# AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks (remote · getagenttrust.com)

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

- Trust score: 70/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-29

## Components

- remote · `getagenttrust.com`: 70/100 (this document), [markdown](https://verifymcp.io/servers/agenttrust-ai-agenttrust/api-mcp-2.md), [page](https://verifymcp.io/servers/agenttrust-ai-agenttrust/api-mcp-2)

## Channel facts

- Endpoint: `https://getagenttrust.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.3`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-29.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 79/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 751 tokens (~150/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_heartbeat" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the AgentTrust — Pre-Invocation AI Agent Trust & Reliability… MCP server?

AgentTrust — Pre-Invocation AI Agent Trust & Reliability… is a hosted endpoint at https://getagenttrust.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http agenttrust-ai-agenttrust 'https://getagenttrust.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "agenttrust-ai-agenttrust": {
      "url": "https://getagenttrust.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "agenttrust-ai-agenttrust": {
      "type": "http",
      "url": "https://getagenttrust.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.agenttrust-ai-agenttrust]
url = "https://getagenttrust.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agenttrust-ai-agenttrust": {
      "type": "remote",
      "url": "https://getagenttrust.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add agenttrust-ai-agenttrust --url 'https://getagenttrust.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  agenttrust-ai-agenttrust:
    url: "https://getagenttrust.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "agenttrust-ai-agenttrust": {
      "Transport": "http",
      "Url": "https://getagenttrust.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add agenttrust-ai-agenttrust -t streamable-http -u 'https://getagenttrust.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "agenttrust-ai-agenttrust": {
      "type": "http",
      "url": "https://getagenttrust.com/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-29 (score 70, 0)

- [functional] Server version: 1.0.2 → 1.0.3

### 2026-09-28 (score 70, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-26 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-25 (score 68, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-23 (score 67, 0)

- [security] Tool “check_agent_trust” rewrote its description, which is the text the model reads

### 2026-09-22 (score 67, +1)

- [functional improvement] Tool coverage: 86% → 100%
- [cosmetic] “check_agent_trust” reworded the description of “endpointUrl”

### 2026-09-21 (score 66, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.0.0 → 1.0.2

## MCP tools (5)

### `list_agents` (~253 tokens)

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.

Input parameters:

- `cursor` (string): Opaque pagination cursor from a previous call's nextCursor.
- `endpointUrl` (string): Look up the agent registered with exactly this invocation URL, instead of browsing the full listing — the entry point for a trust check on an agent you only have a URL for. Matches ignore trailing-sl…
- `limit` (integer): Max agents to return (1-100, default 20).

Output parameters:

- `agents` (array)
- `pagination` (object)

### `get_agent` (~71 tokens)

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.

Input parameters:

- `slug` (string, required): The agent's URL slug (from its public profile or a list_agents result).

Output parameters:

- `agentCard` (object)
- `capabilities` (array)
- `createdAt` (string)
- `description` (string|null)
- `httpStatus` (number|null)
- `id` (string)
- `lastCheckedAt` (string|null)
- `latencyMs` (number|null)
- `name` (string)
- `ownershipVerifiedAt` (string|null)
- `reliabilityScore` (number|null)
- `reliabilityScoreComputedAt` (string|null)
- `reliabilityScoreStatus` (string)
- `slug` (string)
- `status` (string)
- `trustDecision` (object)
- `verified` (boolean)
- `version` (string|null)

### `get_agent_health` (~59 tokens)

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.

Input parameters:

- `slug` (string, required): The agent's URL slug (from its public profile or a list_agents result).

Output parameters:

- `agentId` (string)
- `checkStatus` (string|null)
- `httpStatus` (number|null)
- `lastCheckedAt` (string|null)
- `latencyMs` (number|null)
- `reliabilityScore` (number|null)
- `reliabilityScoreComputedAt` (string|null)
- `reliabilityScoreStatus` (string)
- `slug` (string)
- `status` (string)

### `send_heartbeat` (~63 tokens)

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.

Input parameters:

- `slug` (string, required): The agent's URL slug (from its public profile or a list_agents result).

Output parameters:

- `lastHeartbeatAt` (string|null)
- `slug` (string)
- `status` (string)

### `check_agent_trust` (~163 tokens)

Check Agent Trust

The preferred pre-invocation trust check for an unknown external agent. 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.

Input parameters:

- `endpointUrl` (string, required): The exact invocation URL of the agent you're about to call. Used only to look up AgentTrust's own already-observed data for it — this endpoint is never contacted during the check.

Output parameters:

- `matched` (boolean)
- `name` (string)
- `reliabilityScore` (number|null)
- `reliabilityScoreStatus` (string)
- `slug` (string)
- `status` (string)
- `trustDecision` (object)
- `verified` (boolean)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/agenttrust-ai-agenttrust/api-mcp-2#diagnostics

## Score history

- 2026-09-29: 70
- 2026-09-28: 70
- 2026-09-27: 69
- 2026-09-26: 69
- 2026-09-25: 68
- 2026-09-24: 68
- 2026-09-23: 67
- 2026-09-22: 67
- 2026-09-21: 66
- 2026-09-20: 65

## Common questions

### What is the AgentTrust — Pre-Invocation AI Agent Trust & Reliability… MCP server?

AgentTrust — Pre-Invocation AI Agent Trust & Reliability… is an MCP server listed in the public MCP registry as io.github.agenttrust-ai/agenttrust. Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision. This page covers its hosted endpoint (https://getagenttrust.com/api/mcp).

### Is the AgentTrust — Pre-Invocation AI Agent Trust & Reliability… MCP server safe to use?

AgentTrust — Pre-Invocation AI Agent Trust & Reliability… scores 70 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AgentTrust — Pre-Invocation AI Agent Trust & Reliability… MCP server expose?

AgentTrust — Pre-Invocation AI Agent Trust & Reliability… exposes 5 tools: list_agents, get_agent, get_agent_health, send_heartbeat, check_agent_trust. Their descriptions and schemas cost roughly 609 tokens of context every time the server is loaded.

### Does the AgentTrust — Pre-Invocation AI Agent Trust & Reliability… MCP server require authentication?

No. We connected to AgentTrust — Pre-Invocation AI Agent Trust & Reliability… without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AgentTrust — Pre-Invocation AI Agent Trust & Reliability… MCP server still maintained?

AgentTrust — Pre-Invocation AI Agent Trust & Reliability… is still listed as active in the MCP registry. We last reached this channel on 29 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://getagenttrust.com/api/mcp
- Repository: https://github.com/agenttrust-ai/agenttrust
- Website: https://getagenttrust.com/docs
- Changelog RSS feed: https://verifymcp.io/servers/agenttrust-ai-agenttrust/api-mcp-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/agenttrust-ai-agenttrust/api-mcp-2.json
- HTML version of this page: https://verifymcp.io/servers/agenttrust-ai-agenttrust/api-mcp-2