# Trust Live (remote · mcp-selection-lab-production.up.railway.app)

Evidence-linked MCP selection and non-executing Safe-Call review; surfaces unknowns.

- Trust score: 80/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp-selection-lab-production.up.railway.app`: 80/100 (this document), [markdown](https://verifymcp.io/servers/changhuliu-trust-live/trust-live-mcp.md), [page](https://verifymcp.io/servers/changhuliu-trust-live/trust-live-mcp)

## Channel facts

- Endpoint: `https://mcp-selection-lab-production.up.railway.app/trust-live/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-11-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 54/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 301 tokens (~60/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 80/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 30% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - 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 Trust Live MCP server?

Trust Live is a hosted endpoint at https://mcp-selection-lab-production.up.railway.app/trust-live/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 changhuliu-trust-live 'https://mcp-selection-lab-production.up.railway.app/trust-live/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "changhuliu-trust-live": {
      "url": "https://mcp-selection-lab-production.up.railway.app/trust-live/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "changhuliu-trust-live": {
      "type": "http",
      "url": "https://mcp-selection-lab-production.up.railway.app/trust-live/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.changhuliu-trust-live]
url = "https://mcp-selection-lab-production.up.railway.app/trust-live/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "changhuliu-trust-live": {
      "type": "remote",
      "url": "https://mcp-selection-lab-production.up.railway.app/trust-live/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add changhuliu-trust-live --url 'https://mcp-selection-lab-production.up.railway.app/trust-live/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  changhuliu-trust-live:
    url: "https://mcp-selection-lab-production.up.railway.app/trust-live/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "changhuliu-trust-live": {
      "Transport": "http",
      "Url": "https://mcp-selection-lab-production.up.railway.app/trust-live/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add changhuliu-trust-live -t streamable-http -u 'https://mcp-selection-lab-production.up.railway.app/trust-live/mcp'
```

### Other

```json
{
  "mcpServers": {
    "changhuliu-trust-live": {
      "type": "http",
      "url": "https://mcp-selection-lab-production.up.railway.app/trust-live/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.

### 2026-11-13 (score 80, +1)

- [security] Stability: 0.97 → pass

### 2026-11-12 (score 79, −1)

- [functional] Stability: pass → 0.97

### 2026-11-09 (score 80, +1)

- [security] Stability: 0.97 → pass

### 2026-11-07 (score 79, +1)

- [functional improvement] Endpoint reachability: unreachable → reachable

### 2026-11-06 (score 78, +1)

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

### 2026-11-05 (score 77, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] HSTS header: fail → unverified
- [security regression] Stability: 0.83 → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-11-02 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `recommend_provider` (~49 tokens)

Recommend a provider with hard-filter outcomes, component scores, evidence, and Safe-Call constraints.

Input parameters:

- `task_requirements` (object, required): Structured capability, operation, auth, payment, data and evidence requirements.

### `compare_providers` (~38 tokens)

Compare matching providers across capability, verification, safety, payment, freshness and unknowns.

Input parameters:

- `task_requirements` (object, required): Structured task requirements.

### `get_provider_profile` (~33 tokens)

Get a canonical provider profile with capabilities, evidence references, and safe-call contracts.

Input parameters:

- `provider_id` (string, required)

### `get_capability` (~35 tokens)

Get every provider capability with this canonical action ID, including evidence and Safe-Call contract.

Input parameters:

- `capability_id` (string, required)

### `evaluate_safe_call` (~75 tokens)

Evaluate Safe-Call constraints without invoking the provider tool.

Input parameters:

- `arguments` (object, required): Proposed arguments; evaluated locally and never sent to the provider.
- `capability_id` (string, required)
- `data_classes`
- `provider_id` (string, required)
- `repository_visibility`
- `user_confirmed` (boolean)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/changhuliu-trust-live/trust-live-mcp#diagnostics

## Score history

- 2026-11-21: 80
- 2026-11-20: 80
- 2026-11-19: 80
- 2026-11-18: 80
- 2026-11-17: 80
- 2026-11-16: 80
- 2026-11-15: 80
- 2026-11-14: 80
- 2026-11-13: 80
- 2026-11-12: 79
- 2026-11-11: 80
- 2026-11-10: 80
- 2026-11-09: 80
- 2026-11-08: 79
- 2026-11-07: 79
- 2026-11-06: 78
- 2026-11-05: 77
- 2026-11-04: 77
- 2026-11-03: 77
- 2026-11-02: 77
- 2026-11-01: 76
- 2026-10-31: 76
- 2026-10-30: 75
- 2026-10-29: 75
- 2026-10-28: 74
- 2026-10-27: 74
- 2026-10-26: 73
- 2026-10-25: 73
- 2026-10-24: 72
- 2026-10-23: 72

## Common questions

### What is the Trust Live MCP server?

Trust Live is an MCP server listed in the public MCP registry as io.github.ChanghuLiu/trust-live. Evidence-linked MCP selection and non-executing Safe-Call review; surfaces unknowns. This page covers its hosted endpoint (https://mcp-selection-lab-production.up.railway.app/trust-live/mcp).

### Is the Trust Live MCP server safe to use?

Trust Live scores 80 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 Trust Live MCP server expose?

Trust Live exposes 5 tools: recommend_provider, compare_providers, get_provider_profile, get_capability, evaluate_safe_call. Their descriptions and schemas cost roughly 230 tokens of context every time the server is loaded.

### Does the Trust Live MCP server require authentication?

No. We connected to Trust Live without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Trust Live MCP server still maintained?

Trust Live is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Trust Live MCP server?

VerifyMCP ran 13 checks on Trust Live, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp-selection-lab-production.up.railway.app/trust-live/mcp
- Repository: https://github.com/ChanghuLiu/mcp-selection-lab
- Website: https://mcp-selection-lab-production.up.railway.app/
- Changelog RSS feed: https://verifymcp.io/servers/changhuliu-trust-live/trust-live-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/changhuliu-trust-live/trust-live-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/changhuliu-trust-live/trust-live-mcp.json
- HTML version of this page: https://verifymcp.io/servers/changhuliu-trust-live/trust-live-mcp
