MCP server health, State of MCP census
Shadow AI List
ca.airiskmanagement/shadow-ai-list
Risk-ranked registry of AI tools: look up an AI tool's risk or check if a domain is shadow AI.
Checks
The exact rows akashi check ca.airiskmanagement/shadow-ai-list prints, from the 2026-07-02 census.
| Check | Status | Detail |
|---|---|---|
| registry status | pass | active |
| server.json valid | pass | validates against its declared JSON Schema |
| repo reachable | skip | no repository declared |
| remote reachable | pass | HTTP 200 via initialize |
| MCP conformance | pass | initialize handshake ok |
| tools/list | pass | 4 tools: lookup_ai_tool_risk, check_domain_against_registry, list_shadow_ai, get_top_risky_ai |
| at least one live entrypoint | pass | 1 alive |
Evidence
Repository
No repository declared.
Packages
No packages declared.
Remote endpoints
- https://ailist.airiskmanagement.ca/mcp
streamable-http · reachable· HTTP 200· initialize_ok
4 tools: lookup_ai_tool_risk, check_domain_against_registry, list_shadow_ai, get_top_risky_ai
server.json
validagainst its declared schema
One of 14559 servers in the 2026-07-02 State of MCP census: 11582 healthy (79.6%), 2212 degraded (15.2%), 596 dead (4.1%), 169 unknown (1.2%).
Verify it yourself
This page is a static read of one dated probe. Run the same check locally, any time, with no key:
$ akashi check ca.airiskmanagement/shadow-ai-listInstall Akashi - single Go binary, zero keys, MIT licensed.
Is this your server?
Claiming a server (an auto-refreshing badge and a verified publisher profile) is coming soon. Until then, embed the verified-on-date badge yourself with akashi check ca.airiskmanagement/shadow-ai-list --badge.
Open data, CC BY 4.0. How this census works - denominator, tiers, and what each check does.