Tethered Trust is answering right now. Last checked 11 min ago. It exposes 18 tools.
Compatibility checks for AI agents before they buy or install: verdicts, evidence, receipts.
Today is the operative word: we check Tethered Trust every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.
claude mcp add tethered-trust --transport http https://tetheredtrust.com/mcp
https://tetheredtrust.com/mcp
[mcp_servers.tethered-trust]
url = "https://tetheredtrust.com/mcp"
{
"mcpServers": {
"tethered-trust": {
"url": "https://tetheredtrust.com/mcp"
}
}
}
{
"servers": {
"tethered-trust": {
"type": "http",
"url": "https://tetheredtrust.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
identify_from_photo
identify_product
check_batch
check_cart_before_checkout
check_compatibility
list_coverage
enrich_catalog
check_fit
fix_purchase_plan
how_it_works
find_parts
plan_upgrade
recheck_plan
report_outcome
resolve_product
list_standards
validate_purchase_plan
verify_receipt
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://tetheredtrust.com/mcp | streamable-http | answering | 232 ms | 11 min ago |
Evidence-first trust verdicts for AI-agent services — query one before you transact.
Free public benchmark for AI agents: compliance tasks, every claim checked against signed receipts
Fact-check receipts: search published claim verdicts with cited evidence, or verify a new claim.
MCP security trust-check for agents before installing MCPs, Skills or tools.
MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.
Check the trust/security score of MCP servers, agents, skills & CLIs before you install them.
Consequence evaluation for AI agents. Check recoverability before destructive actions.
Reversibility intelligence and durable exit evidence for AI agents before real-world commitments.
Answers built from our own checks of this server.