Other · Remote MCP server

AgentTrust - Pre-Invocation AI Agent Trust & Reliability Checks

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

Visit AgentTrust - Pre-Invocation AI Agent Trust & Reliability Checks's website

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.agenttrust-ai/agenttrust
Version
1.0.4
Status
Active
Category
other
Transport
Streamable HTTP
Published
2026-10-02
Updated
2026-10-02
Publisher
agenttrust-ai (GitHub)
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/agenttrust-ai) · how
Website
getagenttrust.com/docs
Repository
github.com/agenttrust-ai/agenttrust
Source
Registry API entry

Remote endpoints

TransportURLHeaders declared
Streamable HTTPhttps://getagenttrust.com/api/mcp/publicNone
Streamable HTTPhttps://getagenttrust.com/api/mcpAuthorization (secret)

Live check

This directory connected to each remote endpoint and asked for its list of tools. The check connects and lists tools only; it doesn't run tools, sign in or test security.

Endpoint
https://getagenttrust.com/api/mcp/public (HTTP)
Reachable
Yes (HTTP 200)
Handshake
agenttrust 1.0.4 · protocol 2025-06-18
Tools discovered
1: check_agent_trust
Checked on
2026-10-05
Endpoint
https://getagenttrust.com/api/mcp (HTTP)
Reachable
Yes (HTTP 200)
Handshake
agenttrust 1.0.4 · protocol 2025-06-18
Tools discovered
5: list_agents, get_agent, get_agent_health, send_heartbeat, check_agent_trust
Checked on
2026-10-05

How the live check works

How to connect AgentTrust - Pre-Invocation AI Agent Trust & Reliability Checks

AgentTrust - Pre-Invocation AI Agent Trust & Reliability Checks is a remote MCP server: there is nothing to install. Its endpoints are https://getagenttrust.com/api/mcp/public and https://getagenttrust.com/api/mcp, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.

The registry entry declares an HTTP header for the connection: Authorization (secret). A secret header usually carries an API key or token issued by the service; clients that accept custom headers set it with the server's URL.

Derived from the registry entry; the live check above only shows whether the endpoint answered. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More other servers

All 8,395 →
ServerRunsEndpoint or package
agentsync (remote)Cloudflare Worker remote transport for agentsync. MCP 2026-07-28, dual-era, stateless.Remote · HTTPagentsync-remote.x.workers.dev
AgentTaktReview, edit, and approve AI agent task plans in a ComfyUI-style visual node editor in your terminal.Local · stdioPyPI: agenttakt
AgentTrustQuality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.Local · stdioPyPI: mcp-agenttrust
AgenttrustTrust scores & reputation for the agent-to-agent economy. Verify A2A counterparties.Local · stdionpm: agenttrust-mcp
AgentUtility Browser WorkflowMCP server for the @agentutility browser-workflow cluster - pay-per-call x402 tools, no API keys…Local · stdionpm: @agentutility/mcp-browser-workflow
AgentUtility Edge MarketMCP server for the @agentutility edge-market cluster - pay-per-call x402 tools, no API keys, USDC…Local · stdionpm: @agentutility/mcp-edge-market
AgentUtility MatchpointMCP server for the @agentutility matchpoint cluster - pay-per-call x402 tools, no API keys, USDC…Local · stdionpm: @agentutility/mcp-matchpoint
AgentUtility Model RouterMCP server for the @agentutility model-router cluster - pay-per-call x402 tools, no API keys, USDC…Local · stdionpm: @agentutility/mcp-model-router