Agent Beacon is answering right now. Last checked 4 min ago. It exposes 3 tools.
Report capabilities needed and not found. Requests aren't fulfilled.
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.
claude mcp add agent-beacon --transport http https://beacon.sophomath.com/mcp
https://beacon.sophomath.com/mcp
[mcp_servers.agent-beacon]
url = "https://beacon.sophomath.com/mcp"
{
"mcpServers": {
"agent-beacon": {
"url": "https://beacon.sophomath.com/mcp"
}
}
}
{
"servers": {
"agent-beacon": {
"type": "http",
"url": "https://beacon.sophomath.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
describe_beacon
check_request_status
submit_capability_request
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://beacon.sophomath.com/mcp | streamable-http | answering | 450 ms | 4 min ago |
Time Tracker Ai tools for AI agents. Capabilities: start timer, stop timer, get report. Built by
When the agent writes a bad import, the write doesn’t land. The same check fails the pull request.
Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.
Bug reports your coding agent can fix: real element, console errors, failing requests with bodies.
Downdetector for AI agents: stop paying for retries that can't succeed. Check once, then report.
Search agent-ready sites or fetch one site's report; every capability probe-verified, dated.
Hosted coding agent: start, follow up on and stop tasks that can open GitHub pull requests.
Autopilot MCP server for GEO analyses, reports, content, audits, memories and agents.
Answers built from our own checks of this server.