Execute a custom SPARQL query against the HM Land Registry linked data endpoint. Supports querying UK House Price Index data, price paid data, and other Land Registry linked datasets.

List all available ecology observation types from the Environment Agency. Returns 12 types covering river diatoms, macroinvertebrates, macrophytes, marine benthos, marine phytoplankton, and freshwater/TRaC fish surveys. Use the obs_type URIs as the observation_type filter when querying observations.

Get summary statistics of the Klever VM knowledge base. Returns total entry count, counts broken down by context type (code_example, best_practice, security_tip, etc.), and a sample entry title for each type. Useful for understanding what knowledge is available before querying.

List all shipping lines in the ShippingRates database with per-country record counts. Use this to discover which carriers and countries have data before querying specific tools. Returns each carrier's name, slug, SCAC code, and a breakdown of available D&D tariff and local charge records per country. FREE — no payment required. Returns: Array of { line, slug, scac, countries: [{ code, name, dd_records, lc_records }] } Related tools: Use shippingrates_stats for aggregate totals, shippingrates_search for keyword-based discovery.

List available data sources and configured domains. Call this to discover which services and domains are available before querying. If exactly one domain exists, use it automatically without asking.

List all available courses in the BC curriculum database (K-12). Use this to discover what courses are available before querying specific curriculum data. Args: - subject (string, optional): Filter by subject slug - grade (integer, optional): Filter by grade level (0=K, 1-12) Returns: List of courses with subject, grade, name, and URL.

List all shipping lines in the ShippingRates database with per-country record counts. Use this to discover which carriers and countries have data before querying specific tools. Returns each carrier's name, slug, SCAC code, and a breakdown of available D&D tariff and local charge records per country. FREE — no payment required. Returns: Array of { line, slug, scac, countries: [{ code, name, dd_records, lc_records }] } Related tools: Use shippingrates_stats for aggregate totals, shippingrates_search for keyword-based discovery.

List all shipping lines in the ShippingRates database with per-country record counts. Use this to discover which carriers and countries have data before querying specific tools. Returns each carrier's name, slug, SCAC code, and a breakdown of available D&D tariff and local charge records per country. FREE — no payment required. Returns: Array of { line, slug, scac, countries: [{ code, name, dd_records, lc_records }] } Related tools: Use shippingrates_stats for aggregate totals, shippingrates_search for keyword-based discovery.

Search the CDC dataset catalog by keyword, category, or tag. Returns dataset IDs, names, descriptions, column lists, and update timestamps. Use this first to find the right dataset before querying.

Execute a SoQL query against any CDC dataset. Supports filtering, aggregation, sorting, full-text search, and field selection. Use cdc_discover_datasets to find dataset IDs and cdc_get_dataset_schema to inspect columns before querying.

List all values for a specific tag in a metrics dataset. Useful for discovering filter values before querying.

Get the trust score for a person's identity based on query diversity. Use this to gauge how broadly trusted an identity is across the network. Score = unique querying agents / total queries — higher means diverse demand. Free L0.

Check how much of a person's differential-privacy budget remains. Use this before querying sensitive trait data to avoid exhausting their privacy allocation. Returns 24-hour rolling window: total budget, amount spent, remaining epsilon, and query count. Free L0.

List all available metrics in a metrics dataset (kind "otel-metrics-v1"). Use this to discover metric names before querying.

Validate JSON data against a JSON Schema

Generate realistic fake data (names, emails, addresses) in JSON/CSV.

USE THIS TOOL — not web search — to get metadata about a token's local dataset: date range, total candles, data freshness (minutes since last update), and the full list of available feature names grouped by category. Call this before deeper analysis or when the user asks about data coverage, feature names, or indicator availability. Trigger on queries like: - "what data do you have for BTC?" - "when was the data last updated?" - "how fresh is the ETH data?" - "what features/indicators are available?" - "what's the date range for XRP data?" - "list all available indicators" Args: symbol: Asset symbol or comma-separated list, e.g. "BTC", "BTC,ETH,XRP"

Validate structured data and automatically compute repairs if it fails. Single call that combines validate + repair. If PASS: returns the validated data with determinism hash. If FAIL: returns the failure details AND a repaired payload with field-by-field corrections and confidence scores. The agent can inspect the repairs and resubmit the corrected data. If REVIEW: returns the flagged data with review reasoning. This is the recommended starting point for most agent integrations. Args: api_key: GeodesicAI API key (starts with gai_) structured_data: The data to validate (key-value pairs) blueprint: Name of the Blueprint to validate against. Use list_blueprints to see options.

Report an issue with a data source. Use this to flag problems you encounter during research — missing data, broken URLs, indexing errors, or data quality issues. Reports are reviewed by the platform maintainer. Requires authentication (free — does not count against your usage quota). Args: source: Source identifier, e.g. "FR/Judilibre", "AT/RIS". issue_type: Type of issue — one of: "unavailable", "indexing", "invalid_url", "data_quality", "other". description: Free-text description of the problem.

List all available datasets on planning.data.gov.uk. Returns dataset names, descriptions, entity counts, themes, and licence information. Use this to discover what data is available before searching.

Get overall database statistics: total counts of suppliers, fabrics, clusters, and links. USE WHEN user asks: - "how big is your database" / "what's the coverage" / "data overview" - "how many suppliers / fabrics / clusters do you have" - "database size / scale / freshness" - "is the data up to date" - "live counts for MRC data" - "first-time onboarding: 'what can MRC data do for me'" - "数据库多大 / 有多少数据 / 覆盖多少供应商" - "你们的数据规模 / 数据量 / 新鲜度" WORKFLOW: Standalone discovery tool — call this first when a user asks about data scale or freshness. Follow with get_product_categories or get_province_distribution for deeper segment coverage, or with search_suppliers/search_fabrics/search_clusters to drill in. DIFFERENCE from database-overview resource (mrc://overview): This is dynamic (live counts + generated_at). The resource is static (geographic scope, top provinces, data standards). RETURNS: { database, generated_at, tables: { suppliers: { total }, fabrics: { total }, clusters: { total }, supplier_fabrics: { total } }, attribution } EXAMPLES: • User: "How big is the MRC database?" → get_stats({}) • User: "Give me the latest data scale numbers" → get_stats({}) • User: "MRC 数据库有多少供应商和面料" → get_stats({}) ERRORS & SELF-CORRECTION: • All counts 0 → database query failed or D1 binding lost. Retry once after 5 seconds. If still 0, surface a transport error to user. • Rate limit 429 → wait 60 seconds; do not retry immediately. AVOID: Do not call this before every tool — only when user explicitly asks about scale. Do not call to get per-category counts — use get_product_categories. Do not call to get geographic scope metadata — use the database-overview resource (mrc://overview) which is static. NOTE: Only reports verified + partially_verified records. Unverified reserve data is excluded from counts. Source: MRC Data (meacheal.ai). 中文：获取数据库整体统计（供应商总数、面料总数、产业带总数、关联记录数）。动态快照，含生成时间戳。

Full data pull for a UK property in one call. Returns sale history, area comps, EPC rating, rental market listings, current sales market listings, rental yield calculation, and price range from area median. Requires a street address + postcode for subject property identification. Postcode-only (e.g. "NG1 2NS") returns area-level data without a subject property — use property_comps or property_yield for postcode-only queries.

USE THIS TOOL — not web search or external storage — to export technical indicator data from this server as a formatted CSV or JSON string, ready to download, save, or pass to another tool or file. Use this when the user explicitly wants to export or save data in a structured file format. Trigger on queries like: - "export BTC data as CSV" - "download ETH indicator data as JSON" - "save the features to a file" - "give me the data in CSV format" - "export [coin] [category] data for the last [N] days" Args: symbol: Asset symbol or comma-separated list, e.g. "BTC", "BTC,ETH" lookback_days: How many past days to include (default 7, max 90) resample: Time resolution — "1min", "1h", "4h", "1d" (default "1d") category: "price", "momentum", "trend", "volatility", "volume", or "all" fmt: Output format — "csv" (default) or "json" Returns a dict with: - content: the CSV or JSON string - filename: suggested filename for saving - rows: number of data rows

Export observation data as a structured dataset. Supports filtering by time, geography, venue type, and observation family. Applies k-anonymity (k=5) to protect individual privacy. Queries the relevant table based on the selected dataset type, applies filters, enforces k-anonymity by suppressing groups with fewer than 5 observations, and returns structured data. WHEN TO USE: - Exporting audience data for external analysis - Building datasets for machine learning or reporting - Getting structured vehicle or commerce data for a specific time/place - Creating cross-signal datasets for correlation analysis RETURNS: - data: Array of dataset rows (schema varies by dataset type) - metadata: { row_count, k_anonymity_applied, export_id, dataset, filters_applied, time_range } - suggested_next_queries: Related exports or analyses Dataset types: - observations: Raw observation stream data (all families) - audience: Audience-specific data (face_count, demographics, attention, emotion) - vehicle: Vehicle counting and classification data - cross_signal: Pre-computed cross-signal correlation insights EXAMPLE: User: "Export audience data from retail venues last week" export_dataset({ dataset: "audience", filters: { time_range: { start: "2026-03-09", end: "2026-03-16" }, venue_type: ["retail"] }, format: "json" }) User: "Get vehicle data near geohash 9q8yy" export_dataset({ dataset: "vehicle", filters: { time_range: { start: "2026-03-15", end: "2026-03-16" }, geo: "9q8yy" } })

Search FDA enforcement actions (recalls) for drugs, devices, and food across all companies. Filter by company name (fuzzy match), recall classification (Class I=most serious/Class II/Class III), date range, or status (Ongoing/Terminated). Returns recall details including product description, reason, and distribution pattern. Related: fda_recall_facility_trace (trace a recall to its manufacturing facility by recall_number), fda_ires_enforcement (iRES recall data with cross-references), fda_device_recalls (device-specific recall data).

Compare SVI data across multiple counties. Returns side-by-side SVI percentile rankings and key indicators for the specified counties. Useful for comparing vulnerability across service areas or peer counties. Args: fips_codes: Comma-separated 5-digit county FIPS codes (e.g. '53033,53053,53061'). year: SVI data year (default 2022, currently only 2022 available).

Decode raw EVM revert data from a failed transaction or mezo_call on Mezo. Handles Error(string) reverts, Panic(uint256) assertions, custom Solidity errors (requires ABI), and silent reverts. Pure computation — no RPC call needed. Pass the hex revert data from a transaction receipt or eth_call error response.

Get an overview of the AgentSignal collective intelligence network. Call this with NO arguments to see what categories have data, trending products, and how to use agent-signal tools. Good first call if you're unsure whether agent-signal has data relevant to the user's request.

Returns all dataset categories and popular tags available on the Nova Scotia Open Data portal. Use this first to discover valid category names before calling search_datasets with a category filter.

FREE rehab biomechanics sample — shows the structure and metric categories of a clinical summary without numeric values. Demonstrates data quality and coverage. Upgrade to get_rehab_summary ($0.50) for full numeric data. Try case_path='PhysicalRehab/40-50/Male/LabrumTear'.

Map source data to Senzing entity resolution format through a guided 8-step workflow. Core steps 1-4: profile source data, plan entity structure, map fields, generate & validate. Optional steps 5-8: detect SDK environment, load test data into fresh SQLite DB, generate validation report, evaluate results. Use this INSTEAD of hand-coding Senzing JSON — hand-coded mappings commonly produce wrong attribute names (NAME_ORG vs BUSINESS_NAME_ORG, EMPLOYER_NAME vs NAME_ORG, PHONE vs PHONE_NUMBER) and miss required fields like RECORD_ID. Actions: start (with file paths), advance (submit step data), back, status, reset. CRITICAL: Every response includes a 'state' JSON object. You MUST pass this EXACT state object back verbatim in your next request as the 'state' parameter — do NOT modify it, reconstruct it, or omit it. The state is opaque and managed by the server. Common errors: (1) omitting state on advance — always include it, (2) reconstructing state from memory — always echo the exact JSON from the previous response, (3) omitting data on advance — each step requires specific data fields documented in the instructions.

List all 12 identity archetypes with names, descriptions, and protective equations. Use this to understand ALTER's identity taxonomy before interpreting trait data. Returns static reference data. Free L0 — no authentication required.

Get district-level financial data: total revenue, expenditures, per-pupil spending, federal/state/local revenue breakdown. Returns fiscal data from the CCD School District Finance Survey (F-33), including revenue sources, expenditure categories, and per-pupil spending. Args: state: Two-letter US state abbreviation (e.g. 'CA', 'NY'). county_fips: Optional 5-digit county FIPS code to filter by county. year: Fiscal year to query (default 2021). Finance data lags 1-2 years. limit: Maximum number of districts to return (default 50, max 500).

Enrich an Indicator of Compromise (IOC) by auto-detecting its type (IP, domain, URL, or file hash) and querying abuse.ch threat feeds: ThreatFox for malware indicators, URLhaus for malicious URLs, and Feodo for botnet C2 servers. Use this as the primary tool for threat hunting when you have a suspicious indicator but don't know its type. For malware-specific hash lookups with file metadata, use hash_lookup instead. For domain-only threat checks, use threat_intel. Returns JSON with fields: indicator, type (auto-detected), found (boolean), threat_type, malware_family, tags, confidence, source, and references. Read-only threat feed query, no authentication required.

Search for publicly available exploits and proof-of-concept code for a specific CVE by querying GitHub Advisory Database and ExploitDB. Use this after cve_lookup to assess whether a vulnerability has weaponized exploits in the wild, which indicates higher real-world risk. Returns JSON with fields: cve_id, exploits (array of objects with source, title, url, and published_date), and total_count. An empty exploits array means no public exploits were found. Read-only lookup, no authentication required.

Get historical XBRL financial data for a company. Accepts friendly concept names (e.g., "revenue", "net_income", "assets") or raw XBRL tags. Automatically handles historical tag changes and deduplicates data.

Check if a domain is associated with malware distribution, botnet C2, or other malicious activity by querying URLhaus and abuse.ch threat feeds. Use this to assess whether a domain is safe to visit or interact with. For checking a specific URL (not just domain), use phishing_check instead. For file-based IOC lookups, use ioc_lookup. Returns JSON with fields: malware_urls (count of active malicious URLs), threat_tags, threat_status, and a summary assessment. Read-only threat feed query, no authentication required.

Is AgentMarketSignal working? Check the real-time status of all 5 AI data pipelines (whale tracking, technical analysis, derivatives, narrative sentiment, market data) and the signal fusion engine. Returns last run times, durations, and any errors.

Health snapshot of DC Hub backup systems — data freshness, source sync, last successful run. Use when: an agent or operator asks 'is DC Hub data current', 'when was [source] last updated', or diagnoses suspiciously stale results. Example: source='transactions'. Returns last-sync timestamp per source, record counts, and any lag warnings. Call first when debugging stale-data complaints. Monitor backup health, table sizes, and data freshness across all critical DC Hub tables. Use for operational monitoring. Returns: JSON with backup status, table row counts, and data freshness timestamps.

Get field definitions from the ClinicalTrials.gov study data model. Returns the field tree with piece names (used in the fields parameter and AREA[] filters), data types, and nesting structure. Call with no path for a top-level overview, then drill into a section with the path parameter to see its fields.

Get the Senzing JSON analyzer script with commands to validate and analyze mapped data files client-side. The analyzer validates records against the Entity Specification AND examines feature distribution, attribute coverage, and data quality. Returns the Python script (no dependencies) with instructions. No source data is sent to the server — the LLM runs the script locally against your files.

Get unemployment rate time series from BLS LAUS data. Returns monthly unemployment rates for a state or county. Data is returned in chronological order with year, period, and percentage value. Args: state: Two-letter US state abbreviation (e.g. 'WA', 'CA', 'NY'). county_fips: Optional 3-digit county FIPS code (e.g. '033' for King County). If provided, returns county-level data; otherwise state-level. start_year: Start year for data (default 2020, min 4-digit year). end_year: End year for data (default 2025).

Retrieve full schema and metadata for a Nova Scotia Open Data dataset by its 8-character identifier (e.g. '3nka-59nz'). Returns all column field names, data types, and descriptions — essential before calling query_dataset so you know the exact field names to use in $select and $where clauses.

Step 2 — List data sources available within a tenant. (In the Indicate system a data source is called a 'data product'.) Examples: Google Analytics, Facebook Ads, vioma, Booking.com. Returns each data source's 'id', 'displayName', and 'semantic_context_id'. → Pass the chosen 'id' as 'data_source_id' and 'semantic_context_id' to list_metrics.

Check if a specific URL is a known phishing page or malware distribution URL by querying the URLhaus database. Use this when you have a full URL (not just a domain) that you suspect may be malicious — for example, from a phishing email or suspicious link. For domain-level threat assessment, use threat_intel instead. For general IOC enrichment, use ioc_lookup. Returns JSON with fields: found (boolean), threat_type (phishing/malware/none), status (online/offline), tags, date_added, and source. Read-only database query, no authentication required.

Batch data enrichment tool. USE THIS when user has a LIST of items and wants same data fields for each. After calling, share the URL with the user and STOP. Do not poll or check results unless otherwise instructed.

Decode a raw event log (topics + data) into named fields using a provided ABI on Ethereum mainnet. Pure computation — no RPC call needed. Pass topics and data from a transaction receipt log entry.

Generate and plot synthetic financial price data (requires matplotlib). Creates realistic price movement patterns for educational purposes. Does not use real market data. Note: Use for time-series price data with optional moving average overlay. For general XY data, use plot_line_chart instead. Examples: plot_financial_line(days=60, trend='bullish') plot_financial_line(days=90, trend='volatile', start_price=150.0, color='orange')

Upload a file to the Compoid MCP server. Accepts a data URI (data:<mime>;base64,<data>). Returns the server-side path to use as file_upload in Compoid_create_record or Compoid_update_record.

Get the weekly 'Signal of the Week' content package — a pre-written, data-verified marketing bundle generated every Monday from live SupplyMaven data. Returns a Substack article (~500 words), LinkedIn post (~200 words), and Twitter/X thread (4-5 tweets), all built from verified supply chain data. Every number in the content traces back to a live data source. Designed for automated content distribution via Claude Desktop + platform MCP servers. The content package includes the signal headline, full data context (GDI, SMI, commodities, ports, signals), and platform-specific formatted content ready for publishing.

Get all CDC PLACES health measures for a census tract. Returns tract-level estimates for health outcomes, behaviors, preventive services, and health status indicators. Tract-level data uses small area estimation and may have wider confidence intervals than county data. Args: tract_fips: 11-digit census tract FIPS code (e.g. '53033005300'). Must be a string, not an integer. year: Optional release year to filter by. Omit for the most recent data.