# Proofsource MCP server

Source: https://glimind.com/server/mcp-registry%2Fco.proofsource%2Fproofsource
Registry id: `mcp-registry/co.proofsource/proofsource`
Status: live (checked 2026-10-26T20:33:25.731Z)

## Measurements (30 days)

- Uptime: 99.86%
- Checks: 2880
- Outages (90 days): 2

## Install

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

Claude Code:

```sh
claude mcp add --transport http proofsource-mcp-server https://app.proofsource.co/v1/mcp
```

## Tools (14)

- `add_brand`: 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
- `create_prompt`: 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 s
- `get_changes`: 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 t
- `get_citations`: 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 ran
- `get_competitors`: 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
- `get_fix_verification`: 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_sample
- `get_report_link`: 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 whic
- `get_scan_status`: 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 co
- `get_visibility`: 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, ave
- `list_brands`: The brands this workspace tracks in AI answers, with ids and websites. Call first; every other tool takes a brand_id.
- `list_fix_opportunities`: 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.
- `list_topics`: The topics and buyer questions this workspace asks ChatGPT, Perplexity, Claude and Google AI for a brand. Gives the topic_id create_prompt needs.
- `mark_fix_shipped`: 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 t
- `see_example`: Shows what Proofsource measures, without signing in: a real visibility card for one example brand (Tesla), from answers collected from ChatGPT, Perplexity, Clau

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.