Remote MCP · Endpoint

AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks MCP server

No. AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks answered an MCP handshake 1 hour ago.

UpLast checked 1 hour ago

Server URL

https://getagenttrust.com/api/mcp/public

The last check completed an MCP handshake.

Registry name
io.github.agenttrust-ai/agenttrust
Transport
Streamable HTTP
Protocol negotiated
2025-06-18
Handshake latency
361 ms
Tools exposed
2 tools
Uptime, last 30 days
92.9% from 14 checks
Described by its publisher as
Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.
Listing
From the official MCP registry (active).
Recent checks of AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks
CheckedResultHandshake
1 hour agoHandshake completed361 ms
2 days agoHandshake completed374 ms
5 days agoHandshake completed340 ms
7 days agoHandshake completed274 ms
9 days agoHandshake completed311 ms
11 days agoHandshake completed300 ms
13 days agoHandshake completed277 ms
15 days agoHandshake completed324 ms
17 days agoFailed - the server returned an HTTP error—
18 days agoHandshake completed271 ms
20 days agoHandshake completed281 ms
21 days agoHandshake completed274 ms
23 days agoHandshake completed272 ms
25 days agoHandshake completed270 ms

The last 14 checks. Full history is kept for 30 days; the all-time counter stands at 13 responding of 14.

How to read this

  • ·Handshake latency is one measurement from one probe, from our infrastructure. It is a smoke signal about the endpoint, not a benchmark of your own connection to it.
  • ·An authentication challenge counts as responding. A hosted server that refuses an anonymous prober is behaving correctly.
  • ·A tool count of “behind credentials” means the handshake worked but listing tools needed a token we do not hold.
  • ·Uptime covers the last 30 days of our own checks, at most one an hour, and says how many checks it is drawn from.

Listing data comes from the official MCP registry. Glide is not affiliated with AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks and makes no claim about it beyond what these checks measured.