# Bannerproof (remote · api.bannerproof.app)

EU cookie-consent audit: trackers before consent, Reject all, Consent Mode v2, TCF; evidence + fixes

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `api.bannerproof.app`: 37/100, [markdown](https://verifymcp.io/servers/app-bannerproof-bannerproof/api.md), [page](https://verifymcp.io/servers/app-bannerproof-bannerproof/api)
- remote · `api.bannerproof.app`: 69/100 (this document), [markdown](https://verifymcp.io/servers/app-bannerproof-bannerproof/mcp-free.md), [page](https://verifymcp.io/servers/app-bannerproof-bannerproof/mcp-free)

## Channel facts

- Endpoint: `https://api.bannerproof.app/mcp/free`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.1`

## 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 2026-11-05.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (audit_domain).
  - 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**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2346 tokens (~130/item across 18 items; 18 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 18 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 19 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 Bannerproof MCP server?

Bannerproof is a hosted endpoint at https://api.bannerproof.app/mcp/free, 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 app-bannerproof-bannerproof 'https://api.bannerproof.app/mcp/free'
```

### Cursor

```json
{
  "mcpServers": {
    "app-bannerproof-bannerproof": {
      "url": "https://api.bannerproof.app/mcp/free"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "app-bannerproof-bannerproof": {
      "type": "http",
      "url": "https://api.bannerproof.app/mcp/free"
    }
  }
}
```

### Codex

```toml
[mcp_servers.app-bannerproof-bannerproof]
url = "https://api.bannerproof.app/mcp/free"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-bannerproof-bannerproof": {
      "type": "remote",
      "url": "https://api.bannerproof.app/mcp/free",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add app-bannerproof-bannerproof --url 'https://api.bannerproof.app/mcp/free' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-bannerproof-bannerproof:
    url: "https://api.bannerproof.app/mcp/free"
```

### Netclaw

```json
{
  "McpServers": {
    "app-bannerproof-bannerproof": {
      "Transport": "http",
      "Url": "https://api.bannerproof.app/mcp/free"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-bannerproof-bannerproof -t streamable-http -u 'https://api.bannerproof.app/mcp/free'
```

### Other

```json
{
  "mcpServers": {
    "app-bannerproof-bannerproof": {
      "type": "http",
      "url": "https://api.bannerproof.app/mcp/free"
    }
  }
}
```

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.

### 2026-11-05 (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.

### 2026-11-03 (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.

### 2026-11-01 (score 67, +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.

### 2026-10-31 (score 66, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-30 (score 66)

First indexed and scored.

## MCP tools (18)

### `quick_check` (~180 tokens)

Quick consent check (free)

Free check, no account needed: opens a public website like a first-time visitor and reports whether trackers or third-party requests fire before the visitor consents (GDPR/ePrivacy), with a 0–100 score. Returns only yes/no and the score; the full findings (which trackers, the exact requests, how to fix each one) are available with a connected Bannerproof account (get_findings). Results are cached for up to 7 days. This is an automated technical check, not legal advice.

Input parameters:

- `domain` (string, required): The website's domain, e.g. example.com
- `language` (string|null): Language for the fix instructions and report links: en, de, fr, es, it, nl, da, sv, fi, no, et, pl or pt. Normally the language of the conversation. Default en.

### `get_quick_check_result` (~99 tokens)

Quick check result

Gets the result of a quick_check that was still running, by the job_id that quick_check returned.

Input parameters:

- `job_id` (string, required): The job_id returned by quick_check
- `language` (string|null): Language for the fix instructions and report links: en, de, fr, es, it, nl, da, sv, fi, no, et, pl or pt. Normally the language of the conversation. Default en.

### `account_info` (~32 tokens)

Bannerproof account

Shows the connected Bannerproof account: plan, how many monitored domains it allows and uses, and the remaining audit credits.

### `list_domains` (~29 tokens)

List monitored domains

Lists the domains monitored in the connected Bannerproof account, with the latest score and whether issues were found.

### `add_domain` (~121 tokens)

Add a domain to monitoring

Adds a domain to weekly monitoring in the connected account (within the plan's domain limit) and runs its first scan. Requires a plan with a free domain slot; otherwise it returns an error that names the plan needed.

Input parameters:

- `domain` (string, required): The website's domain, e.g. example.com
- `language` (string|null): Language for the fix instructions and report links: en, de, fr, es, it, nl, da, sv, fi, no, et, pl or pt. Normally the language of the conversation. Default en.

### `get_upgrade_link` (~246 tokens)

Link to buy a plan or credits

Returns a direct checkout link on bannerproof.app for a plan or audit credits (payment happens there, never in the chat). goal: 'audit' = one-off full report for one domain (€19), 'solo' = monitoring for 1 domain (€11/month), 'monitoring' = up to 7 domains (€49/month), 'agency' = up to 25 domains with white-label reports (€139/month), 'credits' = audit credits for checking any site (5 for €79, 15 for €199, 40 for €449). Prices include VAT; the checkout shows the final price.

Input parameters:

- `credits` (integer|null): For goal=credits: 5, 15 or 40
- `domain` (string|null): The domain the purchase is for, if any (pre-fills it after checkout)
- `goal` (string, required): audit, solo, monitoring, agency or credits
- `language` (string|null): Language for the fix instructions and report links: en, de, fr, es, it, nl, da, sv, fi, no, et, pl or pt. Normally the language of the conversation. Default en.

### `scan_domain` (~140 tokens)

Run a fresh scan

Runs a fresh scan of a domain monitored in the connected account (e.g. to check a fix). Waits up to about 40 seconds; if the scan is still running it returns a job_id for get_scan_status. A manual scan can be run once every 15 minutes per domain.

Input parameters:

- `domain` (string, required): A domain monitored in the connected account, e.g. example.com
- `language` (string|null): Language for the fix instructions and report links: en, de, fr, es, it, nl, da, sv, fi, no, et, pl or pt. Normally the language of the conversation. Default en.

### `audit_domain` (~208 tokens)

Audit any website (uses 1 credit)

Full audit of any website (for example a client's or a prospect's site) that is NOT monitored in the account. Spends 1 audit credit, so it is marked destructive and runs only with confirm=true. If the same site was audited in the last 24 hours, the earlier result is returned without spending a credit unless force_new=true. If the site can't be scanned, the credit is returned automatically.

Input parameters:

- `confirm` (boolean, required): Confirms spending 1 audit credit; without true the audit does not run
- `domain` (string, required): The website's domain, e.g. client-site.com
- `force_new` (boolean): Run a new paid audit even if this site was audited in the last 24 hours
- `language` (string|null): Language for the fix instructions and report links: en, de, fr, es, it, nl, da, sv, fi, no, et, pl or pt. Normally the language of the conversation. Default en.

### `get_scan_status` (~101 tokens)

Scan status

Gets the status of a scan_domain or audit_domain that was still running, by the job_id it returned.

Input parameters:

- `job_id` (string, required): The job_id returned by scan_domain or audit_domain
- `language` (string|null): Language for the fix instructions and report links: en, de, fr, es, it, nl, da, sv, fi, no, et, pl or pt. Normally the language of the conversation. Default en.

### `get_findings` (~172 tokens)

Full findings with fixes

Full findings of the latest scan of a domain: which trackers and third-party requests fired before consent or kept running after 'Reject', the cookie banner's reject option, Google Consent Mode v2 signals, what happens after 'Accept', IAB TCF consent after Reject, Global Privacy Control, and a concrete fix and legal reference for each issue. Works for domains monitored in the account and for sites audited with audit_domain(s). For one finding in more depth use explain_finding.

Input parameters:

- `domain` (string, required): The domain, e.g. example.com
- `language` (string|null): Language for the fix instructions and report links: en, de, fr, es, it, nl, da, sv, fi, no, et, pl or pt. Normally the language of the conversation. Default en.

### `scan_history` (~45 tokens)

Scan history

Score and issue count over time for a domain monitored in the account (newest first, up to 30).

Input parameters:

- `domain` (string, required): A domain monitored in the connected account

### `get_report_link` (~114 tokens)

Shareable report link

Creates (or returns the existing) private link to the latest report of a domain, for sending to a client or developer — opens without a login. Works for monitored domains and audited sites.

Input parameters:

- `domain` (string, required): The domain, e.g. example.com
- `language` (string|null): Language for the fix instructions and report links: en, de, fr, es, it, nl, da, sv, fi, no, et, pl or pt. Normally the language of the conversation. Default en.

### `get_capabilities` (~48 tokens)

What Bannerproof checks

Describes what Bannerproof checks, what each tool does, what needs an account and what it costs. Call this first when the user asks what this server can do or which tool to use.

### `explain_finding` (~171 tokens)

Explain a finding

Explains one finding in plain language: what it is, why it is a problem, how to fix it and which rule it relates to. Pass the tracker name exactly as get_findings returned it. Free, no account needed.

Input parameters:

- `language` (string|null): Language for the fix instructions: en, de, fr, es, it, nl, da, sv, fi, no, et, pl or pt. Default en.
- `status` (string|null): What was found: fired_before_consent (default), still_active_after_reject, missing_reject_option, tcf_consent_after_reject or gpc_ignored
- `tracker` (string, required): The tracker or cookie name from get_findings, e.g. 'Meta (Facebook) Pixel' or '_ga cookie'

### `compare_scans` (~119 tokens)

What changed since the last scan

Compares the latest scan of a monitored domain with the previous one (or with the newest scan on or before a given date): new issues, resolved issues, score change, banner and reject option changes. Use it to confirm a fix worked or to see what a site update broke.

Input parameters:

- `compare_with_date` (string|null): Optional date (e.g. 2026-10-01): compare with the newest scan on or before that date instead of the previous one
- `domain` (string, required): A domain monitored in the connected account

### `get_evidence` (~93 tokens)

Evidence pack (CSV/JSON)

Evidence pack of the latest scan of a domain: every tracker request in order with its phase (before consent / after Reject) and time, plus the cookies and consent signals. Returns a summary and download links (CSV and JSON, open without a login) for a client, a developer or a dispute. Works for monitored domains and audited sites.

Input parameters:

- `domain` (string, required): The domain, e.g. example.com

### `audit_domains` (~181 tokens)

Audit several websites (1 credit each)

Audits up to 10 websites at once (e.g. an agency's client list or prospects). Spends 1 audit credit per new audit and runs only with confirm=true; sites audited in the last 24 hours are reused without spending. If the account doesn't have enough credits for the whole list, nothing starts (no partial batch). A site that can't be scanned (down, blocking bots, too slow) is not charged — its credit is returned automatically. Returns a job_id per site — follow up with get_audits_status for all of them, then get_findings per domain.

Input parameters:

- `confirm` (boolean, required): Confirms spending 1 audit credit per new audit; without true nothing runs
- `domains` (array, required): The websites' domains, e.g. ["client-a.com", "client-b.de"] — up to 10

### `get_audits_status` (~89 tokens)

Status of several audits

Status of several audits at once (e.g. the job_ids audit_domains returned): which are done with their score and issue count, which are still running, and which failed — with the reason. Failed scans are not charged: their audit credit goes back to the account automatically.

Input parameters:

- `job_ids` (array, required): The job_ids from audit_domains or audit_domain — up to 10

## Diagnostics

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

## Score history

- 2026-11-05: 69
- 2026-11-04: 68
- 2026-11-03: 68
- 2026-11-02: 67
- 2026-11-01: 67
- 2026-10-31: 66
- 2026-10-30: 66

## Common questions

### What is the Bannerproof MCP server?

Bannerproof is an MCP server listed in the public MCP registry as app.bannerproof/bannerproof. EU cookie-consent audit: trackers before consent, Reject all, Consent Mode v2, TCF; evidence + fixes. This page covers its hosted endpoint (https://api.bannerproof.app/mcp/free).

### Is the Bannerproof MCP server safe to use?

Bannerproof scores 69 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 Bannerproof MCP server expose?

Bannerproof exposes 18 tools: quick_check, get_quick_check_result, account_info, list_domains, add_domain, and 13 more. Their descriptions and schemas cost roughly 2,188 tokens of context every time the server is loaded.

### Does the Bannerproof MCP server require authentication?

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

### Is the Bannerproof MCP server still maintained?

Bannerproof is still listed as active in the MCP registry. We last reached this channel on 5 November 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://api.bannerproof.app/mcp/free
- Repository: https://github.com/bannerproof/bannerproof
- Website: https://bannerproof.app/mcp
- Changelog RSS feed: https://verifymcp.io/servers/app-bannerproof-bannerproof/mcp-free.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-bannerproof-bannerproof/mcp-free.json
- HTML version of this page: https://verifymcp.io/servers/app-bannerproof-bannerproof/mcp-free