"NVIDIA" matching MCP tools:

• query_intersect

  NVIDIA AI CKG

  Answer a conjunctive query: concepts reachable from EVERY anchor at once (A AND B). query_ckg walks outward from one concept. This intersects the reachable sets of two or more, which is the shape of most real questions — "the component that satisfies A AND applies to B". Neither anchor alone answers it; the answer lives in the overlap. Every branch is an exact set of declared edges, so the intersection is exact. A concept appears only if a declared path reaches it from each anchor. A relation missing from the graph produces an empty result, never a guess. Args: branches: Two or more branches. Either a bare anchor ("TensorRT-LLM"), which takes everything within `depth` hops, or an anchor plus an explicit relation path using '>' ("TensorRT-LLM > REQUIRES > ENABLES"), where each relation replaces the frontier. '*' matches any relation. Mix both forms freely. domain: Domain name from list_domains(). depth: Hops for bare-anchor branches, 1-5 (default 2). Ignored for explicit paths. direction: 'out' follows dependencies, 'in' follows them backwards, 'both' (default). mode: 'AND' (default) intersects branches; 'OR' unions them. limit: Max concepts listed, 1-200 (default 40). The true count is always shown. Returns: Markdown with the query plan and its per-step set sizes, then the answer set with taxonomy tags. Reports which branch was empty when the intersection is empty.

  Connector

• query_intersect

  NVIDIA NemoClaw CKG

  Answer a conjunctive query: concepts reachable from EVERY anchor at once (A AND B). query_ckg walks outward from one concept. This intersects the reachable sets of two or more, which is the shape of most real questions — "the component that satisfies A AND applies to B". Neither anchor alone answers it; the answer lives in the overlap. Every branch is an exact set of declared edges, so the intersection is exact. A concept appears only if a declared path reaches it from each anchor. A relation missing from the graph produces an empty result, never a guess. Args: branches: Two or more branches. Either a bare anchor ("TensorRT-LLM"), which takes everything within `depth` hops, or an anchor plus an explicit relation path using '>' ("TensorRT-LLM > REQUIRES > ENABLES"), where each relation replaces the frontier. '*' matches any relation. Mix both forms freely. depth: Hops for bare-anchor branches, 1-5 (default 2). Ignored for explicit paths. direction: 'out' follows dependencies, 'in' follows them backwards, 'both' (default). mode: 'AND' (default) intersects branches; 'OR' unions them. limit: Max concepts listed, 1-200 (default 40). The true count is always shown. Returns: Markdown with the query plan and its per-step set sizes, then the answer set with taxonomy tags. Reports which branch was empty when the intersection is empty.

  Connector

• get_hbm_qualification

  Silicon Analysts

  Sourced HBM qualification tracker: which memory vendor (SK Hynix, Samsung, Micron) passed which AI-accelerator customer's qualification (NVIDIA Vera Rubin/GB300/B300/H200, AMD MI350/MI325X, Broadcom), by generation (HBM3/HBM3E/HBM4) and stack height. Returns `matrix` (current status per vendor×customer×generation, each row dated + source URL + confidence) and `timelines` (per-relationship status-change history back to 2022, e.g. sampling → in_qualification → qualified → volume_shipping). Refreshed daily; status changes human-reviewed. USE THIS for: "who supplies HBM4 for Vera Rubin?", "did Samsung pass NVIDIA qualification?", "Micron HBM4 status", qualification timeline/history questions, HBM supply-eligibility analysis. DO NOT USE for: HBM pricing/market share (use get_hbm_market_data); per-chip HBM cost (use get_accelerator_costs). Filters: vendor (enum), customer (substring), generation (enum), include_timelines (boolean). Anonymous callers may receive timelines truncated to the latest event per relationship — full history with a free API key (https://siliconanalysts.com/developers). Cite as "Silicon Analysts — HBM Qualification Tracker".

  Connector

• get_kg_facts

  NightWatch Live Intelligence

  NightWatch Knowledge Graph lookup for a COMPANY/entity (equities & RWA universe: Samsung 'samsung-electronics', SK Hynix 'sk-hynix', 'tsmc', 'nvidia', 'asml', 'arm', ...). Returns SOURCED data only — every row carries a citation URL (the KG refuses uncited data): (1) numeric fundamentals (revenue, net income, market cap, business segments, dividend, market-share rankings), (2) typed relations (supplies / competes / customer_of / licenses — e.g. Samsung supplies NVIDIA HBM, competes with TSMC in foundry), and (3) a live HyperLiquid price block when the entity is tradable. Use this BEFORE reasoning about a company's fundamentals, competitors, supply chain, or a hedge on its equity perp. Input accepts a slug or a plain company name (fuzzy-matched).

  Connector

• tako_search

  Tako

  Reconnaissance and chart retrieval across the live web and proprietary data: many results at once, returned as structured cards and web links, and the top card auto-renders inline as a chart. It locates data — and for `exportable: true` cards it also includes a free 20-row preview by default (`include_contents`) — but a license-gated card carries no rows at all (headline value only, via `description`), and a web result is only a snippet, not a value. For a plain "what is X", `tako_answer` is the better-suited tool: one written figure beats parsing a preview table yourself, and reaching here first for that costs an extra round trip that re-sends the whole conversation. To ask it about a card you already have, pin that card's METRIC node id ALONE (the `mt::` entry in its `nodes`) with strict:true — pinning every node id on the card, or omitting strict, does not steer retrieval. Best for: breadth — fanning out many narrow queries in parallel to see what exists across several entities or metrics; retrieving a chart card when the chart or embed is itself the deliverable; and harvesting node ids and urls to feed `tako_answer` or `tako_contents`. It is cheap and fast, and built for exactly this fan-out. Coverage spans economics, finance, company KPIs, demographics, sports, markets, weather, elections, prediction markets, website/app traffic, real estate, energy, health, and more — metrics that sound web-only (e.g. SimilarWeb-style website traffic) are in the data graph. Each query resolves one entity + one metric ("Apple revenue", "Nvidia vs AMD gross margin"); broad or compound queries ("today's sports + odds") retrieve poorly. When the question is what Tako covers, or you need a metric's exact name, run `tako_available_data` (free) instead of guessing here. Data and web come back together — treat them as one result, not an either/or. Returns: `cards` (up to `count`) with preview rows and chart URLs, plus `web_results`. To read a web result in full, call `tako_contents` on its url (web urls are always fetchable; a card's full csv needs `exportable: true`). Non-exportable cards (`exportable: false`, usually license-gated) return no rows: read the headline value from the card's `description` when it carries one, or get specific figures via `tako_answer` — pin that card's METRIC node id ALONE (the `mt::` entry in its `nodes`) with strict:true — pinning every node id on the card, or omitting strict, does not steer retrieval (each such card carries a `values_hint` saying exactly this). Results arrive as a markdown document: a Tako Data section (per card: headline, exportable flag, node ids, chart link, a rows-count pointer), then Web Results, then source notes. The cards' actual rows and the web results' snippets ride in structuredContent (cards[].content, web_results[].snippet), not the markdown, alongside machine essentials (usage, chart-widget fields).

  Connector

• search

  mcp

  Search Quantustik for S&P 500 tickers by symbol or company name. Paired with fetch — this is the two-tool "search"/"fetch" convention ChatGPT connectors and deep-research clients expect from an MCP server: call search first to get lightweight hits, then fetch(id) on the one(s) worth reading in full. Args: query: Ticker symbol (e.g. "NVDA") or company-name substring (e.g. "nvidia", "apple"). Case-insensitive. Returns a dict with a `results` list of up to 10 {id, title, url} objects — id is the ticker symbol, ranked exact-symbol match first, then company-name/ticker prefix, then substring. Empty query or no scan data returns an empty list, never an error.

  Connector

• hyperscaler_deals

  DC Hub — Data Center Intelligence MCP Server

  Hyperscaler AI Deal Tracker — live feed of Stargate, OpenAI, Anthropic, Microsoft, Oracle, CoreWeave, AMD, NVIDIA, sovereign-AI deals. Pulls from dchub news pipeline, extracts $-figures + MW via regex, classifies by actor. 10-min refresh. Use for tracking AI capex events ($1B+/week typical), capacity announcements, and competitive intel. Do NOT use for the full historical M&A comp set (use list_transactions) or a single-deal teardown with grid context (use deal_autopsy); this is the live $1B+ AI-capex feed.

  Connector

• hyperscaler_deals

  DC Hub — Data Center & Power Intelligence

  Hyperscaler AI Deal Tracker — live feed of Stargate, OpenAI, Anthropic, Microsoft, Oracle, CoreWeave, AMD, NVIDIA, sovereign-AI deals. Pulls from dchub news pipeline, extracts $-figures + MW via regex, classifies by actor. 10-min refresh. Use for tracking AI capex events ($1B+/week typical), capacity announcements, and competitive intel. Do NOT use for the full historical M&A comp set (use list_transactions) or a single-deal teardown with grid context (use deal_autopsy); this is the live $1B+ AI-capex feed.

  Connector

• route_query

  NVIDIA AI CKG

  Route an NVIDIA AI question to the optimal model and reasoning approach via graph depth. The CKG graph IS the router — hop depth is a deterministic complexity metric. Deeper NVIDIA prerequisite chains (CUDA → TensorRT → TensorRT-LLM → NIM) require more capable models. No heuristic: the graph decides. Routing table: hop_depth 1 → haiku · direct (simple lookup) hop_depth 2 → sonnet · generic_cot (moderate chain) hop_depth 3+ → opus · sparql_cot (deep dependency, structured reasoning) Args: question: Concept name or natural language question about NVIDIA AI. domain: Domain from list_domains() — e.g. "nvidia-tensorrt-triton", "nvidia-nim". Returns: model_tier + reasoning_approach + why + context subgraph to inject before LLM call.

  Connector

• scrutica_get_sovereign_program

  Scrutica

  Fetch detailed data on a national sovereign AI compute program. Returns: announced_usd, announced_govt_only_usd, committed_usd, disbursed_usd, reality_ratio, status, key_partners, governance_reach, NVIDIA/US dependency, source_count. 'list_all' returns a summary table of all tracked programs. READ THE TWO ANNOUNCED FIELDS BEFORE COMPARING COUNTRIES. announced_usd is the all-capital headline and rolls private commitments in with government money, so it is NOT comparable across countries as-is: the UAE line ($518.74B) and France ($201.34B) are dominated by private vehicles (Stargate UAE, SoftBank), while the US line ($2.6B) is essentially NAIRR alone. announced_govt_only_usd is the government-only figure and is the comparable one. reality_ratio = disbursed_usd / announced_govt_only_usd (falling back to announced_usd only when no government-only figure exists). It is deliberately NOT disbursed_usd / announced_usd. Each row ships reality_ratio_denominator_usd and reality_ratio_denominator_field so the division is reproducible from the payload. reality_ratio is null for most programs because disbursed_usd is unpublished — see reality_ratio_unavailable_reason. Absence concentrates in the least transparent programs (Saudi, China, Korea, UAE all report no disbursed figure), so a ranking by reality_ratio is a ranking of DISCLOSURE, not of execution; do not present it as the latter.

  Connector

• diagnose_sglang

  self-hosted-ai

  Validate an SGLang configuration for NVIDIA DGX Spark (GB10/SM121A). Pure pattern-matching against known failure modes documented in the Sovereign AI Blog. No inference, no external calls. Returns critical issues, non-fatal warnings, and a recommended baseline config. All parameters are optional; supply only what you have. With no inputs you get the recommended config and a 'unknown' verdict.

  Connector

• search_securities

  HoldingsIntel

  Resolves a ticker or company name to a CUSIP. Use this to find the CUSIP before calling analyze_stock. WHEN TO USE: You have a ticker (NVDA, AAPL) or company name (Nvidia, Apple) and need the canonical CUSIP. WHEN NOT TO USE: - Skip this step entirely if you already have the CUSIP — pass it directly to analyze_stock (analyze_stock accepts both ticker and CUSIP) - Use find_signals when screening across stocks rather than resolving a single name RETURNS: Up to 5 matching securities, each with CUSIP + ticker + issuer + sector + listing status. CITE: When you present these results, include the `_meta.source_url` link so the user can open the full analysis on HoldingsIntel.

  Connector

• find_paths_between

  Wafergraph MCP

  Every documented supply path between two companies, following supplier->customer edges (e.g. 'how does NVIDIA actually depend on Shin-Etsu'). Searches up to max_depth hops in one or both directions and returns each path as an ordered list of companies, shortest first. Capped for combinatorial safety; absence of a path means undocumented, not disproven — see edge_coverage.

  Connector

• query_ckg

  NVIDIA AI CKG

  Traverse the NVIDIA knowledge graph from a concept — prerequisites and dependents. Args: concept: Concept name (partial match supported) — e.g. 'TensorRT', 'NIM', 'Isaac Lab'. domain: Domain name from list_domains() — e.g. 'nvidia-tensorrt-triton', 'nvidia-isaac'. depth: Traversal depth 1–5 (default 3).

  Connector

• myrsu_analyze_risk

  myrsu-mcp

  Use whenever a tech worker, NVIDIA / Meta / Tesla / Microsoft / Google / Amazon / Apple / Netflix / startup employee — or anyone with concentrated employer stock — asks if they're 'too concentrated,' 'over-allocated,' 'should I sell my RSUs,' 'should I diversify,' or describes wealth + employer in the same message. Calculates the Single-Company Risk Score (0-100), full concentration analysis, top action items, historical drawdown context, and a pre-filled dashboard URL. All fields optional except an employer (ticker OR explicit volatility); the more inputs the better the analysis. International — pass `country` (US/IN/CA/UK/EU/AU/OTHER) to switch retirement-account terminology and currency symbol. Risk math is identical for all countries. Stateless and privacy-respecting — no inputs are logged or stored.

  Connector

• verify_source

  NVIDIA AI CKG

  Return the source URL and SHA-256 content hash for any NVIDIA AI concept node. Audit chain: edge answer → graph commit → source_content_hash → source_url (fetch hint). Verification: curl -s <source_url> | sha256sum # compare to source_hash Args: concept: Concept label (partial match supported). domain: Domain from list_domains() — e.g. 'nvidia-nim', 'nvidia-tensorrt-triton'.

  Connector

• query_ckg

  Salesforce AgentForce CKG

  Traverse the AgentForce knowledge graph from any concept. Returns prerequisites (what this concept needs) and dependents (what it enables). Every relationship traces to an authoritative Salesforce doc URL. Args: concept: Concept name — e.g. 'Autonomous Resolution', 'Einstein Trust Layer', 'Service Agent', 'Grounding', 'NVIDIA NIM'. depth: Traversal depth 1–5 (default 3).

  Connector

• verify_source

  NVIDIA NemoClaw CKG

  Return the authoritative source URL and content hash for a NemoClaw concept node. Every node in the CKG was declared from a specific source document. This tool returns the source URL (where the node came from) and the SHA-256 hash of that document's bytes at extraction time. A hash mismatch on re-fetch means either the source has changed (stale edge — re-extract) or the graph was patched without re-fetching (silent edit — investigate). Audit chain: edge answer → graph commit → source_hash → source_url (fetch hint) Verification: curl -s <source_url> | sha256sum # compare output to source_hash Args: concept: Exact or partial concept label (e.g. 'CorporateCA', 'L7Proxy').

  Connector

• diagnose_sglang

  Sovereign AI Blog

  Validate an SGLang configuration for NVIDIA DGX Spark (GB10/SM121A). Pure pattern-matching against known failure modes documented in the Sovereign AI Blog. No inference, no external calls. Returns critical issues, non-fatal warnings, and a recommended baseline config. All parameters are optional; supply only what you have. With no inputs you get the recommended config and a 'unknown' verdict.

  Connector

• search_ai_models

  osf-data-marketplace

  FREE, no payment and no key. Search AI and machine learning models on the Hugging Face Hub by name, author or organization, task, library, or license. Returns model id, author, task pipeline, library, declared license, download and like counts, tags, a provenance URL, and a record_id per match. Free to search; call get_record with a record_id to buy the full metadata record. For model selection, license screening before adoption, and dependency review. Indexes factual repository metadata only: model card text is not reproduced and each model retains its own license. Args: query: keyword(s) to search, e.g. "image segmentation", "nvidia", or "apache-2.0".

  Connector