Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "verify_lead"
⟨16 unchanged words⟩ server, IBAN, sanctions; a 0-100 lead score.$0.05$0.10 by x402, $0.27 with an API key. ⟨187 unchanged words⟩
Changed the definition of "check_agent_wallet", "verify_lead", "verify_wallet" and 1 more
⟨35 unchanged words⟩ open ERC-8004 feedback, which is not scored.$0.75.$0.005 by x402, $0.75 with an API key. Returns verdict (block, review or no_findings) ⟨84 unchanged words⟩
⟨16 unchanged words⟩ server, IBAN, sanctions; a 0-100 lead score.$0.27.$0.05 by x402, $0.27 with an API key. Returns verdict (real_active, real_inactive, not_found, ambiguous ⟨181 unchanged words⟩
Changed the definition of "sanctions_preview"
⟨9 unchanged words⟩ , EU and UN lists. Returns possible_match, lists_checked, list_dates andlist_dateslist_note only,never anentry. 10 per caller per UTC day, shared ⟨43 unchanged words⟩
Added "wallet_sanctions_preview"; changed the definition of "verify_wallet" (9 tools before, 10 now)
⟨44 unchanged words⟩ on-chain reputation as descriptive signals, never scored.Free ($0).$0.11. Returns risk_score, risk_level, sanctions (hit, lists ⟨49 unchanged words⟩ EVM (0x...) and Solana (base58) addresses. The sanctions match alone is free: the wallet_sanctions_preview tool. Rejected calls are not charged. Args: wallet_address: Blockchain wallet address chain_id: ⟨15 unchanged words⟩
{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":true,"title":"Screen wallet"}
Changed the definition of "check_agent_wallet", "check_entity", "get_risk_score" and 2 more
{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":true,"title":"Check agent wallet"}
{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":true,"title":"Check entity trust"}
Changed the definition of "check_entity" and "get_risk_score"
⟨25 unchanged words⟩ the website domain when you send it. Returnsatrust_score (0-100,score100 = best),atrust_level (high means low risk),levelcluster,andrecommendation,aconfidence,recommendation.top_factors and sources_checked.
Changed the definition of "get_compliance_report"
⟨65 unchanged words⟩ digits) cbe_number: Optional Belgian CBE number (0XXX.XXX.XXX or 10 digits) vat_number: Optional EU VAT number domain: ⟨40 unchanged words⟩
Changed the definition of "check_entity" and "get_risk_score"
Check entity trustCompanyscorecheck via the Limitguard API.Full trust intelligenceCompany check on a business:entity.sanctions screening and country risk, theReturnsDutchtrustKVKscoreregister(for an NL company, and the website domain when you send it. Returns a
Changed the definition of "get_trust_score"
⟨74 unchanged words⟩ another key's or workspace's never are (#946). Signed in with OAuth, your workspace's checks are read instead (#1062). Args: entity_id: The entity name, as ⟨5 unchanged words⟩
Added "sanctions_preview" and "sanctions_screen"; changed the definition of "verify_lead" (7 tools before, 9 now)
⟨16 unchanged words⟩ server, IBAN, sanctions; a 0-100 lead score.$0.24.$0.27. Returns verdict (real_active, real_inactive, not_found, ambiguous ⟨181 unchanged words⟩
Free yes/no sanctions preview against the local OFAC SDN, EU and UN lists. Returns possible_match, lists_checked and list_dates only, never an entry. 10 per caller per UTC day, shared with POST /v1/sanctions/preview, and key holders share a ceiling of 50 per IP; the matched entries are the sanctions_screen tool. Free ($0). Args: name: Company or person name to screen country: Optional ISO 3166-1 alpha-2 country code (orders matches, never excludes one)
Changed the definition of "verify_lead"
⟨45 unchanged words⟩ checks, with flags and one finding perflag.flag or mismatch, a dormant-shell score and, when a target is given, the ICP fit (information only). An input not givenis not checked and nevercounts against the lead. The IBAN account holder ⟨94 unchanged words⟩ Rejected until website phone lookup is switched on target_industries: Ideal-customer industries: SBI/NACE code prefixes ("62") or whole words; information only target_size: Ideal-customer employee range {min, max}, both inclusive; information only
Changed the definition of "check_agent_wallet" and "verify_lead"
⟨62 unchanged words⟩ reason), and sanctions, balance, identity, reputation, wallet_risk andwallet_riskdomain (when a domain is given, else not_requested), each withits ownstatus (ok, unavailable or error). Reputationisanddescriptivedomain are descriptive only and neverchangeschange the verdict. Base only; EVM
Added "check_agent_wallet", "get_trust_score" and "verify_lead"; changed the definition of "get_compliance_report" (4 tools before, 7 now)
⟨16 unchanged words⟩ score with the rules that fired, correlations,ateverymostfinding3asfindingsa ranked action, a per-source status table (ok / unavailable ⟨82 unchanged words⟩
Check a counterparty agent's EVM wallet in one call: OFAC SDN digital-currency address list match, Base USDC and ETH balance, ERC-8004 identity registration (and, given an agent id, that agent's owner and payment wallet) and open ERC-8004 feedback, which is not scored. $0.75. Returns verdict (block, review or no_findings) with verdict_reasons, the components that ran and those that did not (with a reason), and sanctions, balance, identity, reputation and wallet_risk, each with its own status (ok, unavailable or error). Reputation is descriptive…
Changed the definition of "check_entity"
Check entity trust score viaLimitGuardLimitguard API. Full trust intelligence check on a business ⟨40 unchanged words⟩
Added "get_compliance_report" (3 tools before, 4 now)
Per-entity report built from one real check. Registry identity, sanctions and PEP screens, domain signals, risk score with the rules that fired, correlations, at most 3 findings, a per-source status table (ok / unavailable / error) and a report hash. Args: entity_name: Full legal name (with country; omit when sending check_id) country: ISO 3166-1 alpha-2 country code kvk_number: Optional Dutch KVK number (8 digits) cbe_number: Optional Belgian CBE number (0XXX.XXX.XXX) …
Changed the definition of "check_entity", "get_risk_score" and "verify_wallet"
before
—after
{"destructiveHint":false,"openWorldHint":true,"readOnlyHint":true,"title":"Check entity trust"}before
—after
{"destructiveHint":false,"openWorldHint":true,"readOnlyHint":true,"title":"Get risk score"}Changed the definition of "verify_wallet"
⟨23 unchanged words⟩ risk rules with up to 3 advice items. On Base, also reports any ERC-8004 agent the wallet owns and its open on-chain reputation as descriptive signals, never scored. Free ($0). Returns risk_score, risk_level, sanctions ⟨22 unchanged words⟩ you checked that were linked to this wallet). On Base, also erc8004_agent_ids and erc8004_reputation (open ERC-8004 feedback, descriptive only -- never folded into risk_score or advice). Accepts EVM (0x...) and Solana ( ⟨23 unchanged words⟩
Recently observed → Live
Removed "check_agent" and "get_trust_score"; changed the definition of "verify_wallet" (5 tools before, 3 now)
UnimplementedScreen/abetawallet:returnsOFACplaceholderSDNdataaddress match,noton-chainasignalsreal(contractresult.check,
Live → Recently observed
Recently observed → Live
Live → Recently observed
Certificate recorded, valid to 2026-12-09
Authorization not required
First tool surface recorded: 5 tools (server version 1.30.0)
Showing the latest 25 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
⟨44 unchanged words⟩ on-chain reputation as descriptive signals, never scored.$0.11.$0.005 by x402, $0.11 with an API key. Returns risk_score, risk_level, sanctions (hit, lists ⟨90 unchanged words⟩
⟨32 unchanged words⟩ the full wallet screen (the verify_wallet tool, $0.005 by x402, $0.11 with an API key: balances, wallet age and activity, contract ⟨66 unchanged words⟩
Free yes/no check of a wallet address against the OFAC SDN list. Returns wallet_address (canonical), chain_id, sanctioned, lists, as_of (the list's publication date), status (ok or stale), source and upgrade, which names the full wallet screen (the verify_wallet tool, $0.11: balances, wallet age and activity, contract and delegation checks, a risk score with rules and advice, linked entities, ERC-8004 identity and reputation). 10 per caller per UTC day, shared with POST /v1/sanctions/wallet and separate from …
{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":true,"title":"Get risk score"}
{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":true,"title":"Sanctions screen"}
{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":true,"title":" ⟨4 unchanged words⟩
⟨18 unchanged words⟩ Use when you only need basic risk evaluation. Returns risk_score (0-100, 100 = riskiest), risk_level (high means high risk, the reverse of check_entity's trust_level), sanctions_match and fatf_status; no recommendation or factors. Args: entity_name: Full legal name of the ⟨7 unchanged words⟩
Quick riskassessmentscorewithoutfromfullsanctionstrustscreeningcheck.and country risk only. Fasterendpointthanthatcheck_entity:focusesnoonregisterriskorsignalsdomainonly.lookup. Use when you only need basic risk evaluation. ⟨14 unchanged words⟩
Sanctions screen against the local OFAC SDN, EU and UN lists: matched entries. Each match carries its list, entry id, entry type, programmes, countries, listing date and match score (exact normalised or word-order-insensitive name match only). A name match is not a determination. Rejected calls are not charged. Args: name: Company or person name to screen country: Optional ISO 3166-1 alpha-2 country code (orders matches, never excludes one)
⟨8 unchanged words⟩ ":null,"title":"Agent Id"},"domain":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Domain"},"wallet":{"title":"Wallet","type": ⟨7 unchanged words⟩
⟨142 unchanged words⟩ , bank, BIC and last 4 are returned phone: Phone number the lead gave; compared with the numbers the company publishes, never echoed. Rejected until website phone lookup is switched on
⟨65 unchanged words⟩ "default":null,"title":"Name"},"phone":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"title":"Phone"},"vat_number":{"anyOf":[{"type":"string ⟨13 unchanged words⟩
Look up your own most recent trust score for an entity you checked before, from your stored checks: score, level, when, which product, trend and how many checks are on record. Runs no new check and calls no data source. Free ($0). Returns status "found" with trust_score, trust_level, checked_at, source_product, trend and checks_on_record, or status "not_found" with a next_step. Only checks made with your key (via check_entity, or REST entity/KYB checks) are read; another key's or workspace's never are (#946). Args: entity_id: The entity na…
Verify a NL/BE sales lead against the registers in one call: real and active, VAT, mail server, IBAN, sanctions; a 0-100 lead score. $0.24. Returns verdict (real_active, real_inactive, not_found, ambiguous, unverifiable or sanctioned), lead_score, the company as registered, and the vat, iban, sanctions and email checks, with flags and one finding per flag. An input not given is not checked and never counts against the lead. The IBAN account holder is not checked. BE needs company_number. Rejected calls are not charged. …
before
—after
{"destructiveHint":false,"openWorldHint":true,"readOnlyHint":true,"title":"Screen wallet"}Unimplemented / beta: returns placeholder data, not a real result. Free ($0) until real logic ships. Verify AI agent trust via LimitGuard. Today every call returns verified=false, trust_score=0 and status="unimplemented" regardless of input (#206). Intended for multi-agent systems to verify delegation targets. Args: agent_id: Unique agent identifier agent_name: Human-readable agent name
Unimplemented / beta: returns placeholder data, not a real result. Free ($0) until real logic ships. Quick trust score lookup by entity ID. Today every call returns trust_score=0 and trust_level="unknown" regardless of input (#206). Args: entity_id: Entity identifier (KVK number, domain, or hash)