / PoC availability. Identical for every tier — all data is sourced from local DB mirrors (no Shodan/AbuseIPDB), so there is no tier gating. CVE candidate batch: 50. Cost: 10 tokens per call — Free 30/hr ≈ 3 audits, Pro 500/hr ≈ 50 audits. Returns {domain, technologies, cves_by_tech, kev_findings, exploit_findings, summary, next_calls}.