Connect AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks and your agent gets 2 tools, among them assess_agent, check_agent_trust. It answers at https://getagenttrust.com/api/mcp/public over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 23 September 2026; the last check, on 6 November 2026, succeeded.
Trust infrastructure for AI agents: check reliability, verification, and trustDecision by URL.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
assess_agent | Use-or-avoid decision about an AI agent or MCP server endpoint, built from AgentTrust's stored observations of its exact URL. Returns decision (allow_with_caution, avoid, or insufficient_evidence), confidence, reasonCodes, reachability (the Inputs: endpointUrl |
check_agent_trust | Pre-invocation trust check for an unknown AI agent or MCP server endpoint. Pass the exact URL you are about to call as endpointUrl to get what AgentTrust has observed about it: status, endpoint-ownership verification, reliability score (whe Inputs: endpointUrl |
Every block below points at https://getagenttrust.com/api/mcp/public. Pick your client and copy.
claude mcp add --transport http agenttrust-pre-invocation-ai-age https://getagenttrust.com/api/mcp/public
{
"mcpServers": {
"agenttrust-pre-invocation-ai-age": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://getagenttrust.com/api/mcp/public"]
}
}
}{
"mcpServers": {
"agenttrust-pre-invocation-ai-age": {
"url": "https://getagenttrust.com/api/mcp/public"
}
}
}{
"servers": {
"agenttrust-pre-invocation-ai-age": {
"type": "http",
"url": "https://getagenttrust.com/api/mcp/public"
}
}
}{
"context_servers": {
"agenttrust-pre-invocation-ai-age": {
"url": "https://getagenttrust.com/api/mcp/public"
}
}
}{
"mcpServers": {
"agenttrust-pre-invocation-ai-age": {
"serverUrl": "https://getagenttrust.com/api/mcp/public"
}
}
}{
"mcpServers": {
"agenttrust-pre-invocation-ai-age": {
"url": "https://getagenttrust.com/api/mcp/public"
}
}
}name: AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks
version: 0.0.1
schema: v1
mcpServers:
- name: AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks
type: streamable-http
url: https://getagenttrust.com/api/mcp/public{
"mcpServers": {
"agenttrust-pre-invocation-ai-age": {
"httpUrl": "https://getagenttrust.com/api/mcp/public"
}
}
}{
"mcpServers": {
"agenttrust-pre-invocation-ai-age": {
"type": "http",
"url": "https://getagenttrust.com/api/mcp/public"
}
}
}{
"mcpServers": {
"agenttrust-pre-invocation-ai-age": {
"url": "https://getagenttrust.com/api/mcp/public"
}
}
}goose://extension?url=https%3A%2F%2Fgetagenttrust.com%2Fapi%2Fmcp%2Fpublic&type=streamable_http&id=agenttrust-pre-invocation-ai-age&name=AgentTrust%20%E2%80%94%20Pre-Invocation%20AI%20Agent%20Trust%20%26%20Reliability%20Checks
It answered our last check on 6 November 2026 in 302 ms. Over 4 checks since 23 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
2, as returned by the server's own tools/list on 11 November 2026: assess_agent, check_agent_trust.
It answered our last check on 6 November 2026 in 302 ms. Over 4 checks since 23 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://getagenttrust.com/api/mcp/public. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.agenttrust-ai. Endpoint host: getagenttrust.com. ARD identifier: urn:air:io.github.agenttrust-ai:mcp:agenttrust.
First indexed 19 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.