# dk.humanified/trinity-research (remote · trinity-v2-mcp.fly.dev)

Fact-check claims against live web sources: verdict, consensus, cited sources, PII redaction.

- Trust score: 64/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-07

## Components

- remote · `trinity-v2-mcp.fly.dev`: 64/100 (this document), [markdown](https://verifymcp.io/servers/dk-humanified-trinity-research/trinity-v2-mcp.md), [page](https://verifymcp.io/servers/dk-humanified-trinity-research/trinity-v2-mcp)

## Channel facts

- Endpoint: `https://trinity-v2-mcp.fly.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-08-07.

- **Endpoint Security**: 57/100
  - 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 4 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.
  - 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**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 395 tokens (~98/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http dk-humanified-trinity-research https://trinity-v2-mcp.fly.dev/mcp
```

### Codex

```toml
[mcp_servers.dk-humanified-trinity-research]
url = "https://trinity-v2-mcp.fly.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dk-humanified-trinity-research": {
      "type": "remote",
      "url": "https://trinity-v2-mcp.fly.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dk-humanified-trinity-research --url https://trinity-v2-mcp.fly.dev/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dk-humanified-trinity-research:
    url: "https://trinity-v2-mcp.fly.dev/mcp"
```

### Other

```json
{
  "mcpServers": {
    "dk-humanified-trinity-research": {
      "type": "http",
      "url": "https://trinity-v2-mcp.fly.dev/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.

### 2026-08-07 (score 64, +19)

- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional regression] Schema quality: 30 → 98
- [functional regression] Schema quality: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] Schema quality: poor → good
- [functional] Stability: fail → 0.10
- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-08-06 (score 45, −17)

- [security regression] Stability: 0.03 → fail
- [security regression] A breaking change shipped without a version bump: still 1.7.0
- [security regression] Tool “ping” was removed
- [security regression] Tool “privacy_shield_redact” was removed
- [security regression] Tool “structured_brief_synthesizer” was removed
- [security regression] Tool “multi_source_validator” was removed
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes.
- [functional regression] Schema quality: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Schema quality: 98 → 30
- [functional] Schema quality: good → poor

### 2026-08-05 (score 62, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-04 (score 62)

First indexed and scored.

## MCP tools (4)

### `multi_source_validator` (~131 tokens)

Verify a factual claim against multiple live web sources (Brave). Returns a JSON object with a verdict (supported / contradicted / unverified), a 0-1 consensus score, short reasoning, and the actual cited sources (ref, title, url). Judges only from retrieved sources — never fabricates. 'contradicted' is used only when sources actively assert the opposite; absence of evidence yields 'unverified'.

Input parameters:

- `claim` (string, required): The factual claim to verify against multiple web sources.
- `count` (integer): How many web sources to consult (default 5, max 10).

### `ping` (~38 tokens)

Liveness probe. Returns 'pong' plus any supplied message.

Input parameters:

- `message` (string|null): Optional message echoed back, to verify round-trip serialization.

### `privacy_shield_redact` (~73 tokens)

Redact personally identifiable information (PII) from text — emails, phone numbers, IDs, names, etc. Returns the masked text plus a count of what was redacted by type. Privacy-by-default for research workflows.

Input parameters:

- `text` (string, required): The text to scan and redact for personally identifiable information.

### `structured_brief_synthesizer` (~123 tokens)

Synthesize multiple sources into a structured, cited brief. format: 'synthesis' (narrative), 'summary' (bullets), or 'integrated' (how sources connect). Cites inline as [n]; never invents facts beyond the sources.

Input parameters:

- `format` (string): Output format: "synthesis" (narrative, default), "summary" (bullets), or "integrated" (shows how sources logically connect).
- `sources` (array, required): Sources to integrate (each with a title and content).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dk-humanified-trinity-research/trinity-v2-mcp#diagnostics

## Score history

- 2026-08-07: 64
- 2026-08-06: 45
- 2026-08-05: 62
- 2026-08-04: 62

## Links

- Remote endpoint: https://trinity-v2-mcp.fly.dev/mcp
- Changelog RSS feed: https://verifymcp.io/servers/dk-humanified-trinity-research/trinity-v2-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dk-humanified-trinity-research/trinity-v2-mcp.json
- HTML version of this page: https://verifymcp.io/servers/dk-humanified-trinity-research/trinity-v2-mcp