Tool search 164,478 tools · 10,067 live servers

Search documentation with hybrid semantic (vector) and keyword (BM25) search. Use semanticWeight to choose keyword-only (0), semantic-only (1), or a blend; mid values fuse rankings with RRF. Supports Tiger Cloud (TimescaleDB), PostgreSQL, and PostGIS.

Retrieve detailed skills for TimescaleDB operations and best practices. ## Available Skills <available_skills> [9 ]{name description}: design-postgis-tables Comprehensive PostGIS spatial table design reference covering geometry types, coordinate systems, spatial indexing, and performance patterns for location-based applications design-postgres-tables "Use this skill for general PostgreSQL table design.\n\n**Trigger when user asks to:**\n- Design PostgreSQL tables, schemas, or data models when creating new tables and when modifying existing ones.\n- Choose data types, constraints, or indexes for PostgreSQL\n- Create user tables, order tables, reference tables, or JSONB schemas\n- Understand PostgreSQL best practices for normalization, constraints, or indexing\n- Design update-heavy, upsert-heavy, or OLTP-style tables\n\n\n**Keywords:** PostgreSQL schema, table design, data types, PRIMARY KEY, FOREIGN KEY, indexes, B-tree, GIN, JSONB, constraints, normalization, identity columns, partitioning, row-level security\n\nComprehensive reference covering data types, indexing strategies, constraints, JSONB patterns, partitioning, and PostgreSQL-specific best practices.\n" find-hypertable-candidates "Use this skill to analyze an existing PostgreSQL database and identify which tables should be converted to Timescale/TimescaleDB hypertables.\n\n**Trigger when user asks to:**\n- Analyze database tables for hypertable conversion potential\n- Identify time-series or event tables in an existing schema\n- Evaluate if a table would benefit from Timescale/TimescaleDB\n- Audit PostgreSQL tables for migration to Timescale/TimescaleDB/TigerData\n- Score or rank tables for hypertable candidacy\n\n\n**Keywords:** hypertable candidate, table analysis, migration assessment, Timescale, TimescaleDB, time-series detection, insert-heavy tables, event logs, audit tables\n\nProvides SQL queries to analyze table statistics, index patterns, and query patterns. Includes scoring criteria (8+ points = good candidate) and pattern recognition for IoT, events, transactions, and sequential data.\n" migrate-postgres-tables-to-hypertables "Use this skill to migrate identified PostgreSQL tables to Timescale/TimescaleDB hypertables with optimal configuration and validation.\n\n**Trigger when user asks to:**\n- Migrate or convert PostgreSQL tables to hypertables\n- Execute hypertable migration with minimal downtime\n- Plan blue-green migration for large tables\n- Validate hypertable migration success\n- Configure compression after migration\n\n**Prerequisites:** Tables already identified as candidates (use find-hypertable-candidates first if needed)\n\n**Keywords:** migrate to hypertable, convert table, Timescale, TimescaleDB, blue-green migration, in-place conversion, create_hypertable, migration validation, compression setup\n\nStep-by-step migration planning including: partition column selection, chunk interval calculation, PK/constraint handling, migration execution (in-place vs blue-green), and performance validation queries.\n" pgvector-semantic-search "Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search.\n\n**Trigger when user asks to:**\n- Store or search vector embeddings in PostgreSQL\n- Set up semantic search, similarity search, or nearest neighbor search\n- Create HNSW or IVFFlat indexes for vectors\n- Implement RAG (Retrieval Augmented Generation) with PostgreSQL\n- Optimize pgvector performance, recall, or memory usage\n- Use binary quantization for large vector datasets\n\n**Keywords:** pgvector, embeddings, semantic search, vector similarity, HNSW, IVFFlat, halfvec, cosine distance, nearest neighbor, RAG, LLM, AI search\n\nCovers: halfvec storage, HNSW index configuration (m, ef_construction, ef_search), quantization strategies, filtered search, bulk loading, and performance tuning.\n" postgres "Use this skill for any PostgreSQL database work — table design, indexing, data types, constraints, extensions (pgvector, PostGIS, TimescaleDB), search, and migrations.\n\n**Trigger when user asks to:**\n- Design or modify PostgreSQL tables, schemas, or data models\n- Choose data types, constraints, indexes, or partitioning strategies\n- Work with pgvector embeddings, semantic search, or RAG\n- Set up full-text search, hybrid search, or BM25 ranking\n- Use PostGIS for spatial/geographic data\n- Set up TimescaleDB hypertables for time-series data\n- Migrate tables to hypertables or evaluate migration candidates\n- Plan or execute safe schema migrations with zero downtime\n\n**Keywords:** PostgreSQL, Postgres, SQL, schema, table design, indexes, constraints, pgvector, PostGIS, TimescaleDB, hypertable, semantic search, hybrid search, BM25, time-series, migration\n" postgres-database-migration "Use this skill for planning, testing, and safely executing PostgreSQL schema migrations — especially when working with production data or shared databases.\n\n**Trigger when user asks to:**\n- Test a schema migration before applying it to production\n- Add, remove, or rename columns safely on a live table\n- Change a column's data type without downtime\n- Add or drop indexes, constraints, or foreign keys on large tables\n- Understand which ALTER TABLE operations lock the table\n- Roll back a failed migration\n- Plan a zero-downtime migration strategy\n- Fork a database to test a migration safely\n\n**Keywords:** migration, schema change, ALTER TABLE, add column, drop column, rename column, change type, zero downtime, lock, AccessExclusiveLock, concurrent index, forking, rollback, backfill, deploy\n\nCovers: lock-level reference for every common DDL operation, safe migration patterns, fork-based testing, zero-downtime column changes, index creation, constraint addition, backfill strategies, pre/post-migration validation, and rollback planning.\n" postgres-hybrid-text-search "Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF).\n\n**Trigger when user asks to:**\n- Combine keyword and semantic search\n- Implement hybrid search or multi-modal retrieval\n- Use BM25/pg_textsearch with pgvector together\n- Implement RRF (Reciprocal Rank Fusion) for search\n- Build search that handles both exact terms and meaning\n\n\n**Keywords:** hybrid search, BM25, pg_textsearch, RRF, reciprocal rank fusion, keyword search, full-text search, reranking, cross-encoder\n\nCovers: pg_textsearch BM25 index setup, parallel query patterns, client-side RRF fusion (Python/TypeScript), weighting strategies, and optional ML reranking.\n" setup-timescaledb-hypertables "Use this skill when creating database schemas or tables for Timescale, TimescaleDB, TigerData, or Tiger Cloud, especially for time-series, IoT, metrics, events, or log data. Use this to improve the performance of any insert-heavy table.\n\n**Trigger when user asks to:**\n- Create or design SQL schemas/tables AND Timescale/TimescaleDB/TigerData/Tiger Cloud is available\n- Set up hypertables, compression, retention policies, or continuous aggregates\n- Configure partition columns, segment_by, order_by, or chunk intervals\n- Optimize time-series database performance or storage\n- Create tables for sensors, metrics, telemetry, events, or transaction logs\n\n**Keywords:** CREATE TABLE, hypertable, Timescale, TimescaleDB, time-series, IoT, metrics, sensor data, compression policy, continuous aggregates, columnstore, retention policy, chunk interval, segment_by, order_by\n\nStep-by-step instructions for hypertable creation, column selection, compression policies, retention, continuous aggregates, and indexes.\n" </available_skills>

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

Fetch SEC XBRL frames for one concept × one period across all reporting companies. Inline response returns a page of the ranked companies — start at the top or pass offset/next_offset to walk further down the ranking; the full frames response (all reporters) is materialized as df_<id> when a canvas is available, queryable via secedgar_dataframe_query. Accepts friendly names like "revenue" or "assets" (discover via secedgar_search_concepts) or raw XBRL tags. One call hits one XBRL tag — when a friendly name maps to multiple same-meaning tags, the response's `unqueried_tags` lists the others; call again per tag and UNION/COALESCE in SQL with an analysis-specific priority (e.g. SalesRevenueGoodsNet is goods-only). The response's `related_tags` separately flags alternate-DEFINITION tags a meaningful share of filers use as their primary line (e.g. cash incl. restricted cash, equity incl. noncontrolling interest) — a whole-universe screen on the base tag silently omits those filers; query them separately, but do not blindly union (the semantics differ). Response includes `value_distribution` and `period_end_range` to flag XBRL scale-factor anomalies and fiscal-year mixing.

Run a single-statement SELECT against the canvas dataframes registered by secedgar_fetch_frames, secedgar_search_filings, and secedgar_get_financials. Read-only: writes, DDL, DROP, COPY, PRAGMA, ATTACH, and external-file table functions are rejected. System catalogs (information_schema, pg_catalog, sqlite_master, duckdb_*) are denied — list dataframes via secedgar_dataframe_describe. Optional register_as chains the result as a new dataframe with a fresh TTL.

Récupère une décision du Conseil d'État par son numéro de pourvoi. Essaie d'abord le bulk JADE DILA (lookup SQL exact), puis si introuvable tente ArianeWeb Sinequa — les deux bases ont des couvertures complémentaires. Pour retrouver une décision via identifiant DCE_*, utiliser `get_decision_text` à la place. ⚠️ **Numéros réutilisés** : le CE a réattribué ses numéros de pourvoi d'une époque à l'autre. 7 938 numéros sont portés par plusieurs décisions (16 143 décisions concernées, mesuré le 29 août 2026). Le n° 74052, par exemple, désigne à la fois un arrêt de 1969 sur des quotas de mouture et l'arrêt d'Assemblée du 3 février 1989 « Compagnie Alitalia ». Quand c'est le cas, la réponse porte un champ `avertissement` et un champ `homonymes` listant les autres décisions du même numéro. **Ne jamais conclure d'une seule réponse qu'un arrêt n'existe pas** : lire `homonymes`, et désambiguïser en citant toujours la date et la formation (« Ass., 3 février 1989, n° 74052 »). Args: numero: numéro de pourvoi (ex : "497566", "358109") Returns: Décision avec métadonnées — plus `homonymes` et `avertissement` si d'autres décisions portent le même numéro. Ou dict d'erreur structuré `{error, error_category: "not_found"}` si introuvable dans les deux bases.

Récupère une décision administrative par son **numéro de requête exact**. Couvre toutes les juridictions : Conseil d'État, cours administratives d'appel (CAA), tribunaux administratifs (TA). Utilise un lookup SQL exact sur le champ `numero` — pas de FTS5, pas de faux positifs. ⚠️ **Désambiguïsation indispensable** : un même numéro à 7 chiffres (ex: 2200433) est partagé par 24+ tribunaux administratifs différents (chaque TA a sa propre série annuelle qui repart à 1). **Si tu sais quelle juridiction a rendu la décision, passe-la TOUJOURS.** Sans `juridiction`, le repli sur l'API live n'interroge que le Conseil d'État et les CAA : un numéro de TA peut alors ressortir « introuvable » alors qu'il existe. Dans ce cas, réessaie en nommant le tribunal. ⚠️ **Numéros réutilisés dans le temps** : au-delà du partage entre tribunaux, un même numéro désigne parfois plusieurs décisions de LA MÊME juridiction, rendues à des époques différentes (7 938 numéros du CE, mesuré le 29 août 2026). La réponse porte alors un champ `avertissement` et un champ `homonymes`. **Ne jamais conclure d'une seule réponse qu'une décision n'existe pas.** Args: numero: numéro de requête (ex : "2200433", "2116343", "497566") juridiction: identifiant de la juridiction. **Recommandé pour tout numéro à 7 chiffres** (TA/CAA codifié). Formats acceptés : - **Nom long (recommandé)** : "Cour administrative d'appel de Lyon", "Tribunal administratif de Paris", "Conseil d'État" (avec ou sans accent, casse libre). Matching tolérant via extraction de ville. - **Code court** : "TA69", "TA75", "CAA69", "CE", "TC" — et formes courtes "TA Lyon", "CAA Douai". Depuis le 8 septembre 2026, code, nom et forme courte sont traduits en écritures EXACTES de la base (113 formes pour 45 juridictions) : un code ne rate plus les arrêts anciens. Note : "Lyon" seul reste ambigu (TA Lyon ou CAA Lyon) et n'écarte ni l'un ni l'autre. Dès que le nom porte l'ordre de juridiction ("Tribunal administratif de…", "CAA…", "Conseil d'État"), il est CONTRÔLÉ : une décision d'un autre ordre n'est jamais servie à la place, le tool répond introuvable. Avant le 23 août 2026, demander le TA de Lyon renvoyait silencieusement la CAA de Lyon. Returns: Décision avec métadonnées (id, juridiction, numero, date, titre) — plus `homonymes` et `avertissement` si d'autres décisions du même ordre de juridiction portent ce numéro. Ou `{"error": "introuvable"}` si aucun résultat dans JADE. Exemples : get_admin_decision("2200433", juridiction="Tribunal Administratif de Lyon") → DTA_2200433_20230214 (TA Lyon, 14 fév 2023, RSA dérogatoire) get_admin_decision("473286") # CE n'a pas de doublon, juridiction inutile → DCE_473286_20231123 (CE, non-admission du pourvoi sur la précédente)

Recherche pondérée par pertinence BM25 sur la jurisprudence administrative complète (Conseil d'État + Tribunal des conflits + 9 CAA + 40 TA — pour le TC, filtrer avec juridiction="conflits"). Source : bulk JADE DILA (~550 k décisions full text). Contrairement aux outils `search_admin_recent*` qui trient par date, celui-ci classe par pertinence sémantique des mots-clés. Indispensable pour trouver LES bonnes décisions sur un sujet sans dépendre de l'ancienneté. ⚠️ **Si tu cherches par numéro de requête (7 chiffres ex: 2200433)**, utilise plutôt `get_admin_decision(numero, juridiction=...)` qui fait un lookup SQL exact. La recherche FTS5 d'un numéro court ne le trouve que dans les décisions qui le **citent** dans leur texte (ex: décision de cassation), pas la décision identifiée par ce numéro. Args: query: mots-clés (opérateurs FTS5 : AND/OR/NOT, "phrase exacte", mot*) juridiction: filtre d'ORIGINE (depuis le 8 septembre 2026). Accepte un code (`CE`, `CAA59`, `TA69`, `TC`), un nom complet (« Tribunal administratif de Lille ») ou une forme courte (« TA Lille », « CAA Douai »). La base écrit la même cour de plusieurs façons (« CAA de LYON », « Cour administrative d'appel de Lyon »…) : le filtre les couvre toutes, et ne renvoie QUE des décisions rendues par cette juridiction. La réponse porte `juridiction_filtre` quand le filtre est actif. ⚠️ Valeur NON reconnue (une ville nue « Lyon », une faute de frappe) : elle est alors ajoutée comme mot-clé à la requête — les décisions qui la CITENT remontent aussi — et la réponse le dit dans `note`. Codes : `list_juridictions`. sort: "relevance" (défaut, BM25) ou "date_desc" / "date_asc" date_min: limite inférieure ISO YYYY-MM-DD (optionnel) date_max: limite supérieure ISO YYYY-MM-DD (optionnel) limit: nombre de résultats (défaut 20, max 50) offset: pagination Returns: {"total", "returned", "decisions": [...]} avec extracts BM25.

Download a Eurostat dataset in bulk through the SDMX 2.1 TSV endpoint and stage every observation as a SQL table on the dataframe canvas — the route to a whole dataset, where eurostat_query_dataset is the route to a slice of one. The TSV wire format is roughly half the bytes of the JSON-stat body eurostat_query_dataset reads, so it reaches datasets that would otherwise time out, and it is expanded here into one row per observation. Filters take the same dimension-code map eurostat_query_dataset uses and are applied server-side by Eurostat; call eurostat_get_dataset_info first for the dimension codes and eurostat_get_dimension_values for their values. Narrow with since_period/until_period rather than asking for the most recent N periods — the TSV layout keeps a column for every period whichever is requested, so a period range is what actually shrinks the response. Transfers are bounded by a byte budget enforced while streaming: when it is spent the download stops and budgetExceeded is set, leaving a prefix of the dataset rather than an error. Only preview_limit rows come back inline. When a table is staged, call eurostat_dataframe_describe first to confirm its columns, then eurostat_dataframe_query; without a canvas, rows past the preview are not retained.

List the tables staged on a Eurostat dataframe canvas, with their row counts and column names and types. Call this before eurostat_dataframe_query to learn the table and column names to write SQL against. The canvas_id comes from a eurostat_query_dataset or eurostat_download_dataset response that reported a staged table. Every observation column is flat, but the two stagers write different dimension columns, so read the columns reported here rather than assuming: eurostat_query_dataset gives each dimension a code column named after the dimension (e.g. "geo") plus a label companion (e.g. "geo_label"); eurostat_download_dataset gives code columns only — the bulk endpoint carries no labels — plus a "time" column. Both write the same five measure columns — obs_value, obs_flag, obs_flag_label, conf_status, conf_status_label — carrying the same codes for the same observation, so tables from the two stagers join on dimension codes and time and compare like with like.

Run a read-only SQL SELECT against tables staged on a Eurostat dataframe canvas — the way to reach observations past the 5,000-row inline cap of eurostat_query_dataset and past the inline preview of a eurostat_download_dataset bulk download, and to aggregate, group, or join across staged tables without re-fetching from Eurostat. Call eurostat_dataframe_describe first for the table and column names, which differ between the two stagers. Only a single SELECT statement runs: statement chaining, non-SELECT verbs, and functions that read files or external data are rejected. Columns are flat — every dimension is a code column named after the dimension, the measure is obs_value, the observation flag is obs_flag / obs_flag_label and the confidentiality marker is conf_status / conf_status_label; a "_label" companion per dimension exists only on tables eurostat_query_dataset staged. Both stagers write the same five measure columns with the same codes, so join their tables on dimension codes and time and compare obs_flag or conf_status across them directly.

List the tables and column schemas on a DataCanvas staged by an openFDA search tool. Call before openfda_dataframe_query to discover the exact table name, column names, and DuckDB types needed for valid SQL. row_count is the full staged result set, not the inline preview count. Columns typed JSON hold nested openFDA objects/arrays — query them with DuckDB json functions.

Run a read-only SQL SELECT against a DataCanvas table staged by an openFDA search tool (call one with stage=true; its response carries canvas_id + canvas_table). Enables GROUP BY, COUNT/SUM/AVG, time-series, and joins across the staged result set without re-paging the API. Call openfda_dataframe_describe first to get the exact table and column names. Results are capped at the canvas row limit — when truncated is true, page the rest with ORDER BY plus LIMIT/OFFSET. Scalar fields are stored as text (CAST for numeric math); nested objects/arrays are JSON columns — read them with DuckDB json functions, e.g. json_extract_string(openfda, '$.brand_name[0]'). Only SELECT is allowed — DDL, DML, COPY, and file-reading functions are blocked.

Vue 360 d'un établissement de santé en 1 appel (V0.10). Pendant naturel de `panorama_sante_territoire` côté **site** : agrège en parallèle (a) identification FINESS DREES (raison sociale, adresse, téléphone), (b) statut administratif SIRENE via le resolver SIRET (verdicts site + groupe, best_match, SIREN explorés, dinum_errors, explication LLM-friendly), (c) professionnels rattachés via num_finess (sample borné + flag `truncated` si le site a plus de PS — PAS un count total), (d) historique INSEE (timeline périodes administratives par SIRET candidat). Remplace 3 appels MCP individuels (`verifier_site_actif` + `rpps_dans_etablissement` + `historique_etablissement`) par 1 seul. Utile pour : prospection (qualifier un site avant outreach), audit territorial (cross-check rapide d'un FINESS suspect), enrichissement CRM en batch. **Format de retour** : objet `LookupResult`. Quand `found: true`, payload avec 4 sections (finess, statut_site, professionnels, historique). La section `historique` peut être `available: false` quand le FINESS existe mais qu'aucun SIRET candidat n'a été identifié (RPPS vide + DINUM 0 match) — dans ce cas le `message` reprend celui de `historique_etablissement`. Quand `num_finess` est absent de FINESS DREES, retourne `{found: false, lookupStatus: 'not_found', message}`. Coût : 3 sous-appels parallèles. Cache PostgreSQL absorbe la duplication FINESS-RPC ; le pivot RPPS→DINUM est exécuté en double (verifier + historique partagent la cascade), surcoût p95 ≤ 600 ms — acceptable pour un agrégateur. Pour les besoins ciblés (juste le verdict, juste l'historique), préférer les tools individuels. Payload lourd (~7K tokens) : passer `historique_detail: false` pour un retour allégé (résumé au lieu des timelines SIRENE complètes) en usage batch. Alias acceptés : `numFiness`/`finess`/`id` → `num_finess`.

Check operator readiness. Returns the operator lifecycle state and clear guidance on what to do next. Free. Lifecycle states: - ready: Operator is warm and fully operational — vault AND pricing model verified. Proceed with tool calls. - warming_up: Operator is initializing (cold start). Try a tool call — it will warm up on demand. - misconfigured: Persistence rejected a query with a permanent SQL error (permission denied, missing relation). Paid tools will fail until the operator repairs the database — retrying does not help. - quota_exceeded: The persistence provider (Neon) answered HTTP 402 — the operator's database has exhausted its compute/storage quota, so the books are locked for billing. Paid tools fail; retrying does NOT help. The operator's Authority must restore capacity (upgrade the plan or wait for the quota reset). Free tools remain available. - not_registered: Operator has no Authority relationship yet. Call register_operator first. - no_identity: Operator nsec is not configured. Deployment issue.

Re-run ``ensure_schema()`` on every NeonVault this operator uses. Diagnostic / recovery tool for the case where the Neon HTTP SQL API is returning persistent 4xx errors and the operator suspects the schema isn't there or grants are wrong. Idempotent — uses ``CREATE TABLE IF NOT EXISTS`` so a successful re-run is harmless. Returns the per-step result. If any step raises, surfaces the Neon error message inline (0.31.0 reads the SQL error body that earlier wheels swallowed behind ``raise_for_status``). RESTRICTED to operator — requires proof (nsec-signed).

List tables and columns staged on a DataCanvas by a prior oecd_query_dataset spill. Call this before oecd_dataframe_query to discover exact table and column names for SQL. Only available when CANVAS_PROVIDER_TYPE=duckdb is set.

Run a read-only SQL SELECT against OECD observation tables staged on a DataCanvas by oecd_query_dataset. Call oecd_dataframe_describe first to discover exact table and column names, then use this tool for aggregation, filtering, GROUP BY, JOIN, and window functions. Only available when CANVAS_PROVIDER_TYPE=duckdb is set.

Execute a SoQL query against any dataset on any Socrata portal. Use the search parameter for quick full-text lookup, or combine select/where/group/having/order for full analytical control. Returns rows plus the assembled SoQL string so you can learn the pattern. All SODA 2.1 row values are strings even for numeric columns — check dataType from socrata_get_dataset to determine correct WHERE quoting: Number columns use bare literals (year=2023), Text columns use single-quoted strings (year='2023'). To enumerate distinct values, use select="col, count(*) as n" with group="col" and order="n DESC". When CANVAS_PROVIDER_TYPE=duckdb and rows fill the limit, results spill to a DataCanvas table for SQL-based analysis.

List registered tables in a DataCanvas session — schema, row count, and column names. Shows what datasets are available for SQL queries via socrata_dataframe_query. Only meaningful when CANVAS_PROVIDER_TYPE=duckdb is set. Use after socrata_query_dataset spills a large result set to canvas.

Run SELECT-only SQL against a DataCanvas table populated by socrata_query_dataset. DuckDB infers types from spilled data, so numeric columns that SODA returned as strings become queryable with numeric comparisons (year > 2020, amount < 500). Only works when CANVAS_PROVIDER_TYPE=duckdb is set. Use socrata_dataframe_describe to see registered tables and their schemas.

Search fossil occurrences filtered by taxon, geologic time, geography, and depositional environment — the flagship. Use base_name for a clade and all its descendants (what "Tyrannosaurus occurrences" usually means), base_id for that same clade by resolved taxon id, or taxon_name for an exact taxon. Bound the age by a named interval (e.g. "Maastrichtian") or a max_ma/min_ma range, and/or a lng/lat bounding box; scope to a single locality with collection_no (take it from a paleobiology_search_collections row). At least one filter is required — taxon, time, place, environment, or collection_no. Every row carries two distinct coordinate systems — modern lng/lat (where the rock is today) and paleo lng/lat (where the landmass sat at deposition) — plus the formation, age interval, and higher classification (phylum through genus); never plot a deep-time occurrence on a modern coastline. Resolve a name with paleobiology_get_taxon first if unsure. Broad queries return many rows: an inline preview answers the immediate question, and when the set outgrows that preview the matching occurrences — up to the per-call cap — stage on a DataCanvas (canvas_id + table_name, returned only then) for SQL via paleobiology_dataframe_query (count by interval, group by formation/country, map by region). The response reports how many occurrences matched in total, which rows this page covers, and the offset that reaches the next page — page through the whole match set with limit/offset.

Run a read-only SQL SELECT against occurrence result sets staged on a DataCanvas by paleobiology_search_occurrences. This is how you analyze a large fossil set without re-fetching it: count occurrences by early_interval, group by formation, country (cc), or accepted_name, or filter by a paleo/modern coordinate range. The classification column is JSON — roll up by rank with json_extract_string(classification, '$.family') (also $.phylum, $.class, $.order, $.genus). Staged rows are occurrences, so collection-only fields such as lithology are not present. Reference tables by the table_name that search_occurrences returned — call paleobiology_dataframe_describe first if you do not know the table or column names. SELECT only; writes and file-reading functions are rejected.

List the tables and their columns staged on a DataCanvas by paleobiology_search_occurrences. Call this before paleobiology_dataframe_query to discover the exact table_name and column names to reference in SQL.

Run a read-only SQL SELECT against the measurement tables openaq_get_measurements staged on a DataCanvas. Reference tables by the name the measurements call returned (measurements_<sensorId>). For aggregation (monthly means, exceedance counts) and cross-sensor comparison over series too large to inline. Only SELECT is allowed — writes, DDL, and file/network table functions are rejected.

List the tables and columns staged on a DataCanvas so you can write valid SQL for openaq_dataframe_query without guessing column names. Returns each measurement table (measurements_<sensorId>) with its row count and column names. Requires DataCanvas to be enabled.

Query any Treasury Fiscal Data endpoint by path, field list, filters, sort, and page. Call treasury_list_datasets first to get the correct endpoint path and exact field names — a typo in either causes a 400. Filter syntax: each condition is { field, operator, value } where operator is eq/gt/gte/lt/lte/in (e.g., record_date:gte:2024-01-01). Multiple conditions are ANDed together. All response values are strings per the API contract, including numbers and dates; "null" (string) means no value. Supply canvas_id to stage the page result as a DataCanvas table — read its column schema with treasury_dataframe_describe, then run SQL over it with treasury_dataframe_query (requires CANVAS_PROVIDER_TYPE=duckdb on the server).

Fetch national debt (Debt to the Penny) — total public debt outstanding broken into publicly-held debt and intragovernmental holdings. Three modes: "latest" returns the most recent business day's record; "date" returns the record for a specific date (must be a business day — the API only records debt on days markets are open); "series" returns a date range, staging the full result as a DataCanvas table when canvas_id is set or the range matches more than 500 rows — read the table's column schema with treasury_dataframe_describe, then run SQL over it with treasury_dataframe_query. Records go back to 1993-04-01.

Average interest rates Treasury pays on its outstanding securities by security type. Answers "what is the government's cost of borrowing?" Covers every type Treasury reports — marketable issues, non-marketable series, and the aggregate totals — and which types it reports changes over the years, so omit security_type to see the ones a given period carries. Rates are percentages, not basis points. Updated monthly (end-of-month records). Mode "latest" returns the most recent month's rates for all or one security type; "series" returns a time history, staging the result as a DataCanvas table when canvas_id is set or the range matches more than 200 rows — read the table's column schema with treasury_dataframe_describe, then run SQL over it with treasury_dataframe_query.

Official Treasury reporting exchange rates for ~165 countries — the rates US federal agencies are required to use when converting foreign currency to USD for official reporting. Published quarterly (March 31, June 30, Sep 30, Dec 31); mode "latest" returns the most recently published quarter. Rate is expressed as foreign currency units per 1 USD (e.g., a Japan-Yen rate of 159.41 means 1 USD = 159.41 JPY). These are NOT market exchange rates and are not suitable for financial transaction pricing. Mode "series" stages the result as a DataCanvas table when canvas_id is set or the range matches more than 500 rows — read the table's column schema with treasury_dataframe_describe, then run SQL over it with treasury_dataframe_query.

Run a single-statement SELECT against DataCanvas dataframes registered by treasury_query_dataset, treasury_get_debt, treasury_get_interest_rates, and treasury_get_exchange_rates. Read-only: writes, DDL, DROP, COPY, PRAGMA, ATTACH, and external-file table functions are rejected. System catalogs (information_schema, pg_catalog, sqlite_master, duckdb_*) are denied at the bridge layer. All Treasury dataframe columns are VARCHAR — CAST to DECIMAL or DATE for arithmetic and date comparisons. Use treasury_dataframe_describe to list available table names and column schemas before querying.

WHEN: developer needs correct X++ select or T-SQL for D365 tables with proper joins. Triggers: 'X++ select', 'generate a query', 'SQL for', 'join with', 'how to query', 'générer une requête', 'write a select statement', 'select from', 'X++ query for', 'requête X++', 'écrire une select'. Generate both X++ select statements and equivalent T-SQL queries for D365 F&O tables. Uses real field names, relations, and indexes from the knowledge base to produce correct joins. Supports: field selection, multi-table joins (auto-detects relations), WHERE filters, ORDER BY, TOP/firstonly, cross-company. Also accepts natural language descriptions like 'find all open sales orders for customer 1001 with CustTable join'. [!] For multi-table joins, call find_related_objects (or get_relation_graph if the relation index is loaded) FIRST to get the correct FK relations -- this tool will then produce accurate join conditions. [!] The generated X++ is a template -- adapt it to your custom code context before using in production. Returns side-by-side X++ and SQL with explanations.

Weather forecast for coordinates: hourly and/or daily variables for up to 16 days ahead, with optional past_days (up to 92) for recent history. Use past_days instead of openmeteo_get_historical for dates within the last 1–5 days, since ERA5 has a variable lag. Returns per-timestamp records — each hourly entry contains a "time" field (ISO 8601) plus one key per requested variable; each daily entry contains a "time" field (YYYY-MM-DD) plus requested variables. Common hourly variables: temperature_2m, precipitation, wind_speed_10m, relative_humidity_2m, cloud_cover, uv_index, apparent_temperature, precipitation_probability, weather_code, surface_pressure, visibility, wind_direction_10m, wind_gusts_10m, dew_point_2m. Common daily variables: temperature_2m_max, temperature_2m_min, precipitation_sum, wind_speed_10m_max, sunrise, sunset, uv_index_max, precipitation_hours, weather_code. A wide window — a large past_days plus many hourly variables — produces thousands of records; these spill to DataCanvas for SQL querying when canvas is enabled, and return a bounded preview with truncated: true when it is not. At least one of hourly_variables or daily_variables is required.

Historical weather from the ERA5 reanalysis archive (1940–present). Requires start_date and end_date (ISO 8601 date, e.g., "2024-07-01"). ERA5 has a variable lag of up to ~5 days — for dates within the last week, use openmeteo_get_forecast with past_days instead. Uses the same variable names as the forecast API for direct comparison. Large date ranges (multi-year hourly) produce thousands of records — these spill to DataCanvas for SQL querying when canvas is enabled, and return a bounded preview with truncated: true when it is not. At least one of hourly_variables or daily_variables is required.

Marine wave and ocean conditions for a coastal or ocean coordinate: wave height, wave period, wave direction, wind-wave height, swell height, sea-surface temperature. Forecast horizon up to 8 days, with optional past_days (up to 92) for recent history — or start_date and end_date together for an archive range, which returns real wave values back to at least 2022. One window per call: a date range is mutually exclusive with forecast_days and past_days, and needs both ends — a lone start_date or end_date is rejected. Returns per-timestamp records — each entry contains a "time" field plus one key per requested variable. Best for open-ocean and coastal exposed points — sheltered inland waters return near-zero wave values. Common hourly variables: wave_height, wave_direction, wave_period, wind_wave_height, wind_wave_direction, wind_wave_period, swell_wave_height, swell_wave_direction, swell_wave_period. Common daily: wave_height_max, wave_direction_dominant, wave_period_max. Note: ocean_current_velocity is null for non-open-ocean coordinates. A wide window — a large past_days or date range plus many variables — produces thousands of records; these spill to DataCanvas for SQL querying when canvas is enabled, and return a bounded preview with truncated: true when it is not.

Modeled CAMS (Copernicus Atmosphere Monitoring Service) air quality: PM2.5, PM10, nitrogen dioxide, sulphur dioxide, ozone, carbon monoxide, dust, pollen, and European/US AQI indices. This is modeled grid data, not measured station readings — for measured data, use openaq-mcp-server. Forecast horizon up to 7 days, with optional past_days (up to 92) for recent history — or start_date and end_date together for an archive range, which returns real CAMS values back to at least 2022-10-01. One window per call: a date range is mutually exclusive with forecast_days and past_days, and needs both ends — a lone start_date or end_date is rejected. Common variables: pm2_5, pm10, carbon_monoxide, nitrogen_dioxide, sulphur_dioxide, ozone, dust, european_aqi, us_aqi, alder_pollen, birch_pollen, grass_pollen, mugwort_pollen, olive_pollen, ragweed_pollen. A wide window — a large past_days or date range plus many variables — produces thousands of records; these spill to DataCanvas for SQL querying when canvas is enabled, and return a bounded preview with truncated: true when it is not.

GloFAS (Global Flood Awareness System) river discharge forecast and historical reanalysis. Returns daily ensemble river discharge (m³/s) for the river nearest to the given coordinates — no river ID needed, the API snaps to the nearest stream. Forecast horizon up to 210 days ahead; reanalysis history back to 1984-01-01. One mode per call: forecast_days for the future outlook, or start_date and end_date together for reanalysis history. The two modes are mutually exclusive, and a date range needs both ends — a lone start_date or end_date is rejected. Available daily variables: "river_discharge" (ensemble mean), "river_discharge_mean", "river_discharge_min", "river_discharge_max", "river_discharge_median", "river_discharge_p25" (25th percentile), "river_discharge_p75" (75th percentile). Returns null for coordinates far from any river or in areas without GloFAS coverage. A wide reanalysis range produces thousands of daily records and spills to DataCanvas for SQL querying when canvas is enabled, returning a bounded preview with truncated: true when it is not.

Long-range climate projections from bias-corrected daily CMIP6 models, covering 1950-01-01 to 2050-12-31 at any coordinate. Answers "what will conditions look like through 2050?" — the future-projection counterpart to openmeteo_get_historical (ERA5, what happened). Daily resolution only. Available models: CMCC_CM2_VHR4, FGOALS_f3_H, HiRAM_SIT_HR, MRI_AGCM3_2_S, EC_Earth3P_HR, MPI_ESM1_2_XR, NICAM16_8S. A model name outside that list is sent upstream rather than rejected here, so a model Open-Meteo adds later still works; if upstream rejects the request, the error names the offending model on its own rather than the whole requested list. With 2+ models each variable appears once per model with the model name as suffix (e.g. temperature_2m_max_CMCC_CM2_VHR4); a single or omitted model returns plain variable names. Not all models carry all variables — missing combinations return null. Multi-decade daily pulls across several models produce thousands of records and spill to DataCanvas for SQL querying when canvas is enabled, returning a bounded preview with truncated: true when it is not.

Query an IMF SDMX dataflow by dimension key over a time range. Returns observations with time_period, value, and status, plus the unit, scale, and decimals of each series — a key resolving to several series carries one entry per series in series_metadata, since unit and scale differ between them. Requires imf_get_database first to obtain the correct key_format and valid dimension codes. Country codes are ISO 3-letter (USA, GBR, DEU — not US, GB, DE). Key format: dot-separated codes in DSD keyPosition order (e.g. USA.NGDP_RPCH.A for WEO). Every position must carry a code: use + to combine codes (e.g. USA+GBR.NGDP_RPCH.A) and * to match every code at a position (e.g. *.NGDP_RPCH.A for all countries). Codelists from imf_get_database enumerate the code universe, not actual coverage — valid codes can still return no_data if the combination has no series. start_period and end_period must be valid period strings (YYYY, YYYY-SN, YYYY-QN, YYYY-MM, or a calendar-valid YYYY-MM-DD) with start_period no later than end_period; malformed or reversed ranges are rejected. A bound covers the whole period it names, so end_period 2023 includes 2023-M12 and 2023-Q4. Large analytical result sets (multi-country, long time range) spill to DataCanvas; call imf_dataframe_describe first to inspect staged tables and columns, then imf_dataframe_query for SQL analysis.

List DataCanvas tables and columns staged by a prior imf_query_dataset call. Returns each table's name, row count, and column schema (name + DuckDB type). Required before imf_dataframe_query to discover the table and column names for SQL.

Run a read-only SQL SELECT against a DataCanvas table staged by imf_query_dataset. Supports multi-country comparisons, time-series aggregation, and cross-indicator joins. Requires imf_dataframe_describe first to discover table and column names. One SELECT statement per call; a leading WITH … SELECT (CTE) is accepted. DML and DDL are rejected.

Assemble a global profile for one commodity in a single call: top-producing countries, the annual production trend, and trade flows (top exporters and importers). Accepts a commodity name, resolves it to item codes, then queries the production (QCL) and trade (TCL) domains and merges the results. Each ranking is a per-country sum across the resolved items, taken at that country's own latest year with data and grouped by unit so incomparable quantities are never added. The trend is returned inline as year/value points. Country-level only (aggregates excluded). When a required domain is not indexed locally, returns a partial profile with a notice naming the gap rather than failing. The full merged observation set spills to a DataCanvas table for deeper SQL via faostat_dataframe_query.

Run a single-statement SELECT against the canvas tables staged by faostat_query_observations and faostat_commodity_profile (table names look like faostat_xxxxxxxx). Use this for cross-country and cross-item aggregation, GROUP BY rankings, joins, and time-series analysis over the full result set the inline preview only sampled. Standard DuckDB SQL — joins, aggregates, window functions, CTEs all work. Read-only: writes, DDL, DROP, COPY, PRAGMA, ATTACH, and external-file table functions are rejected; system catalogs (information_schema, sqlite_master, duckdb_*) are denied — list staged tables via faostat_dataframe_describe. Every row carries its data-quality `flag` — commonly A=Official, B=time-series break, E=Estimated, I=Imputed, M=Missing (value cannot exist), T=Unofficial, X=from an international organization, plus others FAOSTAT defines per domain — keep it in projections, treat any unrecognized flag as informational, and never assume it is official.

List the canvas tables (faostat_xxxxxxxx) staged by faostat_query_observations and faostat_commodity_profile, each with its source tool, the query parameters that produced it, creation/expiry timestamps, row count, and column schema. Call this before faostat_dataframe_query to discover the exact table and column names to reference in SQL. Tables are listed newest-first and paged: pass `name` to describe one table outright, or page with `offset` + `limit` — when the response reports `truncated`, pass the returned `nextOffset` to fetch the rest.

Get historical daily exchange rates for a currency pair over a date range. ECB publishes on business days only — weekends and holidays produce no entry, and no date outside the requested range is ever returned, so a range covering only non-publication days comes back with an empty rates map and a notice explaining why. A same-currency pair returns a rate of 1 on each publication day in the range. Short ranges (≤90 days by default) are returned inline as a date→rate map. When DataCanvas is enabled (CANVAS_PROVIDER_TYPE=duckdb) long ranges spill to it: the response carries spilled=true, a canvas_id, and a table_name — call fx_dataframe_describe to inspect the staged table, then fx_dataframe_query to run SQL against it. Without DataCanvas long ranges stay inline (spilled=false) and the notice says so.

Run a read-only SQL SELECT against DataCanvas tables staged by fx_get_timeseries. Supports aggregations, GROUP BY, window functions, and JOINs across multiple registered tables. Run fx_dataframe_describe first to discover table names and column schemas. Requires DataCanvas (CANVAS_PROVIDER_TYPE=duckdb) — without it this tool is not listed at all and fx_get_timeseries returns every range inline.

Run a read-only SQL SELECT over the bioactivity rows chembl_get_bioactivities spilled to a canvas — rank, group, dedupe, and aggregate across the FULL set, not the inline preview. Reference each staged table by the name chembl_get_bioactivities returned — bioactivities for its potency_ranked view, bioactivities_null_potency for null_potency; discover the staged tables and their columns with chembl_dataframe_describe. Compute honest aggregates here (e.g. SELECT molecule_chembl_id, MEDIAN(pchembl_value) AS med FROM bioactivities WHERE standard_type = 'IC50' GROUP BY 1 ORDER BY 2 DESC). Two independent bounds apply, each reported on its own field: truncated is true when the SQL result exceeded the canvas row cap, and rendered_rows says how many of the returned rows the markdown table holds once its character budget is reached (below row_count on a wide or long result). Page past either bound with SQL LIMIT/OFFSET — append e.g. LIMIT 500 OFFSET 500 and re-call; offsets reach rows beyond the canvas row cap. Requires CANVAS_PROVIDER_TYPE=duckdb.

List the tables and columns staged on a canvas by chembl_get_bioactivities — inspect before calling chembl_dataframe_query to write correct SQL. Returns each table with its row count, kind (table | view), and column names + types. Requires CANVAS_PROVIDER_TYPE=duckdb.

Search National Flood Insurance Program (NFIP) claims data by state, county, ZIP code, and year range. Returns claim counts, amounts paid on building and contents, flood zones, and loss years. state is required — the full NFIP dataset is 2.7 million rows; unfiltered access is prohibited. When DataCanvas is enabled (CANVAS_PROVIDER_TYPE=duckdb) and results exceed the inline preview, the full result set is staged on a canvas for SQL aggregation via fema_dataframe_query. Use fema_dataframe_describe to inspect the staged table schema before writing SQL. Without canvas, results are returned inline up to the limit.

Run a read-only SQL SELECT against a DataCanvas table staged by fema_search_nfip. Enables aggregation, GROUP BY, SUM/COUNT, time-series, and filtered analysis over the full NFIP claims result without re-fetching from the API. Call fema_dataframe_describe first to get the exact table name and column names needed for valid SQL. Only SELECT statements are allowed — DDL, DML, COPY, and file-reading functions are blocked.

List tables and column schemas on a DataCanvas staged by fema_search_nfip. Call this before fema_dataframe_query to discover the exact table name, column names, and DuckDB data types needed to write valid SQL. Row count reflects what was actually staged — check truncated in the fema_search_nfip response to know whether the canvas holds the full matching set.

Run a read-only SQL query against an app's Postgres database and return up to 200 result rows. SELECT only — writes and DDL (INSERT/UPDATE/DELETE/ALTER/DROP/…) are rejected server-side; use vibekit_chat or vibekit_submit_task to have the agent make data or schema changes. Call vibekit_db_schema first to learn the tables. SQL string, max 5000 chars.

Get a daily or instantaneous time series for one USGS site and parameter over a date range, as time-ordered value records. Large sets (>500 records) return the most recent 500 with truncated=true; with DataCanvas enabled they instead spill to a canvas (canvas_id/table_name) for SQL via water_dataframe_query. Use water_find_sites and water_list_parameters to resolve inputs.

Run a read-only SQL SELECT against water data tables staged on a DataCanvas by water_get_series or water_find_sites. Workflow: run water_get_series or water_find_sites (get canvas_id + table_name) → water_dataframe_describe (confirm the table and its columns) → water_dataframe_query (SQL analysis). Only SELECT statements are permitted. At most 10,000 rows are returned; a query matching more is capped and the response sets truncated=true — scope with WHERE/LIMIT, and use SELECT COUNT(*) or water_dataframe_describe to learn the true match count. Requires DataCanvas to be enabled on this server instance. Returns an error if DataCanvas is not available.

List every gnomAD variant in a gene, transcript, or region with allele frequencies and predicted consequences, optionally filtered to one consequence class (lof, missense, synonymous, other) and/or a maximum allele frequency. The full result is staged on a DataCanvas table named gene_variants and an inline preview is returned alongside canvas_id and table_name — run gnomad_dataframe_query against them to rank by AF, count by consequence, or group across the complete set rather than the preview. When the canvas is disabled (CANVAS_PROVIDER_TYPE != duckdb) the tool returns a capped inline preview with spilled=false and canvas_id empty; the SQL path is then unavailable. Supply exactly one of gene, transcript_id, or region. Echoes the effective dataset and build. Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/

Run a read-only SQL SELECT against a canvas table staged by gnomad_list_gene_variants (table gene_variants) or gnomad_search_clinvar (table clinvar_variants). Use the canvas_id and table_name those tools returned to rank by allele frequency, group by consequence class, count loss-of-function variants, or filter the full set the inline preview only sampled. SELECT statements only — writes, DDL, and file/HTTP table functions are rejected by the canvas gate. Call gnomad_dataframe_describe first to discover staged table and column names.

List the tables staged on a canvas and their columns (name and type) so you can write correct SQL for gnomad_dataframe_query. Use the canvas_id returned by gnomad_list_gene_variants or gnomad_search_clinvar. Returns one entry per table with its row count and column schema.

Replay VRP dashboard (z-score, percentile, regime, strategy scores) at any minute since April 2018. Percentiles and z-scores are leak-free: date-bounded in SQL so the backtest only sees data strictly before the `at` timestamp. Alpha tier.

Check operator readiness. Returns the operator lifecycle state and clear guidance on what to do next. Free. Lifecycle states: - ready: Operator is warm and fully operational — vault AND pricing model verified. Proceed with tool calls. - warming_up: Operator is initializing (cold start). Try a tool call — it will warm up on demand. - misconfigured: Persistence rejected a query with a permanent SQL error (permission denied, missing relation). Paid tools will fail until the operator repairs the database — retrying does not help. - quota_exceeded: The persistence provider (Neon) answered HTTP 402 — the operator's database has exhausted its compute/storage quota, so the books are locked for billing. Paid tools fail; retrying does NOT help. The operator's Authority must restore capacity (upgrade the plan or wait for the quota reset). Free tools remain available. - not_registered: Operator has no Authority relationship yet. Call register_operator first. - no_identity: Operator nsec is not configured. Deployment issue.

Re-run ``ensure_schema()`` on every NeonVault this operator uses. Diagnostic / recovery tool for the case where the Neon HTTP SQL API is returning persistent 4xx errors and the operator suspects the schema isn't there or grants are wrong. Idempotent — uses ``CREATE TABLE IF NOT EXISTS`` so a successful re-run is harmless. Returns the per-step result. If any step raises, surfaces the Neon error message inline (0.31.0 reads the SQL error body that earlier wheels swallowed behind ``raise_for_status``). RESTRICTED to operator — requires proof (nsec-signed).

Semantic search across filings, companies, insiders, and managers. Powerful cross-platform search using PostgreSQL full-text search. Perfect for finding specific events, people, or companies.

Support and end-of-life dates for a runtime, OS, database or framework version from endoflife.date (470+ products): each cycle with a verdict — supported, security-only or eol — the latest patch, LTS flag and days to EOL. Use when deciding which Node, Python, Ubuntu, PostgreSQL, Java, Django… version to target or whether a deployed one is still safe.

List or search the products endoflife.ai tracks (500+). Pass an optional "query" substring to find the canonical slug for a product before calling the other tools (e.g. "postgres" → "postgresql"). Returns matching product slugs.

Use this when you need to execute Python, JavaScript, or SQL code in a sandboxed environment and get the output. Supports Python (subprocess), JavaScript (eval), and SQL (in-memory SQLite). 1. output: stdout captured from code execution (max 10KB) 2. language: the language that was executed 3. executionTimeMs: execution duration in milliseconds 4. exitCode: process exit code (0 = success) 5. error: error message if execution failed (null on success) Example output: {"output":"Hello World\n42\n","language":"python","executionTimeMs":234,"exitCode":0,"error":null} Use this FOR running calculations, data transformations, validating code snippets, or querying in-memory databases. Essential when you need computed results rather than static data. Do NOT use for persistent file storage -- sandbox is ephemeral. Do NOT use for generating hashes -- use crypto_generate_hash. Do NOT use for PDF generation -- use document_generate_pdf. Do NOT use for web scraping -- use web_scrape_to_markdown.

Check operator readiness. Returns the operator lifecycle state and clear guidance on what to do next. Free. Lifecycle states: - ready: Operator is warm and fully operational — vault AND pricing model verified. Proceed with tool calls. - warming_up: Operator is initializing (cold start). Try a tool call — it will warm up on demand. - misconfigured: Persistence rejected a query with a permanent SQL error (permission denied, missing relation). Paid tools will fail until the operator repairs the database — retrying does not help. - quota_exceeded: The persistence provider (Neon) answered HTTP 402 — the operator's database has exhausted its compute/storage quota, so the books are locked for billing. Paid tools fail; retrying does NOT help. The operator's Authority must restore capacity (upgrade the plan or wait for the quota reset). Free tools remain available. - not_registered: Operator has no Authority relationship yet. Call register_operator first. - no_identity: Operator nsec is not configured. Deployment issue.

Re-run ``ensure_schema()`` on every NeonVault this operator uses. Diagnostic / recovery tool for the case where the Neon HTTP SQL API is returning persistent 4xx errors and the operator suspects the schema isn't there or grants are wrong. Idempotent — uses ``CREATE TABLE IF NOT EXISTS`` so a successful re-run is harmless. Returns the per-step result. If any step raises, surfaces the Neon error message inline (0.31.0 reads the SQL error body that earlier wheels swallowed behind ``raise_for_status``). RESTRICTED to operator — requires proof (nsec-signed).