Limitguard
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LIMITGUARD_API_KEY | Yes | Your Limitguard API key, sent as the X-API-Key header on every REST call the tools make. Get a free key with POST https://api.limitguard.ai/v1/keys/create and add prepaid credit for the paid tools. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_entityA | Company check on a business: sanctions screening and country risk, the Dutch KVK register for an NL company, and the website domain when you send it. Returns trust_score (0-100, 100 = best), trust_level (high means low risk), cluster, recommendation, confidence, top_factors and sources_checked. |
| get_trust_scoreA | 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). |
| verify_walletA | Screen a wallet: OFAC SDN address match, on-chain signals (contract check, native and USDC balance, transaction count, first seen on Base) and named 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. $0.11. Supports EVM and Solana addresses. |
| get_risk_scoreA | Quick risk score from sanctions screening and country risk only, without the register or domain lookups of check_entity. 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. |
| get_compliance_reportB | Per-entity report built from one real check: registry identity, sanctions and PEP screens, domain signals, risk score with the rules that fired, correlations, every finding as a ranked action, a per-source status table (ok / unavailable / error) and a report hash. |
| sanctions_previewA | Free yes/no sanctions preview against the local OFAC SDN, EU and UN lists. Returns possible_match, lists_checked, list_dates and list_note only, never an entry. 10 per caller per UTC day. |
| wallet_sanctions_previewA | Free yes/no check of a wallet address against the OFAC SDN list: sanctioned, lists, the list date and its freshness, no programmes or entry ids. 10 per caller per UTC day, separate from sanctions_preview. The full wallet screen is verify_wallet ($0.11). |
| sanctions_screenA | Sanctions screen against the local OFAC SDN, EU and UN lists: matched entries with list, entry id, programmes, countries, listing date and match score. A name match is not a determination. |
| check_agent_walletA | 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. |
| verify_leadA | 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. $0.27. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
The set has several clusters of overlapping tools: check_entity vs get_risk_score vs get_compliance_report vs get_trust_score all serve entity risk, and verify_wallet vs wallet_sanctions_preview vs check_agent_wallet all screen wallets, with sanctions_preview/sanctions_screen/wallet_sanctions_preview forming a third cluster. The descriptions do a good job cross-referencing depth and pricing to differentiate them, but the semantic inversion between check_entity's trust_level (high=low risk) and get_risk_score's risk_level (high=high risk) is a genuine misselection trap.
Most names follow a verb_noun pattern (check_entity, get_trust_score, verify_wallet, get_compliance_report, verify_lead). Verb choice varies across synonyms (check_ vs get_ vs verify_) and the three sanctions_* tools drop the verb entirely, which is a minor deviation rather than a break in convention.
Ten tools is well-scoped for a screening service, and each tool occupies a distinct niche defined by target (entity/wallet/agent/lead), depth (preview/full/report) and cost. Nothing feels like filler or a duplicate entry.
The surface covers entity checks, quick risk scoring, full sanctions screening, wallets, agent wallets, compliance reporting, stored-score retrieval and lead verification—broad lifecycle coverage for a risk-screening domain. Gaps like ongoing monitoring, PEP-only screens or bulk/batch checks exist but are minor workarounds.