# Scrutica MCP server

AI compute infrastructure intelligence: facilities, supply chains, sovereign AI, export controls.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-davidgringras-scrutica
- Repository: https://github.com/davidgringras/scrutica
- Website: https://scrutica.com

## Install
- Endpoint: https://scrutica.com/api/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://scrutica.com/api/mcp

## Tools
- scrutica_search - Search facilities, companies, or sovereign programs by free-text query.
Returns ranked results with id, name, type, one-line summary, and Scrutica URL.
Filter by entity_type to scope to a single class. Filter by ISO 3166-1 alpha-2 country code.
Do NOT use this for BIS Entity List / export-control lookups — use scrutica_query_export_controls.
Do NOT use this for supply-chain traversal — resolve an entity ID first via this tool, then call scrutica_get_supply_chain. Endpoint: https://scrutica.com/api/mcp
- scrutica_get_facility - Fetch complete details for a single Scrutica facility by canonical ID.
Returns: operator, owner, country, power capacity (MW), GPU inventory (where disclosed), location (lat/lng), facility type, status, data_source, source_url, is_estimated flags, and any logged data-quality flags (cross-source divergence investigations).
For BIS Entity List designations tied to the facility's owner, look up the owner org via scrutica_query_export_controls — this tool does not compute ownership-chain BIS exposure.
Resolve facility IDs first via scrutica_search. Endpoint: https://scrutica.com/api/mcp
- scrutica_get_company - Fetch complete details for a single organization (company, government entity, holding company) by canonical Scrutica ID.
Returns: legal name, country of HQ, organization type, parent / subsidiary references, supply-chain edge counts.
Use scrutica_query_export_controls for BIS designation details. Use scrutica_get_supply_chain for full edge graphs. Endpoint: https://scrutica.com/api/mcp
- scrutica_query_export_controls - Look up BIS Entity List designations for companies or countries. The queried dataset is the US Commerce Department Entity List, Federal-Register-anchored; it does NOT cover OFAC SDN or Wassenaar CCL (for an organization's OFAC SDN / NS-CMIC / Section-1260H status, use scrutica_get_company — the record carries on_ofac_sdn / on_ns_cmic / on_1260h booleans).
entity_name is a case-insensitive substring match against the designated entity's published name (no alias expansion). Returns entity_name, entity_type, country, list_type, designation_date, removal_date, grounds, federal_register_citation, source_url (Federal Register notice URL), data_quality_flags.
Authority tier: Federal-Register-anchored designations are Tier 1 (primary source).
bis_coverage_class discriminates how a row is covered: explicitly_named (FR notice cites the entity by name) vs affiliate_50pct_rule (inferred via BIS's 50% Affiliates Rule). coverage_note is populated only on affiliate_50pct_rule rows and states whether that rule is currently suspended.
data_quality_flags is an array of provenance/caveat notes, empty for most rows; where present (derived-country provenance, removal-date sourcing, or the affiliate rows' suspension and substrate-reproducibility caveats) treat it as load-bearing context for the row. Endpoint: https://scrutica.com/api/mcp
- scrutica_entity_list_changes - What CHANGED in the BIS Entity List, as bounded change-log summaries. Backed by the same derivation the public /export-controls/changes page and its RSS feed render.
PREFER this over scrutica_query_export_controls for freshness questions ("what changed this month", "latest additions", "recent removals"): designation rows arrive already grouped into per-Federal-Register-notice change events, so you do not re-derive notice grouping from citation strings.
Each event carries: canonical FR citation and link, notice title / publication date / document number where the citation resolved to one FR document, a derived event date labeled with the source column it came from, entity / addition / removal counts, per-country counts, a bounded sample of entity names, and the entities cross-referenced to compute-infrastructure organizations.
Removal actions are returned separately as date-keyed events — a screening list maintained from additions alone over-blocks forever.
Also returns a last-N-ISO-week activity rollup counting BOTH additions and removals. Zero-count weeks are a real quiet-Federal-Register signal, not missing data.
Results are bounded summaries, never row dumps: at most 24 events per call (default 6, newest first), with any truncation declared in metadata. Cite totals from the count field and per-event entity_count — never by summing a sampled list.
Do NOT use this to look up one entity's designation rows — use scrutica_query_export_controls (substring match on the published name). Use company_id here only to scope the log to notices touching an organization you already resolved.
Authority tier: Federal-Register-anchored designations are Tier 1 (primary source). The event date is derived (modal designation_date, falling back to modal effective_date) and labeled with its source. Endpoint: https://scrutica.com/api/mcp
- scrutica_get_supply_chain - Return supply-chain relationships for one or more organizations.
direction = 'upstream' traces suppliers (who feeds this entity); 'downstream' traces customers (who depends on this entity); 'both' returns both.
Each edge: source_org_id, target_org_id, relationship_type, supply_share (where disclosed), price_correlation_3m (3-month rolling, where available), data_source.
Dataset: 18,999 edges from a licensed supply-chain database (held under subscription, not redistributed) plus SEC Exhibit 21 (substrate snapshot 2026-08-16). Endpoint: https://scrutica.com/api/mcp
- scrutica_get_sovereign_program - 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. Endpoint: https://scrutica.com/api/mcp
- scrutica_get_scenario - Fetch geopolitical compute risk scenarios.
Available: 'taiwan-strait' (4 TSMC disruption scenarios), 'iran-threat' (IRGC missile range vs Gulf compute), 'tokyo-earthquake' (Japan memory-fab exposure), 'south-china-sea' (submarine cable severing), 'abqaiq-2' (Saudi grid).
Returns the scenario's summary plus its substrate serialized from the interactive page's own data modules — assumption scenarios / threat systems / affected assets with per-item sources and authority tiers, capped lists shipping their true totals. The propagation SIMULATION itself remains interactive-only at the returned URL. Endpoint: https://scrutica.com/api/mcp
- scrutica_estimate_flops - Compute peak BF16 FLOP estimates for a hardware configuration.
Returns point estimate + bounds. Methodology matches the Interactive Methodology Explorer at /methodology#flop-estimation.
Do NOT present outputs as exact measurements — always relay the bounds and the is_estimated flag. Endpoint: https://scrutica.com/api/mcp
- scrutica_get_methodology - Return methodology documentation for a Scrutica metric or index.
Topics: 'flop-estimation', 'cost-index', 'compute-visibility-index', 'supply-chain-weighting', 'chokepoint-cascade', 'sovereign-execution-classification'.
Returns the canonical URL + section anchor + summary. Use this when a user asks "how did you calculate X". Endpoint: https://scrutica.com/api/mcp

## Resources
- https://scrutica.com/api/mcp/llms.txt - Scrutica MCP agent guide LLM-optimized reference for this server: tool semantics, worked examples, anti-patterns, authority tiers, citation format. MIME type: text/markdown
- https://scrutica.com/llms-full.txt - Scrutica full site reference (llms-full.txt) The complete machine-readable site reference: every instrument, dataset, and methodology with counts from the current substrate snapshot (~260KB). MIME type: text/plain
- scrutica://methodology/flop-estimation - Methodology: flop estimation How Scrutica derives flop estimation figures. Canonical page: https://scrutica.com/methodology#flop-estimation MIME type: text/markdown
- scrutica://methodology/cost-index - Methodology: cost index How Scrutica derives cost index figures. Canonical page: https://scrutica.com/methodology#cost-index MIME type: text/markdown
- scrutica://methodology/compute-visibility-index - Methodology: compute visibility index How Scrutica derives compute visibility index figures. Canonical page: https://scrutica.com/compute-visibility MIME type: text/markdown
- scrutica://methodology/supply-chain-weighting - Methodology: supply chain weighting How Scrutica derives supply chain weighting figures. Canonical page: https://scrutica.com/methodology#cascade-simulation MIME type: text/markdown
- scrutica://methodology/chokepoint-cascade - Methodology: chokepoint cascade How Scrutica derives chokepoint cascade figures. Canonical page: https://scrutica.com/methodology#cascade-simulation MIME type: text/markdown
- scrutica://methodology/sovereign-execution-classification - Methodology: sovereign execution classification How Scrutica derives sovereign execution classification figures. Canonical page: https://scrutica.com/methodology#sovereign-execution-classification MIME type: text/markdown

## Prompts
- facility_brief - Provenance-complete brief on one compute facility (capacity, control, exposure), built from Scrutica tools. Arguments: facility
- export_control_changes_brief - What changed in the BIS Entity List over a recent window — additions, removals, and the quiet-period caveat handled correctly. Arguments: window
- verify_scrutica_number - Walk the provenance chain behind a specific Scrutica figure and report what supports it. Arguments: claim

## Metadata
- Owner: io.github.davidgringras
- Version: 0.2.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 24, 2026
- Source: https://registry.modelcontextprotocol.io