MCP server + CLI for accessing World Monitor intelligence data. Provides 112 tools across 33 services covering military, financial, geopolitical, cyber, infrastructure, environmental, direct-API financial intelligence, and composite trading-intelligence sources.
Only 1 tool visible in source code (get_insider_activity). Package.json claims 112 tools across 33 services, but actual tool definitions are not present in provided source. The single visible tool has a strong description (145 chars, well-structured) and complete input schema with proper types and descriptions. However, the vast majority of claimed tools cannot be evaluated, they appear to be proxied through WorldMonitorClient or defined in service registries without explicit schema visibility. With only 1 evaluable tool scoring ~65 and 111+ tools capped at 0 (not visible), the average is heavily penalized.
Real insider-activity signal — parses SEC Form 4 XML for actual open-market buys vs sells (the submissions index only says a Form 4 was filed, which is noise since sells/grants/exercises vastly outnumber open-market buys).
111+ tools claimed but not visible in source code. Package.json states '112 tools across 33 services' but actual tool definitions are not provided. Tools appear to be registered via service registries (services/index.ts) and proxied handlers (handlers/index.ts) without explicit schema definitions visible in the provided source.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 57 | 2026-07-28+ | v2 |
No input schemas visible for 111+ tools. Service definitions reference tools but do not expose their input/output schemas in the provided source.
No tool descriptions visible for 111+ tools. Service registries list tool names and endpoints but descriptions are not provided in the source code excerpt.
No output schemas documented. The single visible tool (get_insider_activity) has no documented return type or structure. LLMs cannot plan downstream calls or extract data without knowing what fields to expect.
No error handling guidance visible. Tools do not document what errors can occur, whether they are retryable, or what the LLM should do next. Per pattern:recovery-guide, error responses must tell the LLM what to do.