90trust / 100
Boundaryai
by boundaryai.ai in Security & trust
MCP serverPassing, checked 1 h ago
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
https://mcp.boundaryai.ai/mcp
Last 30 days
All checks passedSome failedAll failedNot checked
- Uptime
- 100%
- Response time
- 217 ms typical, 217 ms slowest 5%
- Last check
- 1 h ago
- Next check
- in 5 h
How to call it
Add it to any MCP client that supports remote servers. It asks for sign-in or an API key.
{
"mcpServers": {
"boundaryai": {
"type": "http",
"url": "https://mcp.boundaryai.ai/mcp"
}
}
}The tool list is behind sign-in, so we can't show it.
Security scan
- No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time |
|---|---|---|---|
| 1 h ago | Passed | 401 | 217 ms |