Eclipse Trust MCP is answering right now. Last checked 1 min ago. It exposes 5 tools.
Is this bench result real? Who issued it, at what scope, anchored where? One call answers.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.
claude mcp add trust --transport http https://cetech.ai/trust/mcp
https://cetech.ai/trust/mcp
[mcp_servers.trust]
url = "https://cetech.ai/trust/mcp"
{
"mcpServers": {
"trust": {
"url": "https://cetech.ai/trust/mcp"
}
}
}
{
"servers": {
"trust": {
"type": "http",
"url": "https://cetech.ai/trust/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
trust_get_bench_verdict
trust_get_validation_record
trust_resolve_agent
trust_status
trust_verify_receipt
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://cetech.ai/trust/mcp | streamable-http | answering | 800 ms | 1 min ago |
Who calls this, what breaks, which callers an edit missed: labelled answers. Windows, Python, TS/JS.
A second opinion, in one call, from a desk where an answer is allowed to be no.
Is this transaction safe to sign? Decodes what it really does and answers allow, warn or block.
The trust harness for AI agents. Set what an agent can do before it acts.
MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.
Reads what was agreed and answers whether a new request is Included, citing only confirmed lines.
Ask your AI what breaks before you change Salesforce. Offline, read-only, cited answers.
Is there a materially better time for this call, stream or upload, given where everyone is?
Answers built from our own checks of this server.