legion-ai-intelligence
# Legion AI Intelligence — MCP Server
Connect AI agents to real-time AI ecosystem intelligence.
## Tools
| Tool | Description |
|------|-------------|
| get_ai_incidents | 1,178+ classified AI security incidents |
| get_ai_model_pricing | 28 models, 7 providers |
| get_gpu_pricing | GPU cloud pricing from 7 providers |
| get_ai_route | Smart model routing (cost/speed/reliability) |
| get_ai_status | Live provider availability |
| get_company_intelligence | Cross-signal company analysis |
| scan_n8n | n8n CVE-2026-21858 scanner |
## Setup
Add to claude_desktop_config.json:
{
"mcpServers": {
"legion-ai": {
"command": "python3",
"args": ["path/to/server.py"]
}
}
}
## Links
- API: https://api.legion-api.com
- RapidAPI: https://rapidapi.com/gemmozero/api/legion-ai-security-incidents
- Datasets: https://huggingface.co/gemmozero
- Site: https://legion-api.com
## Cursor / Claude Code / Windsurf
```json
{ "mcpServers": { "legion-ai": { "command": "uvx", "args": ["--from", "git+https://github.com/Legion33shadow/legion-mcp", "legion-mcp"] } } }
```
No API key required. Free tier: 10 results per call. Full access: https://gemmo.gumroad.com/l/ngtmw
TDQS
Scored across 11 tools
Most tools target clearly distinct signals: pricing, status, drift, jobs, regulations, incidents, and routing. The only mild overlap is get_incident_stats (aggregate counts) vs get_ai_incidents (searchable records), but the descriptions clearly separate counting from searching. get_company_intelligence is a synthesis tool and doesn't collide with the atomic tools.
Ten of eleven tools follow a clean get_* snake_case pattern (get_ai_model_pricing, get_gpu_pricing, get_ai_route, etc.). scan_n8n breaks the get_ prefix convention, but it is an action verb appropriate to a scan operation, so the deviation is minor and readable.
Eleven tools is well-scoped for an AI-ecosystem intelligence server, with each tool covering a distinct signal source (pricing, status, drift, incidents, jobs, regulations, routing, vulnerability scanning). No obvious filler or redundancy.
The surface covers a broad range of intelligence signals plus a cross-signal aggregator (get_company_intelligence) and a routing recommender, giving good lifecycle coverage. Minor gaps exist, such as no historical/trend query for pricing or status, but core workflows are covered.