Fresh is answering right now. Last checked 5 min ago. It exposes 2 tools.
Know whether an AI agent should REUSE or REFETCH a URL before retrieving it again.
Nothing serious here today
Today is the operative word: we check Fresh every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 5 min ago.
claude mcp add fresh --transport http https://fresh-api-production-c783.up.railway.app/mcp{
"mcpServers": {
"fresh": {
"url": "https://fresh-api-production-c783.up.railway.app/mcp"
}
}
}[mcp_servers.fresh]
url = "https://fresh-api-production-c783.up.railway.app/mcp"{
"mcpServers": {
"fresh": {
"url": "https://fresh-api-production-c783.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"fresh": {
"url": "https://fresh-api-production-c783.up.railway.app/mcp"
}
}
}Available tools 2
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
fresh_check
fresh_observe
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://fresh-api-production-c783.up.railway.app/mcp | streamable-http | answering | 394 ms | 5 min ago |
Alternatives to Fresh
same job, measured the same wayAn AI agent's safe read-only scout to orient in an unknown repository before touching it.
Check whether a real-world fact can be verified before an agent acts on it. Free, no auth.
Prior art for AI agents. Ask a claim index before retrying a known failure.
Resolve whether an uncertain side-effecting action completed before software retries it.
Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
What every agent should know
The trust harness for AI agents. Set what an agent can do before it acts.
Fresh — questions
Answers built from our own checks of this server.