# Citation Verification (remote · verification-mcp.atlasword.workers.dev)

Real-time fact-check, citation verification, and source-freshness for AI agents.

- Trust score: 18/100 (low)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `verification-mcp.atlasword.workers.dev`: 18/100 (this document), [markdown](https://verifymcp.io/servers/guptaprakhariitr-verification-mcp/verification-mcp.md), [page](https://verifymcp.io/servers/guptaprakhariitr-verification-mcp/verification-mcp)

## Channel facts

- Endpoint: `https://verification-mcp.atlasword.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.1`

## 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 2026-08-03.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint returned HTTP 500.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 4 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add --transport http guptaprakhariitr-verification-mcp https://verification-mcp.atlasword.workers.dev/mcp
```

### Codex

```toml
[mcp_servers.guptaprakhariitr-verification-mcp]
url = "https://verification-mcp.atlasword.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "guptaprakhariitr-verification-mcp": {
      "type": "remote",
      "url": "https://verification-mcp.atlasword.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add guptaprakhariitr-verification-mcp --url https://verification-mcp.atlasword.workers.dev/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  guptaprakhariitr-verification-mcp:
    url: "https://verification-mcp.atlasword.workers.dev/mcp"
```

### Other

```json
{
  "mcpServers": {
    "guptaprakhariitr-verification-mcp": {
      "type": "http",
      "url": "https://verification-mcp.atlasword.workers.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.

### 2026-08-03 (score 18, −38)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.03 → unverified
- [security regression] Transport: pass → fail
- [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] Tool coverage: 100 → unverified
- [functional regression] Capabilities: fail → unverified

### 2026-08-02 (score 56, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-01 (score 56, +38)

- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 3 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] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: excellent
- [functional] First check of Tool coverage: 67
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: pass

### 2026-07-31 (score 18, +6)

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

### 2026-07-30 (score 12, 0)

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

### 2026-07-27 (score 12, 0)

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

### 2026-07-26 (score 12)

First indexed and scored.

## MCP tools (3)

### `fact_check` (~122 tokens)

Verify a factual claim against authoritative sources (Wikipedia, Wikidata, Crossref academic citations). Returns a verdict ('supported' / 'contradicted' / 'mixed' / 'unverified'), a 0–1 confidence score, and the list of sources with excerpts. Use this when an agent is about to assert a fact it isn't 100% sure of, or when post-processing LLM output to flag possibly-hallucinated claims.

Input parameters:

- `claim` (string, required): A single factual claim, ideally one sentence. Longer text is truncated to 200 chars.

### `cite_check` (~92 tokens)

Verify that one or more cited URLs (a) resolve, (b) match the cited claim text, and (c) aren't retracted. Useful when an LLM produced inline citations and you want to confirm they're real and on-point. Pass DOIs directly (e.g. '10.1038/nature12373') or full URLs. Up to 25 per call.

Input parameters:

- `citations` (array, required)

### `source_freshness` (~93 tokens)

Check whether a source URL is still live and how recently it was modified. Returns the HTTP last-modified header (if present), the most recent Wayback Machine snapshot, and a 'changed_recently' flag (last 90 days). Use this for RAG hygiene — flagging citations that point to pages that may have changed since the agent's training data.

Input parameters:

- `url` (string, required): URL to check.

## Diagnostics

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

## Score history

- 2026-08-03: 18
- 2026-08-02: 56
- 2026-08-01: 56
- 2026-07-31: 18
- 2026-07-30: 12
- 2026-07-29: 12
- 2026-07-28: 12
- 2026-07-27: 12
- 2026-07-26: 12

## Links

- Remote endpoint: https://verification-mcp.atlasword.workers.dev/mcp
- Repository: https://github.com/guptaprakhariitr/verification-mcp
- Website: https://verification-mcp.atlasword.workers.dev/
- Changelog RSS feed: https://verifymcp.io/servers/guptaprakhariitr-verification-mcp/verification-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/guptaprakhariitr-verification-mcp/verification-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/guptaprakhariitr-verification-mcp/verification-mcp