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

by agenttrust-ai Your server? Claim it

not responding

AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks is listed as active in the registry but did not answer our last check. It exposes 6 tools. Last commit 31 Oct 2026.

Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.

Uptime history 51 days of history · worst day 7%

51 days agonow

9.4%

Uptime 24h

26 of 276 checks

Tools

read from the server

305 ms

Response time

average over 24h

Stars

last commit 31 Oct 2026

What changed 79

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 21 September 2026. No other catalogue keeps this.

7 Nov 4 tools appeared get_agent, get_agent_health, list_agents and 1 more

7 Nov 4 tools disappeared get_agent, get_agent_health, list_agents and 1 more

7 Nov 2 tool descriptions were rewritten assess_agent, check_agent_trust

30 Oct 4 tools appeared get_agent, get_agent_health, list_agents and 1 more

29 Oct 4 tools disappeared get_agent, get_agent_health, list_agents and 1 more

29 Oct 2 tool descriptions were rewritten assess_agent, check_agent_trust

25 Oct a tool appeared assess_agent

22 Oct 4 tools appeared get_agent, get_agent_health, list_agents and 1 more

22 Oct 4 tools disappeared get_agent, get_agent_health, list_agents and 1 more

22 Oct a tool description was rewritten check_agent_trust

and 49 more, back to 21 September 2026

AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks does not always answer

Over the last week it answered 22.9% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agenttrust --transport http https://agenttrust-umber.vercel.app/api/mcp

Settings → Connectors → Add custom connector, then paste this address

https://agenttrust-umber.vercel.app/api/mcp

~/.codex/config.toml

[mcp_servers.agenttrust]
url = "https://agenttrust-umber.vercel.app/api/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "agenttrust": {
      "url": "https://agenttrust-umber.vercel.app/api/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agenttrust": {
      "type": "http",
      "url": "https://agenttrust-umber.vercel.app/api/mcp"
    }
  }
}

This server publishes 2 more addresses. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

agent

check_agent_trust

Pre-invocation trust check for an unknown AI agent or MCP server endpoint. Read-only, requires no AgentTrust API key or account. Looks up an agent by its exact invocation URL among AgentTrust's already-observed public agents and returns its status, endpoint-ownership verification, agent reliability score (when available), and a machine-readable trustDecision (recommended, confidence, reasons). Does NOT contact endpointUrl itself during this check — it only reads AgentTrust's own existing monitoring history. An unregistered URL returns { matched: false }, never an error.

get_agent

Get one AgentTrust agent's public profile by slug, including its structured Agent Card, current reliability score, and a machine-readable trustDecision (recommended, confidence, reasons) for deciding whether to invoke it.

get_agent_health

Get one agent's current effective health status and monitoring detail — derived from heartbeat freshness for push-mode agents, or the latest pull check otherwise.

agents

list_agents

Discover AgentTrust agents. Pass `endpointUrl` to check the trust status of a specific external agent by its exact invocation URL before deciding whether to invoke it — the response includes a reliability score, endpoint-ownership verification status, and a machine-readable trustDecision (recommended, confidence, reasons). Without `endpointUrl`, returns the plain paginated listing of public agents, newest first. Requires an API key; for an anonymous pre-invocation check use check_agent_trust.

assess

assess_agent

Immediate use-or-avoid decision about an AI agent or MCP server endpoint, for an agent deciding whether to call it. Returns decision (allow_with_caution, avoid, or insufficient_evidence), confidence, reasonCodes, reachability (the latest stored observation, with its age), initialRisk, the historical reliability score and trustDecision (unchanged), limitations, and freshness. Built only from AgentTrust's stored observations: it never contacts endpointUrl. Reachability is not safety: allow_with_caution never means the agent's behavior is safe. Requires no API key.

send

send_heartbeat

Record a push-style heartbeat for an agent you own, marking it alive right now. The server sets the timestamp; no client-supplied time is accepted.

Endpoints

URL	Transport	State	Latency	Checked
https://agenttrust-umber.vercel.app/api/mcp	streamable-http	answering	44 ms	0 min ago
https://getagenttrust.com/api/mcp	streamable-http	answering	40 ms	0 min ago
https://getagenttrust.com/api/mcp/public	streamable-http	answering	38 ms	0 min ago

Alternatives to AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks

same job, measured the same way

Hosannaith MCP

by cameron4316

Check x402 endpoint reliability on Algorand before an agent routes a payment there.

244 installs/wk local only

Mizan

by higgsfield-mizan-bazar

Check an x402 endpoint before your agent pays it: avoid / caution / ok, proven on-chain.

3 tools answering

Endpoint Diligence

by x402supply

Live x402 endpoint trust/diligence check before you pay it. $0.02/call via x402.

3 tools answering

Lumière PayCheck

by book0feli

Check any x402 endpoint before your AI agent pays it: trust grade, verdict, and hijack checks.

632 installs/wk 9 tools answering

Pulsefeed X402

by nikolife2016

Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.

79 installs/wk 11 tools answering

X402score MCP

by zagchk

Check an x402-paid API endpoint's trust score before paying it - live-probed, not self-reported.

56 installs/wk local only

gutsy

by kouhxp

Local gut check before risky agent actions: calibrated safe/intended probabilities, no API calls.

178 installs/wk local only

Citable

by zaialamm

SEO and AI-visibility checks agents buy per call — USDC on Solana, no API key.

111 installs/wk local only

AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks — questions

Answers built from our own checks of this server.

What can AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks do?

It exposes 6 tools, read directly from the server on our last check. Among them: assess_agent, check_agent_trust, get_agent, get_agent_health, list_agents, send_heartbeat. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 26 of 276 checks got a reply (9.4%), average response time 305 ms. The bar chart above shows every period we have measured.

The registry lists AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks as active — why does it not respond?

The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.

How do I connect AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks need an API key?

No. AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks?

It answers our handshake in 305 ms on average, which is faster than 45% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks open source?

The code is open source: it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at agenttrust-umber.vercel.app, which runs on its operator's own terms.