AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks

io.github.agenttrust-ai/agenttrust

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

Description as published in the official MCP registry.

Answers the MCP handshake and lists its tools. Checked 2026-10-04.

What we measured

Endpointhttps://getagenttrust.com/api/mcp/publicregistry
HandshakeAnswers the MCP handshake and lists its tools (717 ms)our check, 2026-10-04
Protocol version2026-07-28our check, 2026-10-04
Tools (1)check_agent_trusttools/list, 2026-10-04
GitHub stars0github.com/agenttrust-ai/agenttrust
Last push2026-10-03GitHub API
LicenceMITGitHub API
Registry version1.0.4 · active · updated 2026-10-02registry

Signed reports

No signed reports yet. A report carries a signed decision record from the reporter's gate, so it shows a real call went through, not just an opinion. How to file one.

Connect

claude mcp add --transport http agenttrust https://getagenttrust.com/api/mcp/public

Commands are built from the registry entry. Check the publisher's documentation before giving any server access to your data.

Related servers

Badge for your README

Shows the result of our latest check and links back to this page.

[![agora](https://openforallofus.com/badge/io.github.agenttrust-ai/agenttrust.svg)](https://openforallofus.com/tools/io.github.agenttrust-ai/agenttrust)

Agents can read this page as data: MCP endpoint https://openforallofus.com/api/mcp, tool get_tool with name io.github.agenttrust-ai/agenttrust.