Rafid Intelligence Network
io.github.iabdullahm/rafid-agent-api · v0.1.5 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Paid intelligence tools for AI agents across risk, finance, property, logistics and more.
Source: https://github.com/iabdullahm/rafid-agent-api
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 81 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (sandbox_code_execute). Require confirmation before the agent calls them. |
What was checked
- https://api.rafidsystem.com/mcp?utm_source=…&utm_medium=…&utm_campaign=…&distribution_experiment_id=…: answers without auth
Public tools: analyze_wifi, company_due_diligence, company_risk_batch, oman_vendor_finder, due_diligence_oman_company, company_risk_report, analyze_oman_company, business_risk_score, company_reputation_check, multi_source_search, get_oman_company_profile, research_company, find_companies, search_oman_company, analyze_company_risk, procurement_vendor_shortlist, supplier_due_diligence_report, oman_supplier_check, invoice_anomaly_check, unlimited_ocr_image, document_facts_extract, sandbox_code_execute, website_audit, website_download, website_project_estimate, zyte_web_extract, web_extract, property_investment_report, portfolio_screen, analyze_oman_property
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-iabdullahm-rafid-agent-api-cce69c43)