Tool search 101,866 tools · 5,225 live servers

Search the Sovereign AI Blog for articles matching a natural language query, optionally filtered by tag and sorted by relevance or date. Behaviour matrix: - query='', sort=* -> list newest-first, optionally tag-filtered - query!='', sort=relevance -> TF-IDF ranked, optionally tag-filtered - query!='', sort=date_desc -> TF-IDF filtered (score > 0.001), then sorted by date Pure read-only, deterministic for a given KB snapshot.

[cost: rag (one embed + one vector search) | read-only, network: outbound to embed model only | rate-limited per IP] Like `lookup_response_code` but augmented: returns the static RFC entry PLUS the top vendor-specific RAG hits for the exact code (and any free-text context the user pasted). When the static entry carries known vendor-specific reason-phrase variants (e.g. 484 + opensips → 'Invalid FROM' from `parse_from.c`), those phrases are folded into the embed query so the right vendor docs surface. Use when the user asks 'why did <vendor> reject this with <code>?' and you want vendor-grounded common causes, not just the RFC text. Especially helpful for fax-rejection paths - 488 / 415 / 606 on a T.38 reinvite (`m=image udptl t38`) is one of the most common 488 variants and the tool surfaces FreeSWITCH `mod_spandsp` / Cisco CUBE / AudioCodes T.38 docs alongside the RFC text. Pair with: `lookup_response_code` first (cheaper); `lint_sip_request` when the code is 4xx and they have the offending request; `compare_sdp_offer_answer` for 488/415 caused by a T.38 reinvite SDP mismatch; `validate_stir_shaken_identity` when the code is 438; `stir_attestation_explainer` for STIR-shaped codes (428/436/437/438/608); `dns_diagnose_sip_target` when the code is 503 / 408 and routing is suspect.

Query a staged synthetic customer export. This is a monitored decoy boundary.

Search the regulatory corpus using keyword / trigram matching. Uses PostgreSQL trigram similarity on document titles and summaries. Returns documents ranked by relevance with summaries and classification tags. Prefer list_documents with filters (regulation, entity_type, source) first. Only use this for free-text keyword search when structured filters aren't sufficient. Args: query: Search terms (e.g. 'strong customer authentication', 'ICT risk', 'AML reporting'). per_page: Number of results (default 20, max 100).

Get regulatory obligations - specific requirements extracted from regulations. Each obligation includes the requirement text, applicable article reference, deadline, which entity types it applies to, actor roles, and current status. Results are paginated (max 50 per page). Supports keyword search via the query parameter (trigram + ILIKE matching on obligation text). Combine with regulation, entity_type, and actor_role filters for precise results. Set canonical=True to get deduplicated canonical obligations with enforcement intelligence instead. Canonical obligations return one entry per unique legal requirement per actor role, with compliance difficulty and enforcement metrics. Use get_actor_roles first to discover available actor roles per regulation. Args: entity_type: Filter by entity type code (e.g. 'credit_institution', 'payment_institution'). regulation: Filter by regulation code (e.g. 'dora', 'mica', 'aml'). status: Filter by status: 'upcoming', 'active', 'overdue', or 'expired'. query: Keyword search on obligation text (e.g. 'ICT risk', 'strong customer authentication'). actor_role: Comma-separated actor roles to filter by (e.g. 'credit_institution,significant_institution'). Use get_actor_roles to see available roles. canonical: If True, return deduplicated canonical obligations with enforcement intelligence instead of raw obligations. page: Page number (default 1). per_page: Results per page (default 20, max 50).

Return Finlex search URL for Finnish statute keyword search. Finlex has no public JSON search API — returns the search URL for Claude to fetch. Args: query: Search terms in Finnish or English (e.g. 'kilpailukielto', 'non-compete').

Return EUR-Lex search URL for finding regulation provisions by keyword. Use when you don't know the exact article number but need to find relevant provisions. Requires Velvoite Premium API key. Args: query: Search terms (e.g. 'data processing agreement processor obligations'). regulation: Optional regulation code to scope the search (e.g. 'gdpr').

Search CJEU case law via EUR-Lex CELLAR SPARQL (live — not limited to Velvoite corpus). Returns cases matching keywords in the case title. Use to find court decisions on a specific regulation, topic, or legal concept. Fetch the returned url to read the full judgment text. Requires Velvoite Premium API key. Args: query: Keywords to search in case titles (e.g. 'money laundering', 'crypto-assets', 'payment institution authorisation'). Phrase search — keep it specific. article_ref: Optional extra keyword to append to the title search (e.g. 'Directive 2015/849', 'GDPR Article 17'). CJEU titles rarely contain article numbers — use the regulation name instead.

Return access details for a Finnish Supreme Administrative Court (KHO) precedent decision. Requires Velvoite Premium API key. KHO decisions are cited as KHO:YYYY:N (e.g. KHO:2024:52). Use search_kho_decisions(year) to browse all decisions for a given year. ACCESS PATTERN — follow this order: 1. Use the returned search_query with web_search to find the kho.fi page 2. From search results, fetch the kho.fi URL directly 3. Do NOT fetch finlex_url directly — Finlex requires prior search provenance Args: year: Decision year (e.g. '2024'). number: Decision number within the year (e.g. '52').

Evaluate a PromQL query in a range of time