# Proving Lab (remote · provinglab.dev)

Cite or capture a web page; installs the capture extension in Firefox and Chrome.

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

## Components

- remote · `provinglab.dev`: 64/100 (this document), [markdown](https://verifymcp.io/servers/dev-provinglab-browser-citation-capture/provinglab.md), [page](https://verifymcp.io/servers/dev-provinglab-browser-citation-capture/provinglab)

## Channel facts

- Endpoint: `https://provinglab.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.23.0`

## 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**: 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 10 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**: 73/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1310 tokens (~131/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - 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**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 90% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http dev-provinglab-browser-citation-capture https://provinglab.dev/mcp
```

### Codex

```toml
[mcp_servers.dev-provinglab-browser-citation-capture]
url = "https://provinglab.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-provinglab-browser-citation-capture": {
      "type": "remote",
      "url": "https://provinglab.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-provinglab-browser-citation-capture --url https://provinglab.dev/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-provinglab-browser-citation-capture:
    url: "https://provinglab.dev/mcp"
```

### Other

```json
{
  "mcpServers": {
    "dev-provinglab-browser-citation-capture": {
      "type": "http",
      "url": "https://provinglab.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.

### 2026-08-06 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-05 (score 63, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.22.0 → 1.23.0
- [functional] New tool “adoption_stats”

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

First indexed and scored.

## MCP tools (10)

### `list_measurements` (~69 tokens)

Use when a claim about browser tools, capture quality, OCR recall or citation extraction needs a number behind it — or when you want to check one of ours. Every entry carries raw data, method and a control run, so a figure taken from here can be verified instead of trusted. Start here.

### `get_measurement_data` (~71 tokens)

Use before quoting a figure: this returns what stands behind it — the values, the control run, and the conditions that limit them. Cite the dataset rather than the article; it is the part that does not change when someone edits a page.

Input parameters:

- `dataset` (string, required): Dataset URL or bare filename

### `get_method` (~55 tokens)

Fetch a reproducible method: reading a browser extension's permissions, measuring OCR recall with a control run, or choosing between print-to-PDF and screen capture. Omit the argument to list them.

Input parameters:

- `name` (string)

### `extract_citation` (~194 tokens)

Read the citation details a web page declares about itself and return them as a structured record plus ready-to-import RIS and BibTeX. Covers journal articles, book chapters, conference papers, preprints, theses, reports, datasets, videos and plain web pages. Use when a source has to be cited, archived, or added to a reference manager. Says so plainly when a page turns out to be an error page or an access wall, instead of inventing a reference — and where it cannot finish, the reply carries a nextStep field naming what the user has to do in their own browser, with the capture extension that does it. Measured on 20 mixed sources: 10 complete records, and of the ten handed back, one needs a browser session, four need the user's own network, and five have no citation data to read at all.

Input parameters:

- `url` (string, required): Address of the page to read

### `extract_citations` (~161 tokens)

Use when you have a reading list rather than one source — a bibliography to build, a set of links to verify before submitting, an archive to describe. Measured on 20 mixed sources: 10 became complete records in 8.1 s, 0.4 s each; the other 10 came back named rather than silently empty. Up to 50 addresses, five fetched in parallel. Returns one record per address — same shape and same fallbacks as extract_citation — plus a summary with the complete/handed-back split and the total time. Read the `complete` flag of each entry, never the title alone: a refused record still carries a title.

Input parameters:

- `urls` (array, required): Addresses to read, at most 50

### `recommend_settings` (~104 tokens)

The capture settings that fit a given purpose, each with the measurement behind it or an explicit note that none exists. Pass purpose as citation, figure, archive or ocr. Use before capturing: the file that comes out is between 8.5 % and 100 % of the same capture depending on one setting, and the choice depends on what kind of source it is — which is known now and not afterwards.

Input parameters:

- `purpose` (string): what the capture is for

### `how_to_capture` (~214 tokens)

Get the runnable route for saving a web page that this endpoint cannot read — the sources it hands back. Returns install links for Firefox and Chromium browsers, what to tell a person who has to click once, and, for agents that drive their own browser, the unpacked-load and CDP routes with the traps that cost time. Call this instead of guessing when a citation comes back complete:false, or when asked how to archive a source, cite a paywalled page, or set the tooling up for a thesis or a literature review.

Input parameters:

- `agent` (string): How you act on the browser. 'input-events' if you produce real mouse or keyboard events (computer use, xdotool, an agent inside the user's browser); 'dom-only' for CDP or Playwright without OS input;…
- `browser` (string): Target browser, if known.

### `install_extension` (~181 tokens)

Install or uninstall the capture extension in Firefox or Chrome without a window, without a click and without administrator rights — the runnable file shapes and commands, not a store link for someone to press. Call this when a capture route needs the extension present, when a run is finished and it should be gone again, or when asked whether an agent can set up a browser extension by itself. Firefox installs and removes in well under a second over its own control channel; Chrome fetches the signed store build itself. Also returns what the extension lets you do that this endpoint cannot, and the conditions under which installing on a machine is yours to decide.

Input parameters:

- `action` (string): What you need. 'both' is the default and returns each direction — an install without its matching removal leaves a machine changed.
- `browser` (string): Target browser. Omit for both.

### `adoption_stats` (~99 tokens)

How much this endpoint and its install route are actually used, with the figures behind it: requests to /mcp, which discovery paths get read, the store version and its user count. Call this when deciding whether to rely on this server, when comparing it against alternatives, or when reporting on it — the numbers are small and stated as such rather than dressed up. Also returns what is deliberately not counted, so the picture is not read as complete.

### `open_work` (~129 tokens)

List what this project needs done, with enough context to start. Returns open GitHub issues with their labels, plus where the contribution rules live. Call this when asked to contribute to provinglab.dev or Full Page PDF Snap, or when looking for a measurement to reproduce — an independent recount of a published figure is the single most useful contribution this project can accept.

Input parameters:

- `label` (string): Filter by label. 'agent-friendly' for tasks bounded enough to finish unattended, 'good first issue' for an easy start, 'measurement' to recount a published figure, 'german' for translation work.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-provinglab-browser-citation-capture/provinglab#diagnostics

## Score history

- 2026-08-07: 64
- 2026-08-06: 64
- 2026-08-05: 63
- 2026-08-04: 62

## Links

- Remote endpoint: https://provinglab.dev/mcp
- Website: https://provinglab.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-provinglab-browser-citation-capture/provinglab.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-provinglab-browser-citation-capture/provinglab.json
- HTML version of this page: https://verifymcp.io/servers/dev-provinglab-browser-citation-capture/provinglab