Intel Threadlinqs MCP
The Intel Threadlinqs MCP server provides 49 tools across threat intelligence, detection engineering, IOC analysis, threat actors, MITRE ATT&CK, C2 infrastructure, and composite Purple-tier workflows.
Threat Intelligence
Search/browse 583+ threats by severity, actor, CVE, MITRE technique, sector, malware, campaign, date, etc.
Get full threat details: metadata, CVSS, attribution, CVEs/CWEs, MITRE mappings, IOCs, detections
Bulk fetch up to 20 threats in one call; get enrichment, similar threats, and analysis transcripts
(Purple) Threat hunting bundle: threat detail + IOCs + detections + simulations + infrastructure pivots in one call
Detection Rules
Search/list 5,700+ rules in Splunk SPL, Microsoft KQL, and Sigma YAML
Get full rule content, MITRE mappings, data sources, and false positive guidance
Export rules in SPL, KQL, Sigma YAML, or JSON
IOCs & Enrichment
Search 16,500+ indicators (IPs, domains, hashes, URLs, behavioral)
Live enrichment via ThreatFox, MalwareBazaar, AbuseIPDB, and passive DNS
(Purple) IOC intelligence: full dossier with threat/actor attribution, DNS trail, infrastructure pivots, and 7-feed consensus score
Threat Actors
Search 334+ actors by name, alias, nation-state, or motivation
Get actor profiles: TTPs, attributed threats, MITRE rollup, IOC counts
(Purple) Composite actor intelligence: profile + active C2 + cross-actor shared entities + activity timeline
MITRE ATT&CK
Coverage stats across all techniques/tactics with detection counts
Technique detail: mitigations, data sources, linked threats
(Purple) Gap analysis: prioritized uncovered techniques by detection debt score
(Purple) Attack path prediction based on 4,271+ observed technique transitions
C2 Infrastructure
List/analyze 140+ live Cobalt Strike beacons: configs, watermarks, geolocation, operator fingerprints
C2 timeline, cross-correlations, and behavioral clustering
(Purple) Generate firewall-ready IP blocklists by framework, recency, and format
CVE & CWE Intelligence
CVE/CWE details with CVSS, affected products, linked threats, and mitigations
(Purple) CVE intelligence: EPSS velocity, KEV status, exploitation timeline, detection coverage
Daily Intelligence & Correlations
Daily debriefs, recent threats, and full daily intel bundles
7 correlation engines: MITRE heatmap, adversary infrastructure, IOC consensus, CVE velocity, attribution network, detection debt, enrichment health
Pivoting & Entity Resolution
Pivot on malware families, offensive tools, or named campaigns
Normalize actor/malware/tool aliases to canonical forms
Utilities
Health check, platform stats, enrichment overview, changelog, and roadmap
Provides Splunk SPL detection rules for threat detection and hunting across the threat intelligence corpus.
intelthreadlinqs-mcp
MCP server for Threadlinqs Intelligence — 81 tools and 25 analyst-playbook prompts across threat intelligence, detections, IOCs, threat actors, MITRE attack-chains, C2 infrastructure, and Purple-tier composite intelligence. Drop-in for Claude Code, Claude Desktop, Cursor, and any MCP-compatible client.
What this gives your AI agent
1,700+ threats with full metadata, severity, attribution, CVE/CWE, MITRE
16,000+ detection rules in Splunk SPL, Microsoft KQL, and Sigma YAML
47,000+ IOCs (IPs, domains, hashes, URLs, behavioral)
500+ threat actors with TTPs profiles and cross-actor infrastructure links
140+ live C2 beacons (Cobalt Strike) with watermark clustering + operator attribution
Daily intelligence debriefs + 7-engine correlation analytics
MITRE attack-chain prediction based on 4,271 observed technique transitions
Related MCP server: Cooper Cyber Coffee OpenCTI MCP Server
Quick install
# No install needed — npx will fetch it
npx -y intelthreadlinqs-mcpClaude Code
claude mcp add threadlinqs-intel \
-e THREADLINQS_API_KEY=tl_your_key_here \
-- npx -y intelthreadlinqs-mcpThe -e THREADLINQS_API_KEY is required in practice. The Threadlinqs Intelligence MCP server is a Purple-tier feature — it checks your key's tier at startup and warns if it is missing, invalid, or below Purple. The server still starts and exposes its tool catalog so clients and registries can introspect it, but tool calls are gated server-side: without a Purple or Gold key (tier ≥ 3) they return an Access denied error instead of data. There is no free or anonymous access to gated intelligence.
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"threadlinqs-intel": {
"command": "npx",
"args": ["-y", "intelthreadlinqs-mcp"],
"env": {
"THREADLINQS_API_KEY": "tl_your_key_here"
}
}
}
}Cursor
.cursor/mcp.json:
{
"mcpServers": {
"threadlinqs-intel": {
"command": "npx",
"args": ["-y", "intelthreadlinqs-mcp"],
"env": {
"THREADLINQS_API_KEY": "tl_your_key_here"
}
}
}
}VS Code
.vscode/mcp.json:
{
"servers": {
"threadlinqs-intel": {
"type": "stdio",
"command": "npx",
"args": ["-y", "intelthreadlinqs-mcp"],
"env": {
"THREADLINQS_API_KEY": "tl_your_key_here"
}
}
}
}Getting an API key
Sign up at intel.threadlinqs.com, verify your email, and head to Profile → API Key. Note that signing up alone lands you on Blue (tier 1) — MCP tool calls need tier ≥ 3, so they return an under-tier error until you upgrade. A 7-day Purple free trial is offered at checkout on the pricing page.
Access — Purple tier only
The MCP server is a Purple-tier feature: all 81 tools require a Purple or Gold subscription (tier ≥ 3). The server checks your key's tier at startup and warns when it is missing, invalid, or below Purple — it still starts and lists its tools so clients can introspect the catalog, but the tier is enforced server-side on every call, so gated tools return Access denied rather than data. There is no free or anonymous access to gated intelligence.
Tier | Price | MCP access |
Purple | $11.99/mo | ✅ All 81 tools |
Gold | Custom | ✅ All 81 tools (team — contact sales) |
Lower tiers | — | ❌ No MCP access (the public website + REST API keep their own free Blue tier) |
A 7-day Purple free trial is available at checkout on the pricing page — it is not granted by signup alone. Tool calls enforce the tier server-side and return a structured 403 if your subscription lapses.
v4.3 flagship tools (Purple tier)
The composite tools are the reason most people upgrade to Purple — each one replaces 5–7 single-purpose MCP calls.
get_threat_hunting_bundle ⭐
Input: threat_id (e.g. "TL-2026-0599")
Returns: complete hunt dossier in one shot — threat metadata, full IOC list, SPL/KQL/Sigma detection queries, similar threats, simulation commands, and cross-threat infrastructure pivots. The single most useful tool in the platform.
get_actor_intelligence
Input: actor name (e.g. "Lazarus Group", "APT29")
Returns: comprehensive adversary picture — actor profile, attributed threats, MITRE techniques, IOCs (200 cap), detection rules (100 cap), activity timeline, active C2 infrastructure correlated to the actor, and cross-actor shared entities.
get_ioc_intelligence
Input: ioc_value (IP, domain, hash, URL)
Returns: every threat that touches the IOC + actor attribution + DNS enrichment trail + cross-IOC infrastructure pivots + consensus confidence score across 7 external feeds (Pulsedive, GreyNoise, YARAify, MalwareBazaar, URLScan, VxVault, OpenPhish). The "I found this in a log — tell me everything" workflow.
get_cve_intelligence
Input: cve_id (e.g. "CVE-2024-3400")
Returns: CVE detail + linked threats + EPSS exploitation velocity + KEV status + detection coverage % + available attack simulations + first-weaponization timeline.
get_mitre_gap_analysis
Input: optional tactic filter, limit
Returns: prioritized list of MITRE techniques without detection coverage, sorted by debt score (threat exposure + KEV count + EPSS). Each entry includes example threats and recommended detection types. Answers "what should I write detections for next?"
predict_mitre_transitions
Input: technique_id (e.g. "T1566"), top_n, direction (forward | reverse)
Returns: ranked next-technique predictions with probability and observation count, plus example threats showing the chain. Built from 4,271 observed transitions across the corpus.
generate_c2_blocklist
Input: none.
Returns: firewall-ready blocklist of active C2 IPs with country, ASN, version, watermark, and last-seen metadata. Currently tracking Cobalt Strike beacons. For operator clustering call get_c2, and for unmasked C2 domains get_c2_dns_intel.
Specialized tools
search_actors— Find threat actors by name, alias, nation-state, or motivation.get_actor— Full actor dossier in a single call.get_similar_threats— Precomputed-similarity matches by shared TTPs, IOC overlap, and same-actor attribution.
Agent skill
A portable skill that teaches any MCP client how to route across these tools — which tool to
call first, the hunt query grammar, the response budget, and the data caveats that keep
answers honest. Generated from the live catalog, so its tool reference cannot drift.
Single file (paste into any assistant): https://intel.threadlinqs.com/mcp/skill.md
Bundle (
SKILL.md+references/, for Claude Desktop / API skill upload): https://intel.threadlinqs.com/skills/intelthreadlinqs-mcp-skill.zipAlso in this repo under
skill/, and linked from https://intel.threadlinqs.com/mcp.
Prompts — 25 analyst playbooks
Prompts are pre-built workflows that orchestrate the tools for you. Rather than working out which of 81 tools to chain, invoke a playbook and the agent gets an ordered, argument-correct plan. Between them they reach every tool on the server, so an agent that only reads prompts/list still finds the whole surface.
Playbook | What it does |
| Start here — catalog, corpus shape, categories, TLQL grammar |
| CVE end-to-end: severity, exploitation, exposure, remediation |
| Actor dossier: TTPs, targeting, attribution confidence |
| Indicator → linked threats, blast radius, blocking action |
| Aggregate questions in TLQL over the hunt index |
| Open-ended research via semantic corpus search |
| Map a threat's SPL/KQL/Sigma to ATT&CK, flag gaps |
| Highest-value detection debt, ranked by exposure |
| Draft a deployable rule grounded in corpus logic |
| Forecast the next (or preceding) ATT&CK techniques |
| Why two threats are linked, with the evidence |
| Campaign members, shared infra, pivotal entities |
| Audit whether an attribution is evidence-backed |
| Pivot across DNS, hosting and adjacent infrastructure |
| Profile a malware family or offensive tool |
| Firewall-ready C2 blocklist with operator clustering |
| Fold community signal in; surface coverage lead time |
| Triage by exploitability, not CVSS alone |
| Simulations paired with the detections they should trip |
| STIX 2.1, ATT&CK Navigator, SIEM-ready rules |
| Batch a list of threat/CVE ids without N round-trips |
| Covered vs uncovered for a CVE, actor or technique |
| Today's posture, top new threats, daily theme |
| Review a day or span from the debrief archive |
| Corpus health, engine state, enrichment completeness |
Full tool catalog
For the complete list of 81 tools with parameters and example invocations, see the interactive MCP documentation page.
Architecture
Transport: stdio (local subprocess)
Auth:
THREADLINQS_API_KEYenvironment variable (Bearer token to the worker API)Runtime: Node ≥18
SDK:
@modelcontextprotocol/sdk@^1.26.0Backend: Cloudflare Workers + D1 (multi-region)
Purple gate: the server checks the API key's tier at startup and warns if it is missing, invalid, or below Purple/Gold (tier ≥ 3) — it starts regardless so the tool catalog stays introspectable; the gate itself is enforced server-side on every tool call (structured 403 on lapse or under-tier)
Introspection has three tiers (since 8.1.0): authenticated
tools/list→ the public/mcp/catalog.json→ a catalog snapshot bundled in the package. The first two need network; the third does not, sotools/listreturns the real catalog even in a fully network-isolated sandbox. Previously that case returned an empty array — not an error, an empty list, which is indistinguishable from a server with no tools, and is why registry scanners indexed this server with zero tools.Maintainers: regenerate the snapshot with
npm run sync:catalogafter deploying the worker, since the worker owns the tool and prompt registries.npm run test:catalogfails the build when the snapshot and the live catalog disagree, and it runs onprepublishOnly.
Links
License
MIT © Threadlinqs
Available Tools
81 toolsbulk_get_cvesBulk Get CVEsARead-onlyIdempotent
Fetch up to 20 enriched CVEs by ID in one call. Returns {cves, missing, count}.
Inputs: cve_ids (required). Returns: cves, count, missing
bulk_get_threatsBulk Get ThreatsARead-onlyIdempotent
Fetch up to 20 threats by ID in one call. Returns LEAN rows by default (identity, severity, attribution, CVEs, targets + counts for MITRE/IOCs/detections/timeline/tags), which is what makes 20 ids actually fit in one response. count is the number of rows actually present in threats[]; unresolvable ids come back in missing. detail="full" returns whole dossiers but is capped at 3 ids per call (a full dossier is ~68 KB) — the overflow is named in deferred_ids, never silently dropped. Drill into any row with get_threat(id).
Inputs: threat_ids (required), detail. Returns: count, detail, missing, threats, +4 more
explain_correlationExplain CorrelationARead-onlyIdempotent
Why two threats are linked: the per-channel similarity decomposition (techniques, IOCs, CVEs, products, CWEs, context), which channel dominates and by how much, the concrete shared artifacts, the signal count, and quality flags for high-confidence/low-evidence and stale links. Use when get_similar_threats gives a score and you need the evidence behind it. Pass the pair in either order. Returns 404 when the engine has no edge between them.
Inputs: threat_a (required), threat_b (required). Returns: error, is_stale, dominance, shared_cves, +5 more
export_detectionExport DetectionARead-onlyIdempotent
Export one detection rule in a specific format. format=spl|kql|sigma returns the raw query text for that flavor; format=json returns the full detection object.
Inputs: format (required), detection_id (required). Returns: format, content, available, detection_id
export_stixExport STIX 2.1 BundleARead-onlyIdempotent
Export a threat, actor, or CVE as a STIX 2.1 bundle for ingestion into a TIP/SIEM. Provide at least one of threat_id, actor, or cve_id. Returns a {type:"bundle", objects:[...]} with indicator (per IOC), attack-pattern (per MITRE technique), intrusion-set (actor), vulnerability (CVE), malware/threat-actor, and relationship objects. Set include_osint=true to add sighting SROs for indicators the community independently reported (TL_OSINT_Scan / tweetfeed.live, CC0) — community-sourced and heavily concentrated, so they carry x_threadlinqs_trust="community-unverified". The bundle is capped (≤200 objects / ≤80KB); a note object is appended if truncated.
Inputs: actor, cve_id, threat_id, include_osint. Returns: id, type, objects
generate_c2_blocklistGenerate C2 BlocklistARead-onlyIdempotent
Compile a firewall-ready C2 blocklist of active command-and-control IPs observed recently. Returns deduplicated network indicators ready to drop into a denylist. Use this for actionable blocking; use get_c2 with view="beacons" when you need the underlying beacon detail.
Inputs: no named parameters. Returns: cidrs, count, detail, since_days, +1 more
get_actorGet Actor ProfileARead-onlyIdempotent
Get a lean threat-actor profile by name or alias: actor metadata, attribution counts, attributed-threat summary rows, MITRE tactic rollup + technique ids, IOC category counts (no raw values), CVE/CWE/tool summaries, and relationships. Tactic keys are canonicalised (the corpus writes both "Credential Access" and "credential-access") and the rollup counts DISTINCT TECHNIQUES per tactic; mitre.technique_ids is capped at 60 against mitre.techniques_total. relationships splits into shared_infra / shared_techniques / shared_tooling with the type re-derived from the value, because corr_attribution types tool names as hashes. An empty actor_relationships means UNRECORDED, not unrelated — see actor_relationships_coverage. For heavy detail use the follow-up tools: get_threat(id) for a full threat, search_detections / get_detection_detail for detection bodies, search_iocs for IOC values, get_infrastructure_pivots for shared infrastructure.
Inputs: name (required). Returns: cves, actor, mitre, tools, +6 more
get_actor_intelligenceActor IntelligenceARead-onlyIdempotent
Composite intelligence picture for a threat actor: the actor profile (threats, MITRE, IOC counts, CVEs, tooling, targets), the known actor_relationships baseline, plus cross-actor attribution SCOPED TO THIS ACTOR — only shared entities whose actor list names it or one of its aliases, ranked by attribution belief (shared malware/infrastructure outranks commodity TTPs). Use it to answer "who else does this actor overlap with, and on what evidence".
Inputs: name (required). Returns: cves, actor, mitre, tools, +3 more
get_actor_relationshipsKnown Actor LinksARead-onlyIdempotent
The platform's baseline of ALREADY-DOCUMENTED links between threat actors (subgroup / overlaps / similar / linked-to) with both uuids and the source. Call this before claiming any actor-to-actor relationship is new — it is the only surface that says whether a link is public knowledge. CRITICAL: this table is sparse, covering a small minority of the corpus's actor labels (the response carries live coverage numbers). An empty result means the link is UNRECORDED, never that it was disproved or that the actors are unrelated. Use it to rule a claim out of NOVELTY, never to rule a relationship out of EXISTENCE. Matches both slots, so it also returns rows where your actor is the target — get_actor's relationship list does not.
Inputs: actor, limit, rel_type. Returns: data, count, caveat, coverage, +2 more
get_atlas_intelligenceATLAS (Adversarial ML)ARead-onlyIdempotent
MITRE ATLAS technique co-occurrence for threats that attack AI/ML systems — prompt injection, agent-tool abuse, context and memory poisoning, cost harvesting. data returns pairs whose BOTH endpoints are real ATLAS ids (^AML.), with cooccurrence_count, support, confidence and lift; free-text publish labels ("Prompt Injection", "Tool Poisoning") are returned SEPARATELY in tag_pairs and are not ATLAS techniques. SMALL-N WARNING: the corpus holds 106 pairs of which only 10 were observed more than once, so min_cooccurrence defaults to 2. Lower it and you get rows where confidence=1.0 and lift=1/support are arithmetic on a single observation — those carry single_observation:true; do not report them as associations. Ranked by cooccurrence_count, then lift.
Inputs: limit, min_cooccurrence. Returns: data, note, count, pairs, +4 more
get_attack_flowAttack FlowARead-onlyIdempotent
Get the analyst-authored MITRE ATT&CK Flow for a threat: a causal DAG of actions, conditions, operators and assets, with per-node technique ids, tactics and descriptions. This is asserted causality — what actually caused what — not a flat technique list. Check generator: 'harness' is authored, 'derived' is timeline ORDERING and must not be read as causality. Use get_flow_similar_threats to find threats sharing a causal sequence.
Inputs: threat_id (required), view. Returns: flow, generator, threat_id, flow_valid, +3 more
get_attribution_coverageAttribution CoverageARead-onlyIdempotent
Corpus-level attribution honesty: how many threats are genuinely assessed vs merely actor-labelled at ingest vs uncovered, broken down by confidence, scope and reason code, plus the research backlog, contradictions, top actors and the research clock (last real assessment, not last nightly intake).
Inputs: actor. Returns: corpus, engine, recent, by_scope, +3 more
get_attribution_evidenceAttribution EvidenceARead-onlyIdempotent
Why a threat is attributed to an actor: the verdict, canonical actor, confidence, scope, the cited evidence chain, which signals fired, suspected alternatives and the analyst reasoning. Crucially it also reports state — whether this is a researched assessment or an unresearched intake stub — which threats.threat_actor alone cannot tell you.
Inputs: threat_id (required). Returns: actor, scope, state, title, +14 more
get_c2C2 IntelligenceARead-onlyIdempotent
Query the live C2 (command-and-control) intelligence center. Pick a view: 'beacons' (active C2 beacon snapshots — default), 'configs' (full extracted C2 configs), 'operators' (operator clusters), 'watermarks' (Cobalt Strike watermark index), 'correlations' (cross-C2 correlations), 'timeline' (activity over time), 'stats' (aggregate counts). Use generate_c2_blocklist when you want firewall-ready output rather than raw records.
Inputs: view, limit, offset. Returns: asns, data, items, total, +9 more
get_c2_dns_intelC2 DNS UnmaskingARead-onlyIdempotent
Reverse-DNS unmasking of C2 beacon infrastructure: which domains ride on each beacon IP, infrastructure fidelity (dedicated / mixed / shared), compromised-host flags and sample domains. Answers "what else lives on this C2 infrastructure". Filter by fidelity to separate adversary-owned infrastructure from shared hosting.
Inputs: limit, fidelity, compromised. Returns: rows, stats, total, offset
get_campaign_intelligenceCampaign IntelligenceARead-onlyIdempotent
Pivot on a named campaign / operation by name (e.g. "Snowflake campaign", "ClickFix"). Returns the threats in the campaign, the actors involved, prevalence, and common ATT&CK techniques. Membership is the UNION of the curated threat_campaign_refs table and threats whose own TITLE names the campaign, because the curated table is thin (ClickFix: 7 curated rows against 57 threats that name it). Each threat carries matched_via (grounded | title | grounded+title) and the response carries a membership breakdown — neither source is complete, so treat title rows as leads and check them before calling them members.
Inputs: name (required). Returns: query, actors, matched, threats, +5 more
get_changelogGet ChangelogARead-onlyIdempotent
Get the platform changelog (new threats, detections, features), strictly newest-first by date. Pass limit (default 20, max 100). NOTE: this is a hand-maintained release feed, not a deploy log — it stopped being written in Feb 2026, so the response carries latest_entry_date / stale_days / a warning. For what the platform actually looks like NOW use get_platform_stats (live corpus counts) and get_engine_status (pipeline state); do not answer "what changed recently" from this alone.
Inputs: limit. Returns: count, stale, total, entries, +4 more
get_community_campaignsCommunity CampaignsARead-onlyIdempotent
Campaign clusters from the community OSINT layer (tweetfeed.live, CC0): cluster name, confidence, targeted brand, first/last seen, indicator count and types, tags and reporters. Cluster labels are UPSTREAM AI output, not Threadlinqs attribution — do not present them as our assessment. On an upstream proxy failure the response carries community_error rather than erroring; report "community feed unavailable", not "no campaigns".
Inputs: limit. Returns: window, campaigns, generated_at, community_error
get_correlation_pathCorrelation PathARead-onlyIdempotent
Shortest evidence path between two threats across the similarity graph: the intermediate threats, each hop's dominant linking signal and shared artifacts, and the weakest-link strength of the whole path. Answers "is this incident connected to that campaign, and through what". Returns found:false with a reason (no edges vs different components) rather than an empty array.
Inputs: to (required), from (required), max_hops. Returns: to, from, hops, found, +2 more
get_correlationsCorrelation EngineARead-onlyIdempotent
Read precomputed cross-dataset correlations. Choose an engine: 'overview' (rollup of all engines — default), 'mitre-heatmap', 'adversary-infra', 'ioc-consensus', 'cve-velocity', 'attribution', 'detection-debt', or 'enrichment'. Use 'overview' first to see what's available, then drill into a specific engine.
Inputs: limit, engine, offset. Returns: cves, iocs, engines, sources, +5 more
get_correlation_subgraphCorrelation SubgraphARead-onlyIdempotent
The N-hop neighbourhood around any graph node — nodes, edges, and each edge's fidelity — for incremental exploration of the correlation graph. Start at depth 1 and expand: a whole-corpus graph exceeds every response budget. For a pre-aggregated single-entity view prefer get_entity_profile, which is cheaper and usually what you want; use this when you need the actual edge topology. Edges of the NPMI types (actor_technique, technique_cooccurrence) also carry the raw pmi, co_occurrence_count and the marginals {c, df_actor, df_tech, N} the score was computed from — use those, not the rounded fidelity, to compare two edges.
Inputs: seed_id (required), seed_type (required), depth, edge_type, +3 more. Returns: seed, edges, nodes, counts, +2 more
get_cveGet CVEARead-onlyIdempotent
Look up a CVE by identifier (e.g. CVE-2024-3400): description, CVSS v2/v3/v4, EPSS, CISA KEV status, exploitation flags (PoC/exploit/nuclei), weaknesses (CWE ids), affected products, references, and linked threats. threat_ids is the LIVE join over threats.cve_list (threat_ids_source says so; threat_ids_note appears when the stale derived index disagreed, and any ids only that index held are surfaced separately in threat_ids_derived_only rather than merged) — it is the same linkage get_cve_intelligence reports. Enumerated pre-release CPEs are collapsed into ranges (affected_products_raw_count gives the uncollapsed count). enrichment_status distinguishes a fully enriched record from one merely seeded from KEV, where blank CVSS/EPSS means NOT MEASURED rather than measured-absent. For linked threats WITH titles/actors/detections/velocity in one call, prefer get_cve_intelligence.
Inputs: cve_id (required). Returns: kev, epss, cve_id, cvss_v3, +14 more
get_cve_intelligenceCVE IntelligenceARead-onlyIdempotent
Composite CVE dossier in one call: the enriched CVE detail, the threats that reference it (authoritative join — cve.threat_ids is reconciled to it), the attributed actors and MITRE techniques behind those threats, weaponization velocity for THIS CVE with its rank against the corpus, CWE-sibling related CVEs, and detections that name it.
Inputs: cve_id (required). Returns: cve, mitre, actors, threats, +3 more
get_cweGet CWEARead-onlyIdempotent
Look up a CWE by identifier (e.g. CWE-79): weakness name, description, abstraction, MITRE likelihood_of_exploit, common consequences, detection methods, phased mitigations, related CWEs, the corpus threats that carry it, and related_cves - the corpus CVEs mapping to this weakness (top 20 by KEV then CVSS, with related_cve_count giving the true total; use search_vulnerabilities with cwe= for the full list). NOTE: CWE has no CVSS severity - likelihood_of_exploit is the ontology's own High/Medium/Low rating, and severity_note says so; for scored severity read the related_cves rows or call get_cve. related_cves is null (never []) if the join could not run.
Inputs: cwe_id (required). Returns: name, cwe_id, enriched, threat_ids, +11 more
get_d3fend_postureD3FEND PostureARead-onlyIdempotent
Get the defensive twin of a threat's ATT&CK mapping: offensive technique to digital artifact to D3FEND countermeasure, plus coverage by defensive tactic. Use to answer 'what would have stopped this'. COVERAGE: 197 of 1,891 threats carry a mapping, so absence is common and is not an error — a threat that exists with no mapping answers 200 with an empty mappings and a reason saying whether it has no techniques at all or techniques the ontology has no countermeasure for; only an unknown threat id answers 404. IMPORTANT: this is a deterministic projection of the threat's techniques through a static ontology — two threats sharing countermeasures almost always just share techniques, so never treat countermeasure overlap as independent correlation evidence.
Inputs: threat_id (required), limit. Returns: count, error, caveat, reason, +9 more
get_daily_intel_bundleDaily Intel BundleARead-onlyIdempotent
One-shot "what happened" bundle: the day's debrief (latest by default, or pass date) plus platform stats, the top recent threats as LEAN summary rows, and the correlations overview. Drill into any listed threat with get_threat(id).
Inputs: date, top_n. Returns: debrief, detail_hint, top_threats, platform_stats, +1 more
get_daily_themeDaily ThemeARead-onlyIdempotent
Get the recent daily landscape themes (newest first, 14 days) with each day's top 6 threat tags. tags is recomputed LIVE over that date's threats, ranked count-descending with an alphabetical tie-break, and tags_source says whether a row used the live rollup ('live'), the stored nightly snapshot ('snapshot') or had no tags at all ('none') — tags_available is the boolean. The theme SENTENCE is generated just after midnight ET, before the day's ingest finishes, so theme_note/snapshot_threat_count disclose how many of the day's threats it was actually written from; when they disagree, trust tags.
Inputs: no named parameters. Returns: themes, tags_note, yesterday
get_debriefGet DebriefARead-onlyIdempotent
Get the full daily intelligence debrief for a specific calendar date (YYYY-MM-DD): posture summary, themes, threats grouped by severity, MITRE coverage, IOC distribution, actor attribution, and detection status. Find available dates first with list_debriefs.
Inputs: date (required). Returns: date, stats, title, themes, +5 more
get_detection_detailGet Detection DetailARead-onlyIdempotent
Get the full detail for one detection rule by its ID, including the complete query text (SPL/KQL/Sigma), metadata, and the threat it maps to.
Inputs: detection_id (required). Returns: id, name, query, severity, +7 more
get_detectionsGet DetectionsARead-onlyIdempotent
List detection logic (Splunk SPL, Microsoft KQL, Sigma). Optionally filter by threat_id or detection type. Paginated: pass limit (default 15, max 100) and offset to page; the result includes has_more and an opaque next_cursor (reusable as offset/cursor).
Inputs: type, limit, cursor, offset, +1 more. Returns: data, total, has_more, next_cursor
get_engine_statusIntelligence Engine StatusARead-onlyIdempotent
Is the intelligence pipeline healthy? Per-engine row counts, last-compute times and derived ok/stale/empty status; the nightly graph pipeline's staged progress, current stage and degraded flag; recent failures; and the latest held-out accuracy eval (AUC). Check this before reasoning over correlation output if freshness matters.
Inputs: no named parameters. Returns: eval, engines, failures, generated_at, +1 more
get_enrichment_overviewEnrichment OverviewARead-onlyIdempotent
Health and coverage of the enrichment LANES feeding the platform, one row each: cve_details, threat_iocs, detections, mitre_attack, c2_intel, dns_enrichment, tl_osint_scan, osint_blocklist_liveness. EPSS and KEV are NOT separate lanes - they are fields inside cve_details (whose hit_rate is the share of CVEs carrying both CVSS v3 and EPSS), and there is no IOC-reputation lane; the nearest signals are osint_blocklist_liveness and tl_osint_scan. Each lane's hit_rate has its OWN definition (they are not comparable to each other) and coverage_basis distinguishes 'measured_zero' from 'not_measured' - c2_intel really is 0% corpus coverage, because c2_correlations_v2 has no populated threat_id. This is a nightly snapshot: read as_of/stale_hours before treating it as current.
Inputs: no named parameters. Returns: note, as_of, sources, summary, +1 more
get_entity_aliasesEntity Aliases (reverse)ARead-onlyIdempotent
Every alias the reference set maps to ONE entity — the reverse of resolve_entity, which only walks a single alias forward. Use it to check alias collision: the commonest reason two "different actors" turn out to be one. IMPORTANT: the source (MISP) OVER-MERGES — it folds subgroups into their parent, so "andariel" and "bluenoroff" both appear under "Lazarus Group". An alias entry is a MAPPING, not an assertion of identity. Each alias therefore carries relation (canonical|subgroup|alias), other_entities (how many other entities claim the same label) and corpus_threats (how many threats this platform files under that exact label); corpus_uses_separately lists labels the corpus treats as their own actor despite the merge. Accepts a name or a uuid.
Inputs: name, type, uuid. Returns: uuid, caveat, aliases, cluster, +6 more
get_entity_profileEntity ProfileARead-onlyIdempotent
One-call dossier for any node in the intelligence graph — threat, technique, actor, IOC or CVE. Returns its centrality/pivot rank, top graph neighbours with edge fidelity, and type-specific rollups (linked threats, techniques with risk scores, IOCs with consensus and rarity, campaigns, related CVEs). Best token-per-call ratio in the graph family: replaces five or six separate lookups. Neighbours on the NPMI edge types also carry raw pmi, co_occurrence_count and the marginals {c, df_actor, df_tech, N}. For technique and ioc nodes the response includes rarity — corpus_df (how many threats mention it) against corpus_n — which is what separates a distinctive shared technique from background noise; check top_neighbors_truncated and raise limit before concluding a neighbour is absent.
Inputs: node_id (required), node_type (required), limit. Returns: cves, iocs, node, rarity, +6 more
get_flow_coverageFlow CoverageARead-onlyIdempotent
How much of the corpus carries an authored ATT&CK Flow, split by provenance, plus flow node/transition/path-similarity totals and whether the flow similarity channel has met its coverage gate. Call this before reasoning over flow data so you know the denominator — flow-derived findings only speak to the covered slice.
Inputs: no named parameters. Returns: flows, channel, threats, authored, +5 more
get_flow_similar_threatsFlow-Similar ThreatsARead-onlyIdempotent
Find threats that share a causal SEQUENCE of techniques with this one, scored by ordered-bigram cosine over ATT&CK Flow transitions. This sees what no other channel can: every existing similarity signal compares flat sets, so two threats can share an identical attack ORDER while sharing no indicator, CVE or actor. Returns the shared transitions (e.g. 'T1003>T1021') so the claim is inspectable. Scored independently and NOT folded into get_similar_threats' blended score.
Inputs: threat_id (required), limit, min_score. Returns: data, count, reason, threat_id
get_graph_campaignsGraph CampaignsARead-onlyIdempotent
Campaign clusters the engine assembled from the similarity graph (connected components + label propagation): label, cohesion, top actors/techniques/IOCs/nation-states, and per-member {title, created_at, category, threat_actor}. Each cluster carries duplicate_risk plus its evidence (distinct_member_dates, date_span_days, shared_title_tokens) — a similarity-derived cluster of one event documented several times looks identical to a real multi-event campaign until you read those. Distinct from get_campaign_intelligence (looks up a NAMED campaign from threat text) and from list_campaigns (the roster of named campaigns); this one reports clusters the engine derived itself.
Inputs: limit. Returns: data, summary
get_infrastructure_pivotsInfrastructure PivotsARead-onlyIdempotent
For a given threat, surface cross-threat infrastructure links — shared IPs/domains/hashes and DNS-derived overlaps that tie it to other campaigns. Derived from the SAME indicator universe the correlation graph scores, so a pivot here and an ioc-basis edge in explain_correlation agree. Each pivot carries value_threat_count (2 = the value is nearly unique to this pair; 40 = commodity such as a Run key) and a rarity-derived confidence — read those before calling an overlap a link. coverage gives the denominator: pivot_count 0 with scorable_iocs > 0 is a REAL negative, pivot_count 0 with scorable_iocs 0 only means the threat carries no pivotable indicator. Labels (malware family, tool name, technique) are deliberately not pivotable — two write-ups naming the same family observed nothing in common. Use get_similar_threats for TTP/actor-based similarity instead.
Inputs: threat_id (required). Returns: coverage, dns_trail, threat_id, pivot_count, +2 more
get_ioc_blast_radiusIOC Blast RadiusARead-onlyIdempotent
Map the blast radius of one indicator: the threats that contain it, the MITRE techniques those threats use, and the actors + sibling IOCs in the same campaigns. Matching is case-insensitive, and for a CVE the threat ring is the UNION of indicator rows and threats.cve_list (the authoritative CVE-to-threat mapping) — coverage reports which of the two produced how many, so a count can be traced to its source. edge_scores is a sampled graph_edges projection for fidelity context, never the denominator. Use this to scope impact of a single IOC; for a richer multi-source dossier on one indicator use get_ioc_intelligence instead.
Inputs: value (required), depth. Returns: rings, stats, center, coverage, +1 more
get_ioc_dnsIOC DNS EnrichmentARead-onlyIdempotent
Return stored DNS enrichment for an IP or domain indicator (reverse-IP and subdomain records previously resolved and cached in the platform dataset). This reads stored data — it is NOT a live lookup at call time. Use get_ioc_intelligence for the full stored dossier.
Inputs: value (required). Returns: total, domains, cross_links, query_value
get_ioc_intelligenceIOC Intelligence DossierARead-onlyIdempotent
Get the composite intelligence dossier for one indicator: linked threats, actor attribution, related IOCs, and enrichment context in a single call. Prefer this over search_iocs when you already have an exact indicator value and want its full story.
Inputs: value (required). Returns: osint, threats, ioc_value, truncated, +4 more
get_landscape_briefingLandscape BriefingARead-onlyIdempotent
Get the latest threat-landscape briefing — a synthesized posture summary of recent threat activity. latest is the most recent briefing that is a REAL synthesis: the narrative model currently fails on most hourly runs, and a failed run still writes a one-bullet automated posture stub, so the newest row is usually not a summary at all. When a fallback is served the response says so (latest_is_fallback + fallback_note naming both dates) and latest_age_hours gives its age; briefings[0] is always the newest regardless of quality, and every row carries is_synthesis. narrative_ok reports whether the newest run produced a real narrative.
Inputs: no named parameters. Returns: latest, briefings, page_size, stub_count, +8 more
get_latest_debriefGet Latest DebriefARead-onlyIdempotent
Get the most recent daily intelligence debrief in full detail (resolves the latest date for you).
Inputs: no named parameters. Returns: date, title, latest, summary
get_malware_intelligenceMalware IntelligenceARead-onlyIdempotent
Pivot on a malware FAMILY by name (e.g. "LockBit", "Vidar", "Emotet"). Returns the canonical family + type, prevalence (threat/actor counts, first/last seen), the threats deploying it, the actors using it, and its most-common ATT&CK techniques. For an offensive TOOL (Cobalt Strike, Mimikatz) use get_tool_intelligence instead. Call resolve_entity first if unsure of the canonical name.
Inputs: name (required). Returns: query, actors, matched, threats, +5 more
get_mitre_coverageMITRE CoverageBRead-onlyIdempotent
Get MITRE ATT&CK coverage across the platform. Optionally filter by tactic.
Inputs: tactic. Returns: tactics, top_techniques, total_techniques
get_mitre_gap_analysisMITRE Gap AnalysisARead-onlyIdempotent
Prioritized list of MITRE ATT&CK techniques with the weakest detection coverage (detection debt), ranked by debt_score = attributed threats / (1 + detection rules mapping the technique or its parent), scaled by exploitability (max EPSS / KEV of the CVEs its threats weaponize) and rarity. Higher = more exposure with less rule coverage. Filter by tactic (spelling-insensitive: "execution", "Execution" and "Execution (ICS)" all match) and cap with limit; summary.gaps/coverage_pct describe the FILTERED corpus, not the returned page.
Inputs: limit, tactic. Returns: summary, techniques
get_mitre_techniqueMITRE TechniqueARead-onlyIdempotent
Get details for a specific MITRE ATT&CK technique by ID (e.g. T1059 or T1059.001): authoritative name, tactics, matrix, revocation status, mitigations, detection data sources, and the corpus threats using it. The threat list is paged — a heavily-used technique attaches hundreds of threats, so pass include_threats=false for the definition alone (a few KB), or limit/offset to page. threat_count always reports the true total.
Inputs: technique_id (required), limit, offset, include_threats. Returns: matrix, source, tactic, revoked, +15 more
get_osintGet OSINT CorroborationARead-onlyIdempotent
Community corroboration for a threat or an indicator from the TL_OSINT_Scan layer (tweetfeed.live, CC0). Given threat_id, returns the matched community tags, the corroborated indicator count, and whether the community saw an indicator BEFORE our report. Given ioc_value, returns sightings, reporters, tags and every linked threat. Community-sourced and heavily concentrated (~73% of recent submissions come from a single reporter) — treat as corroborating evidence, never as authoritative attribution.
Inputs: ioc_value, threat_id. Returns: value, scanned, lead_days, reporters, +6 more
get_osint_trendsCommunity OSINT TrendsARead-onlyIdempotent
What the security community is surging on right now (tweetfeed.live, CC0), joined against our own corpus coverage: trending tags with movement, TLD distribution, novelty, top producers, daily volume — plus corpus (how much of our corpus the community corroborates) and early_warning (the lead-time distribution). The coverage-gap and lead-time read; the corpus join exists nowhere else. Keyed on community TAGS, not malware family (populated on <1% of upstream rows).
Inputs: no named parameters. Returns: tlds, daily, caveat, corpus, +6 more
get_pivotal_entitiesPivotal EntitiesARead-onlyIdempotent
The hubs and bridges of the intelligence graph ranked by weighted degree and approximate betweenness — where a single detection buys the most coverage. NOTE: betweenness is an ego-bridge heuristic, not exact Brandes; the response says so in note. Do not present it as exact betweenness.
Inputs: limit, node_type. Returns: data, note
get_platform_statsPlatform StatsARead-onlyIdempotent
Get aggregate platform statistics: threat, detection, IOC, MITRE technique, and actor counts.
Inputs: no named parameters. Returns: top_actors, total_iocs, total_ttps, by_category, +6 more
get_recent_threatsRecent ThreatsARead-onlyIdempotent
List the most recently published threats. Paginated: pass limit (default 15, max 100) and offset to page through older threats; the result includes has_more and an opaque next_cursor (reusable as offset/cursor).
Inputs: limit, cursor, offset. Returns: data, total, has_more, next_cursor
get_roadmapGet RoadmapARead-onlyIdempotent
Get the Threadlinqs Intelligence platform roadmap: completed, in_progress and ideas (planned), with counts, generated_at and as_of. WARNING: this table is hand-maintained and has not been updated since Feb 2026 — the response carries stale_days and a warning, and several items still marked "planned" have since shipped. Do not report an item as unbuilt on this basis; confirm with get_started (live tool catalog), get_platform_stats or get_engine_status.
Inputs: no named parameters. Returns: as_of, ideas, stale, counts, +5 more
get_similar_threatsSimilar ThreatsARead-onlyIdempotent
Threats similar to a given threat, with the EVIDENCE behind each link: per-channel score breakdown, which signal dominates, the concrete shared techniques / IOCs / CVEs, and quality flags for stale or high-confidence-low-evidence links. Use explain_correlation for a full decomposition of one specific pair.
Inputs: id (required), limit. Returns: data, count, counts, similar, +1 more
get_startedGet StartedARead-onlyIdempotent
Start here. Returns the Threadlinqs Intelligence tool catalog, categories, tiering, and usage guidance. No API call — read this before using other tools.
Inputs: no named parameters. Returns: tools, server, exports, tiering, +3 more
get_technique_rulesTechnique Co-occurrence RulesARead-onlyIdempotent
MITRE ATT&CK technique PAIRS mined from the corpus with support, confidence and lift — which techniques travel together far above chance. Each rule carries both technique ids AND their ATT&CK names (technique_a_name / technique_b_name), so a rule is readable without a follow-up lookup. Complements predict_mitre_transitions exactly: that answers sequence (what follows what), this answers co-occurrence (what appears alongside what). Rules come back lift-descending; summary.total_rules reports how many exist in total, so has_more tells you whether the tail was cut. Note minSupport 0.02 — a pair must appear in ~2% of threats to be mined at all, so rare-technique pairs are structurally absent rather than uncorrelated.
Inputs: limit. Returns: rules, summary
get_threatGet ThreatARead-onlyIdempotent
Get the detail for a single threat by its ID (e.g. TL-2026-0042): overview, attribution, MITRE techniques, IOCs, the detection roster, timeline, targets and tags. RETRIEVABLE IN PARTS — pass sections to choose what comes back; the response echoes _sections telling you what was returned and what was omitted. By default detection RULE BODIES (SPL/KQL/Sigma) are omitted — they are ~40% of a heavy dossier and have dedicated tools (export_detection / get_detection_detail) — and description is trimmed to 1500 chars with description_chars disclosing the true length. Pass sections="all" and max_description=-1 for the complete record. For malware families, tools, sectors/regions, OS and campaigns, call get_threat_enrichment.
Inputs: id (required), sections, max_description. Returns: id, iocs, tags, osint, +18 more
get_threat_bundleGet Threat BundleARead-onlyIdempotent
One-shot dossier for a threat: threat detail plus its simulations and pipeline transcripts (include="summary" returns just the threat). Fewer round-trips than get_threat + get_threat_simulations + get_threat_transcripts separately. The threat is the same bounded projection get_threat returns by default — call get_threat(id, sections="all") for the unabridged record.
Inputs: threat_id (required), include, simulation_limit. Returns: threat, simulations, transcripts
get_threat_enrichmentThreat EnrichmentARead-onlyIdempotent
Reference-grounded enrichment for one threat by ID: the malware families and tools used, targeted sectors/regions, affected operating systems, named campaigns, AI/ML (ATLAS) techniques, and per-technique mitigations + detection data sources. Complements get_threat (overview/MITRE/IOCs/detections) — call this for the "what malware/tools were used and who was targeted" view. Read coverage before acting on an empty array: grounded = the normalised association tables, threat_record = fell back to the threat's own target_sectors/target_regions, unmapped = NOT MAPPED, which is not the same as not targeted.
Inputs: id (required). Returns: id, atlas, tools, malware, +5 more
get_threat_hunting_bundleThreat Hunting BundleARead-onlyIdempotent
Flagship one-call hunting dossier for a threat: threat detail + similar threats + simulations + infrastructure pivots, composed server-side. Best single tool to scope a hunt around one threat. Every section is bounded so the bundle fits in one response — raise simulation_limit / pivot_limit, or call get_infrastructure_pivots and get_threat directly, when you need the full lists.
Inputs: threat_id (required), shape, pivot_limit, simulation_limit. Returns: iocs, ttps, _shape, counts, +10 more
get_threat_levelThreat LevelARead-onlyIdempotent
Get the computed current threat-landscape level (a 0–25 rating of overall posture).
Inputs: no named parameters. Returns: max, level, score, criteria, +1 more
get_threat_simulationsThreat SimulationsARead-onlyIdempotent
DEPRECATED (generation stopped 2026-08-03; ~5,362 archived rows still served, no new ones are produced) — the response carries deprecated:true and the caveat inline. Adversary-emulation playbooks attached to a threat. Most were synthetic-telemetry generators against local mocks rather than real execution, so they could not trigger the platform's own detections. One threat's playbooks can run 30 KB+ of command text: narrow with platform (see available_platforms) and limit. An empty result carries a reason distinguishing "this threat never had any" from "none for that platform". Prefer get_attack_flow, which returns the analyst-authored causal DAG that replaced them.
Inputs: threat_id (required), limit, platform. Returns: caveat, reason, matched, returned, +8 more
get_threat_transcriptsGet Threat TranscriptsARead-onlyIdempotent
Get the PIPELINE PROVENANCE record for a threat — how its profile was produced, not analysis of the threat itself. Returns the 7 pipeline phases (HUNT/RESEARCH/SIMULATION/DETECT/PUBLISH/CORRELATION/TRANSCRIPT) with per-phase timing, the quality gates and their PASS/FAIL metrics (tag/technique/IOC/reference counts), an overall quality score, the inter-agent handoff log, and correlation_highlights (related threat ids and the high-frequency IOCs that linked them). The handoff messages are routing stubs and file pointers, NOT analyst prose — do not expect written reasoning about the adversary. Use this to judge how thoroughly a threat was worked and to find its related-threat/IOC leads; use get_threat or get_threat_enrichment for the analysis, and get_attribution_evidence for why it is attributed.
Inputs: threat_id (required). Returns: count, threat_id, transcripts
get_tool_intelligenceTool IntelligenceARead-onlyIdempotent
Pivot on an offensive tool / utility / RMM / LOLBin by name (e.g. "Cobalt Strike", "Mimikatz", "AnyDesk", "PsExec"). Returns the canonical tool + class, prevalence, the threats and actors using it, and its most-common ATT&CK techniques. prevalence.actor_count is the TRUE distinct-actor total; the actors[] array is clipped to the top 20 (see prevalence.actors_returned) — do not read its length as the population.
Inputs: name (required). Returns: query, actors, matched, threats, +5 more
healthHealth CheckARead-onlyIdempotent
Lightweight liveness probe: confirms the API is reachable and your key is valid, and returns platform counts + the latest debrief date.
Inputs: no named parameters. Returns: status, tool_count, catalog_hint, prompt_count, +7 more
huntHunt (TLQL)ARead-onlyIdempotent
Run a deterministic SIEM-style query over the pre-joined observation index (~106k rows across tool, malware, ioc, mitre, cve, attribution, dns and infra observations). Use this INSTEAD of chaining many search_threats calls when the question is an aggregate ("how many X grouped by Y") or crosses observation types ("threats using tool A that also have IOC type B"). Append "| stats count by " to aggregate; without it you get matching rows. A threat contributes one row per observation, so for "how many THREATS" use "| stats count_distinct(threat) by " — plain count double-counts. Operators are = != > < >= <= LIKE CONTAINS IN "NOT IN"; quote any value with a hyphen (cve = "CVE-2024-3400"). Call hunt_schema first if you do not know the field names.
Inputs: query (required), limit. Returns: by, func, mode, rows, +7 more
hunt_schemaHunt SchemaARead-onlyIdempotent
The hunt query grammar: every filterable field and alias, which fields are scoped observables vs denormalized, the operators, the stats-pipe form, worked examples, and how fresh the index is. Call once before writing a hunt query.
Inputs: no named parameters. Returns: grammar, row_count, rebuilt_at, duration_ms, +1 more
list_campaignsList Named CampaignsARead-onlyIdempotent
Roster of NAMED campaigns/operations referenced by the corpus, with the actors, nation-states, date range and member threats behind each. Answers the campaign-lineage question the other tools cannot: get_campaign_intelligence needs you to already know a name, and get_graph_campaigns only reports the engine's own similarity clusters. Filter with min_actors to find campaigns carrying two or more distinct actors. Each member carries text_supported — whether the campaign name literally occurs in that threat's own record — because the underlying table has no provenance column and at least one row attaches a threat to a campaign with no textual basis, manufacturing a cross-nation link. Check unsupported and cross_nation before treating campaign co-membership as correlation evidence.
Inputs: limit, min_actors. Returns: data, count, total, caveat, +1 more
list_debriefsList DebriefsARead-onlyIdempotent
List recent daily intelligence debriefs (newest first) with their per-day rollups: new/updated threats, the day's theme, top categories and actors, severity counts, mitre_technique_count (+ mitre_techniques_sample, the first 10 of an alphabetically-sorted ID list — NOT a top-10), and ioc_breakdown by type with ioc_total. Enough to pick the day worth drilling into without fetching each one; use get_debrief for a date's full detail (all techniques, per-threat lists, highlights). Pass limit (default 30, max 100); the result includes has_more (true when the page is full, so older debriefs may exist). NOTE: the debriefs endpoint does not yet honor offset — it serves the most recent window.
Inputs: limit. Returns: data, total, has_more, next_cursor
list_simulationsList SimulationsARead-onlyIdempotent
DEPRECATED (generation stopped 2026-08-03; archived rows only). List adversary-emulation simulation scenarios across the platform (atomic test commands grouped by threat). total / total_simulations are CORPUS-wide; the page you got is returned / page_simulations, and has_more + next_offset walk the rest. The correlation block (shared_techniques, attack_chain_similarities, platform/tactic coverage) is computed over the RETURNED PAGE only — it carries scope:"page" and changes with limit. Pass limit (default 50, max 200) and offset. include_facets=true adds the corpus filter vocabulary (~20 KB of actor/nation/category strings) — off by default. Prefer get_flow_coverage and get_attack_flow — ATT&CK Flows replaced simulations.
Inputs: limit, offset, include_facets. Returns: total, threats, has_more, returned, +7 more
list_threat_categoriesList Threat CategoriesARead-onlyIdempotent
List every threat category with its threat count across the whole corpus. Use to discover valid category filters for search_threats.
Inputs: no named parameters. Returns: data, total_categories
predict_mitre_transitionsPredict MITRE TransitionsARead-onlyIdempotent
Predict the MITRE ATT&CK techniques most likely to follow (or precede) a given technique, with probabilities and example threats. Each row carries order_basis: 'attack_flow' rows come from analyst-authored ATT&CK Flow DAGs (real asserted causality), 'mitre_canonical' rows are inferred by sorting a threat's flat technique set by canonical tactic rank, and 'blended' rows have both. Prefer attack_flow evidence: ~24% of real transitions run against canonical tactic order and are inexpressible by the canonical basis. Use forward to anticipate the next step; reverse to infer what came before.
Inputs: basis, top_n, direction, technique_id. Returns: data, total, direction, transitions, +1 more
resolve_entityResolve Canonical NameARead-onlyIdempotent
Normalize an actor / malware / tool / sector / region / technique name or alias to its canonical reference form + stable UUID (e.g. "fancy bear" → "APT28"). Call this BEFORE pivoting (get_actor / get_malware_intelligence / get_tool_intelligence / search_threats) when unsure of the canonical name. Optional type narrows the lookup.
Inputs: name (required), type. Returns: uuid, query, matched, canonical, +2 more
search_actorsList ActorsARead-onlyIdempotent
List attributed threat actors with aggregate stats (threat_count, severity levels, categories, nation_state). Returns the full roster in one call, or narrow it with the optional tool / malware / sector filters (e.g. tool="Cobalt Strike" → only actors that used it). Use get_actor for a single actor's full profile. Not paginated; the response carries a total count. Names are REPAIRED before they are returned: the corpus stores threat_actor as free text and comma-split it, so prose fragments and truncated parentheticals used to appear as adversaries — label_hygiene reports what was dropped and repaired. Two per-row flags matter: role: "co-mention" means the corpus never files a threat under that name as its primary attribution, and also_grounded_as means the corpus also records the name as a malware family or tool (e.g. SNOWLIGHT). Check both before reporting a row as an operator.
Inputs: tool, sector, malware. Returns: total, actors, has_more, next_cursor, +1 more
search_corpus_semanticSemantic Corpus SearchARead-onlyIdempotent
Vector + rerank retrieval over the whole corpus, returning ranked source cards. Use when keyword search fails — conceptual or paraphrased questions where the exact terms do not appear in the text. Complements search_threats, which is boolean/exact over structured filters. Depends on the AI Search binding and is rate-limited; a 503 means the index is unavailable, not that nothing matched.
Inputs: query (required). Returns: query, chunks, results
search_detectionsSearch DetectionsARead-onlyIdempotent
Keyword search across detection logic (SPL/KQL/Sigma) by rule text, technique, or threat. Optionally filter by type (spl|kql|sigma) or severity. Paginated via limit (default 25, max 200) + offset.
Inputs: query (required), type, limit, offset, +1 more. Returns: data
search_iocsSearch IOCsARead-onlyIdempotent
Search indicators of compromise (IPs, domains, hashes, URLs). Filter by value substring and/or category. Pass limit (default 25, max 100); the result includes has_more (true when the page is full, so more may exist). NOTE: the indicator endpoint does not yet honor offset — narrow with a more specific value/type substring rather than paging.
Inputs: type, limit, value. Returns: data, total, has_more, next_cursor
search_threatsSearch ThreatsARead-onlyIdempotent
The deterministic threat-catalog query tool. Returns LEAN summary rows {id, title, severity, category, status, threat_actor, nation_state, affected_products, cves, cvss_score, summary, created} — call get_threat for full detail on a specific id. Combine a free-text query with any structured filters; ALL filters AND-combine and apply together (e.g. query="supply chain" + threat_actor="TeamPCP" + category="SUPPLY_CHAIN" returns only matching rows, with affected_products inline). Paginated: limit (default 20, max 100) + offset/cursor; result carries total, has_more, and next_cursor.
Inputs: os, cve, tag, tool, +19 more. Returns: data, total, has_more, next_cursor
search_vulnerabilitiesSearch VulnerabilitiesARead-onlyIdempotent
Query the real-time CVE feed — validated against CVE.org and enriched from open sources (CVSS, EPSS exploitation probability, CISA KEV, public PoCs/exploits, nuclei detection templates, affected products/packages, plus platform-native trending/priority). Sort by trending|latest|priority|cvss|epss; filter by severity, kev (KEV-only), has_poc, nuclei, epss_min, window (days), vendor, cwe, or free-text query. Returns COMPACT cards {cve_id, severity, cvss, epss_percentile, is_kev, has_poc/exploit/nuclei, priority, trending, vendors, age} — call get_cve(id) for full detail.
Inputs: cwe, kev, sort, limit, +7 more. Returns: sort, total, facets, pagination, +1 more
search_xscan_indicatorsSearch Community IndicatorsARead-onlyIdempotent
Search the canonical community-indicator set (TL_OSINT_Scan / tweetfeed.live, CC0) — indicators the community reported that were also matched against our corpus. Filter by tag, type, ASN, country, minimum linked-threat count, or a value substring. There is deliberately NO family filter: the upstream AI family field is populated on under 1% of rows, so a family argument would return nothing. Use tag instead (community tags carry the family signal). Community-sourced and heavily concentrated (~73% of recent submissions come from a single reporter) — corroborating, not authoritative.
Inputs: q, asn, tag, type, +4 more. Returns: data, total, has_more, next_cursor
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 81 tools
The descriptions are unusually thorough, but the set is dense with overlapping families: get_threat / get_threat_enrichment / get_threat_bundle / get_threat_hunting_bundle, get_cve / get_cve_intelligence, get_actor / get_actor_intelligence, get_ioc_intelligence / get_entity_profile, and the multiple campaign tools. An agent can easily pick a differently-scoped variant and get a different result shape than expected. The detailed caveats are the only thing keeping this from a 1.
The overwhelming majority of tool names follow a clear verb_noun snake_case pattern: get_threat, search_threats, list_debriefs, export_stix, generate_c2_blocklist, explain_correlation, and hunt_schema. Minor deviations like `health` and bare `hunt`, plus the alternation between get/search on very similar resources, keep it from a perfect 5.
81 tools is far beyond a workable MCP surface; the list itself becomes the main cognitive burden for an agent. The many get_*_intelligence and bundle tools show the platform knows fragmentation is a problem, but they add to rather than reduce the raw count.
The threat-intelligence domain is covered remarkably well: threats, actors, malware, tools, campaigns, CVEs, CWEs, IOCs, detections, C2, MITRE, ATT&CK Flows, and correlation evidence all have dedicated lookup and search paths. There are only minor workaroundable gaps such as some endpoints without full pagination and some stored-only enrichment layers.
Maintenance
Related MCP Connectors
Enrich, search, assess, and manage threat intelligence through 80+ typed MCP tools.
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceAn MCP server that exposes a 60+ tool security and threat-intel stack to AI agents, enabling secret scanning, Sigma rule generation, ransomware lookup, OSINT, and deep research.1MIT
- FlicenseNot gradedqualityDmaintenanceThis MCP server connects Claude Desktop to OpenCTI for AI-augmented threat intelligence analysis, enabling natural language queries and instant, contextualized answers from your threat intelligence database.29-
- AlicenseNot gradedqualityDmaintenanceA comprehensive MCP server that exposes multiple OSINT tools to AI assistants like Claude, enabling sophisticated reconnaissance and information gathering tasks using industry-standard OSINT tools.250MIT
- AlicenseNot gradedqualityDmaintenanceUnifies 7,283+ detection rules from Sigma, Splunk ESCU, Elastic, and KQL into a single queryable interface via MCP, with a web dashboard and autonomous agent pipeline for detection engineering.1Apache 2.0