io.github.iabdullahm/rafid-agent-api

Tools

• analyze_company_risk

  Gather evidence-tiered risk signals for a company across corporate identity, domain, website, sanctions-list name-matching, adverse news, reputation and legal/regulatory signals — never a safe/unsafe verdict. Use when an agent needs risk evidence to weigh before a transaction, partnership, or onboarding decision — not a substitute for compliance/legal sign-off.

  shallow
• analyze_oman_company

  Generate deterministic commercial-intelligence signals, risk flags and positive signals for one Oman company by companyId, for a stated evaluation purpose. Use when an agent needs to assess whether an Oman company looks like a serious, established operating business — as a supplier, customer, partner or investment target.

  shallow
• analyze_oman_property

  Analyze an Oman residential property using local rental comparables, market context and investment metrics. Use when an agent needs Oman-specific rental, yield, price-position or operating-cost analysis.

  shallow
• analyze_property

  Calculate gross/net rental yield, income, operating costs and simple payback in OMR. Calculations only. Use when an agent needs financial metrics (yield, income, payback) for a single property.

  shallow
• business_risk_score

  Assess the risk of doing business with a company in any country using corporate, financial, compliance, reputation, operational and digital evidence. Returns a 0–100 risk score (100 = highest detected risk), a separate 0–1 confidence, per-category component scores, evidence-backed risk flags and positive signals, sanctions/restricted-party screening with match strength, and machine-readable due-diligence guidance (proceed / proceed_with_monitoring / enhanced_due_diligence / manual_review / avoid_automated_transaction). Use before onboarding a supplier or vendor, paying a new business, entering a B2B transaction, approving a marketplace seller, extending credit or insurance, or recommending a company — whenever an autonomous agent needs structured, evidence-backed business due diligence it cannot reliably generate from its own model knowledge.

  shallow
• company_reputation_check

  Investigate the public reputation and commercial risk signals of a company in any country — identity consistency against official registries, sanctions-list name screening, adverse media (with legal stage: allegation vs. outcome), customer reputation, online presence, business stability and domain signals — returning evidence-linked scores with a separate confidence score. Use this capability when an AI agent needs to assess a company's public reputation, credibility, adverse-media exposure, sanctions signals, customer reputation, online presence, identity consistency and other publicly observable commercial risk indicators before entering a business relationship.

  shallow
• compare_properties

  Compare 2–20 uniquely named properties in OMR using the same metrics; order by rounded net yield, preserving input order for ties. Use when an agent must rank or choose between 2-20 candidate properties by net yield.

  shallow
• document_facts_extract

  Extract structured, evidence-backed facts, entities, dates, amounts, obligations, deadlines and risk indicators from business documents (contracts, invoices, purchase orders, quotations, tenders/RFPs, leases, policies, financial reports, legal documents, CVs, company profiles) from any country. Every fact carries a 0–1 extraction confidence and source evidence (verbatim excerpt, character offsets, section, and the page when the document has real pages); dates, amounts, currencies, percentages and durations are normalized only when unambiguous. Accepts an https documentUrl (PDF with a text layer, DOCX, HTML, text) or extracted text, up to 25 pages. Use when an agent needs reliable machine-readable facts from a contract, invoice, tender, lease, purchase order, policy, financial report or other business document instead of a general summary.

  shallow
• due_diligence_oman_company

  Perform structured commercial due diligence on one Oman company by companyId ahead of a stated transaction, returning identity verification, risk assessment, a prioritized due-diligence checklist and known information gaps. Use before awarding a contract, entering a partnership, extending credit or investing, when a structured, source-backed due-diligence pass is needed ahead of the decision.

  shallow
• estimate_maintenance

  Estimate an annual maintenance reserve in OMR from value, age and unit count with explicit optional assumptions. Uncalibrated heuristic, not a survey. Use when an agent needs an annual maintenance reserve estimate for a property, not an actual inspection.

  shallow
• find_companies

  Discover companies from public web sources matching an industry, location, size and/or keyword criteria, returning cited candidate companies (never fabricated) with a stated confidence score. Use when an agent needs to discover a list of candidate companies matching criteria (industry, location, size, keywords) rather than analyze one already-known company.

  shallow
• get_oman_company_profile

  Return a structured profile for one Oman company by companyId — identity, registration, location and contact fields, digital-presence detection and full source provenance. Use after search_oman_company resolves a companyId, to retrieve the company's structured profile before deciding whether deeper analysis or due diligence is warranted.

  shallow
• invoice_anomaly_check

  Detect duplicate, inconsistent, unusual or potentially fraudulent invoices before payment using arithmetic, supplier-history, purchase-order and payment-detail checks. Returns a 0–100 risk score, a risk level, an advisory decision (continue / review / hold) and machine-readable anomalies (e.g. DUPLICATE_INVOICE, POSSIBLE_DUPLICATE, BANK_ACCOUNT_CHANGED, PO_AMOUNT_EXCEEDED, SPLIT_INVOICE_PATTERN, SUBTOTAL_MISMATCH), each with severity, confidence and structured evidence. Works on a single invoice (standalone) or with optional historical invoices, supplier profile, purchase order, contract, approval threshold and payment history (context-aware). Deterministic, decimal-safe, any country and currency. Use before approving, paying, booking, reconciling or auditing an invoice, especially when an agent needs to determine whether the invoice requires human review.

  shallow
• oman_supplier_check

  Screen an Oman supplier for procurement using company identity, business activity, website, contact consistency, address signals, public-risk indicators and sanctions screening. Use before adding an Oman supplier to an RFQ, vendor shortlist, procurement process or supplier onboarding workflow.

  shallow
• preview_capability

  Free preview of a paid capability: checks whether useful data/analysis is available for a given input, before paying — proof of "I have information for this request," never the paid analysis itself. No payment, charge or account is ever involved. Not every capability supports preview (status is "unavailable" when it doesn't). Recommended flow: discover -> preview -> evaluate -> pay -> execute.

  shallow
• research_company

  Research a company from public web sources: overview, products, leadership, funding, competitors, technology signals, recent developments and risk flags, with cited sources and a confidence score. Use when an agent needs a structured research brief on a named company — for sales/investment/partnership research, competitive analysis, or general company background — beyond what a structured company registry alone provides.

  shallow
• search_oman_company

  Search structured Oman business records by name, registration number, governorate, wilayat and/or industry, returning candidate companies ranked by deterministic identity-match confidence. Use before company analysis or due diligence when the exact company identity is uncertain, or to find candidate Oman companies matching a name or registration number.

  shallow

Embed this server’s score

Tool count and median score across every tool in this server’s corpus — honest in a way a single cherry-picked tool’s badge wouldn’t be.

[![Vouch score](https://vouch.tools/api/servers/4894fa39-39bb-448c-b0c9-97b840113fe0/badge.svg)](https://vouch.tools/servers/4894fa39-39bb-448c-b0c9-97b840113fe0)