83trust / 100
agent-lint
by runningunattended.com in AI models & inference
MCP serverPassing, checked 3 h ago
Checks CLAUDE.md, AGENTS.md or a system prompt for 12 safeguards unattended agents need.
https://runningunattended.com/api/mcp
Last 30 days
All checks passedSome failedAll failedNot checked
- Uptime
- 100%
- Response time
- 282 ms typical, 282 ms slowest 5%
- Last check
- 3 h ago
- Next check
- in 3 h
How to call it
Add it to any MCP client that supports remote servers.
{
"mcpServers": {
"agent-lint": {
"type": "http",
"url": "https://runningunattended.com/api/mcp"
}
}
}1 tools
- lint_rules_file
Check an agent rules file (CLAUDE.md, AGENTS.md, system prompt) for 12 safeguards an unattended agent needs (kill switch, spending limit, untrusted-input rule, secrets, memory, audit...). Keyword checks: they report what is written down, not what is enforced. Also flags live-look
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 |
|---|---|---|---|
| 3 h ago | Passed | 200 | 282 ms |
| 13 h ago | Passed | 200 | 271 ms |
| 21 h ago | Passed | 200 | 748 ms |