# Proofsource (remote · app.proofsource.co)

AI visibility: which buyer questions name your brand in ChatGPT, Perplexity, Claude, AI Overviews.

- Trust score: 86/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `app.proofsource.co`: 86/100 (this document), [markdown](https://verifymcp.io/servers/co-proofsource-proofsource/v1-mcp.md), [page](https://verifymcp.io/servers/co-proofsource-proofsource/v1-mcp)

## Channel facts

- Endpoint: `https://app.proofsource.co/v1/mcp`
- Transports: `streamable-http`
- Auth: `required`
- 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 2026-10-23.

- **Endpoint Security**: 97/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - 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.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1992 tokens (~132/item across 15 items; 14 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 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 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### How do I install the Proofsource MCP server?

Proofsource is a hosted endpoint at https://app.proofsource.co/v1/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 co-proofsource-proofsource 'https://app.proofsource.co/v1/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "co-proofsource-proofsource": {
      "url": "https://app.proofsource.co/v1/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "co-proofsource-proofsource": {
      "type": "http",
      "url": "https://app.proofsource.co/v1/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.co-proofsource-proofsource]
url = "https://app.proofsource.co/v1/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "co-proofsource-proofsource": {
      "type": "remote",
      "url": "https://app.proofsource.co/v1/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add co-proofsource-proofsource --url 'https://app.proofsource.co/v1/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  co-proofsource-proofsource:
    url: "https://app.proofsource.co/v1/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "co-proofsource-proofsource": {
      "Transport": "http",
      "Url": "https://app.proofsource.co/v1/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add co-proofsource-proofsource -t streamable-http -u 'https://app.proofsource.co/v1/mcp'
```

### Other

```json
{
  "mcpServers": {
    "co-proofsource-proofsource": {
      "type": "http",
      "url": "https://app.proofsource.co/v1/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.

### 2026-10-22 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 84, 0)

- [cosmetic] “mark_fix_shipped” added an optional parameter “acknowledge_unfilled_gaps”

### 2026-10-18 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 83, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “add_brand” rewrote its description, which is the text the model reads
- [security] Tool “create_prompt” rewrote its description, which is the text the model reads
- [security] Tool “list_brands” rewrote its description, which is the text the model reads
- [security] Tool “list_topics” rewrote its description, which is the text the model reads
- [security] Tool “see_example” rewrote its description, which is the text the model reads

### 2026-10-16 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 82, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-13 (score 81)

First indexed and scored.

## MCP tools (14)

### `list_brands` (~34 tokens)

List my tracked brands

The brands this workspace tracks in AI answers, with ids and websites. Call first; every other tool takes a brand_id.

### `list_topics` (~64 tokens)

Which buyer questions are tracked?

The topics and buyer questions this workspace asks ChatGPT, Perplexity, Claude and Google AI for a brand. Gives the topic_id create_prompt needs.

Input parameters:

- `brand_id` (string): Brand id from list_brands. May be omitted when the workspace tracks a single brand.

### `get_visibility` (~200 tokens)

Is my brand mentioned in AI answers?

How often ChatGPT, Perplexity, Claude and Google AI mention the brand when buyers ask about its category. by=engine (default): mention rate, share of voice, average position, citation share and sentiment per engine, with the change from the previous period. by=question: each buyer question's mention rate and rank.

Input parameters:

- `brand_id` (string): Brand id from list_brands. May be omitted when the workspace tracks a single brand.
- `by` (string): engine (default) or question.
- `engines` (array): Optional: only these engines (e.g. openai, perplexity, anthropic, google_aio). Default: the engines the dashboard headline counts (ChatGPT, Perplexity, Claude, Google AI Overviews, plus any the plan…
- `window_days` (integer): Trailing window in whole UTC days ending today. Default 30.

### `get_competitors` (~154 tokens)

Who does AI recommend instead of me?

The competitors AI answers name for the brand's buyer questions, per engine, with each one's share of voice against the brand and how it changed over the window.

Input parameters:

- `brand_id` (string): Brand id from list_brands. May be omitted when the workspace tracks a single brand.
- `engines` (array): Optional: only these engines (e.g. openai, perplexity, anthropic, google_aio). Default: the engines the dashboard headline counts (ChatGPT, Perplexity, Claude, Google AI Overviews, plus any the plan…
- `window_days` (integer): Trailing window in whole UTC days ending today. Default 30.

### `get_citations` (~170 tokens)

Which sources do AI answers cite?

The websites AI answers cite for the brand's buyer questions, ranked by share of citations and by how many answers cite them, and where the brand's own site ranks.

Input parameters:

- `brand_id` (string): Brand id from list_brands. May be omitted when the workspace tracks a single brand.
- `engines` (array): Optional: only these engines (e.g. openai, perplexity, anthropic, google_aio). Default: the engines the dashboard headline counts (ChatGPT, Perplexity, Claude, Google AI Overviews, plus any the plan…
- `limit` (integer): Max sites per ranking. Default 25.
- `window_days` (integer): Trailing window in whole UTC days ending today. Default 30.

### `get_changes` (~88 tokens)

What changed in my AI visibility?

What moved over the window: the daily mention-rate trend, how much the engines' answers changed, notable changes on competitors' websites, and new pages about the category.

Input parameters:

- `brand_id` (string): Brand id from list_brands. May be omitted when the workspace tracks a single brand.
- `window_days` (integer): Trailing window in whole UTC days ending today. Default 30.

### `list_fix_opportunities` (~88 tokens)

What should I fix to show up in AI answers?

The gaps that keep AI engines from citing or recommending the brand, each with its evidence and the suggested fix. Gives the gap_id mark_fix_shipped needs.

Input parameters:

- `brand_id` (string): Brand id from list_brands. May be omitted when the workspace tracks a single brand.
- `include_closed` (boolean): Also return gaps that were checked and no longer apply. Default false.

### `get_fix_verification` (~121 tokens)

Did my fix work?

Each fix marked shipped for the brand with its mention rate before and after and a verdict: moved (beyond normal answer churn), within_noise, or awaiting_samples. Fixes marked "Not a fix" are left out; auto-detected page changes carry source auto_detected.

Input parameters:

- `brand_id` (string): Brand id from list_brands. May be omitted when the workspace tracks a single brand.
- `fix_event_id` (string): Optional: just this fix.
- `limit` (integer): Most recent fixes to return. Default 20.

### `create_prompt` (~133 tokens)

Track a new buyer question

Adds a buyer question to a topic so it is asked on every engine in the plan from the next run. Counts toward the plan's question limit. Calling again with the same text returns the existing question, never a duplicate.

Input parameters:

- `confirm_new_engines` (boolean): Set true to confirm using an engine this workspace has never used before.
- `target_engines` (array): Optional: limit to these engines. Omit for the plan's engines.
- `text` (string, required): The question, phrased the way a buyer would ask an AI assistant.
- `topic_id` (string, required): Topic id from list_topics.

### `mark_fix_shipped` (~216 tokens)

I shipped a fix

Records that a fix shipped, against a gap_id from list_fix_opportunities or a published content_draft_id, so get_fix_verification can measure whether it moved the brand's mention rate. Calling again with the same fix and description returns the existing record.

Input parameters:

- `acknowledge_unfilled_gaps` (boolean): A content draft that still has [INSERT ...] gaps is refused and the gaps listed. Set true only after the user confirms the shipped page has them filled.
- `brand_id` (string): Brand id from list_brands. May be omitted when the workspace tracks a single brand.
- `content_draft_id` (string): A published content draft (one of gap_id or content_draft_id).
- `description` (string, required): What shipped, in one or two sentences.
- `gap_id` (string): The gap finding the fix addresses (one of gap_id or content_draft_id).
- `shipped_at` (string): When it shipped: RFC 3339 timestamp or YYYY-MM-DD. Default now.

### `add_brand` (~180 tokens)

Check my brand in AI answers

Start measuring a brand: does ChatGPT, Perplexity, Claude or Google AI mention it, and who does AI recommend instead? Give the brand's website (or its app store, Google Maps, YouTube or Instagram link). It reads the site, picks the buyer questions, and starts the first scan across the AI engines. Reading the site takes 1-2 minutes; if it is still running, call again with the same link and it picks up the same run, never a second one. Returns the brand_id; then use get_scan_status.

Input parameters:

- `description` (string): Optional: what the brand sells, in a sentence. Only needed when add_brand says it couldn't read the website.
- `link` (string, required): The brand's website, like acme.com, or its app store, Google Maps, YouTube or Instagram link.

### `get_scan_status` (~82 tokens)

Is my brand's scan done?

Progress of a brand's first scan after add_brand: the stage, how many AI answers are in out of how many expected, per engine, and when it should finish. Once complete, use get_visibility for the results.

Input parameters:

- `brand_id` (string): Brand id from list_brands or add_brand. May be omitted when the workspace tracks a single brand.

### `get_report_link` (~96 tokens)

Get a shareable AI visibility report

A link to the brand's AI visibility report to share with a team or client: how often AI answers mention the brand, which competitors they name instead, and which sources they cite. Returns the newest finished report's own unlisted link. Reports are built automatically after a brand's first scan.

Input parameters:

- `brand_id` (string): Brand id from list_brands or add_brand. May be omitted when the workspace tracks a single brand.

### `see_example` (~139 tokens)

See an example AI visibility card

Shows what Proofsource measures, without signing in: a real visibility card for one example brand (Tesla), from answers collected from ChatGPT, Perplexity, Claude and Google AI Overviews. It shows how often AI answers mention the brand, per engine, which competitors they name instead, and sample answers. Use it when someone asks whether their brand shows up in AI answers and has not signed in. It always shows the example brand; to check their own brand they sign in.

Input parameters:

- `brand` (string): Optional: the brand the person asked about. The example card is shown either way, with a note to sign in to check that brand.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/co-proofsource-proofsource/v1-mcp#diagnostics

## Score history

- 2026-10-23: 86
- 2026-10-22: 86
- 2026-10-21: 85
- 2026-10-20: 85
- 2026-10-19: 84
- 2026-10-18: 84
- 2026-10-17: 83
- 2026-10-16: 83
- 2026-10-15: 82
- 2026-10-14: 82
- 2026-10-13: 81

## Common questions

### What is the Proofsource MCP server?

Proofsource is an MCP server listed in the public MCP registry as co.proofsource/proofsource. AI visibility: which buyer questions name your brand in ChatGPT, Perplexity, Claude, AI Overviews. This page covers its hosted endpoint (https://app.proofsource.co/v1/mcp).

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

Proofsource scores 86 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 Proofsource MCP server expose?

Proofsource exposes 14 tools: list_brands, list_topics, get_visibility, get_competitors, get_citations, and 9 more. Their descriptions and schemas cost roughly 1,765 tokens of context every time the server is loaded.

### Does the Proofsource MCP server require authentication?

Yes. Proofsource asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Proofsource MCP server still maintained?

Proofsource is still listed as active in the MCP registry. We last reached this channel on 23 October 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://app.proofsource.co/v1/mcp
- Repository: https://github.com/lcbasu/proofsource-plugins
- Website: https://proofsource.co/ai-assistants
- Changelog RSS feed: https://verifymcp.io/servers/co-proofsource-proofsource/v1-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/co-proofsource-proofsource/v1-mcp.json
- HTML version of this page: https://verifymcp.io/servers/co-proofsource-proofsource/v1-mcp