Proofsource MCP server

Which servers in the official MCP registry are Proofsource's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-13

← Back to Proofsource

Whose server it is

Registry nameco.proofsource/proofsourceverified in the MCP registry

The registry name sits under proofsource.co. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-13

Stateanswerschecked 2026-10-13
Tools14
Server calls itselfproofsource
Server version1.0.0
Protocol version2025-06-18

On 2026-10-13 the server answered initialize and tools/list without a sign-in. First answer in 131 ms.

Tools it offers14 tools · read 2026-10-13

list_brands
The brands this Proofsource workspace tracks in AI answers, with ids and websites. Call first; every other tool takes a brand_id.
list_topics
The topics and buyer questions Proofsource asks ChatGPT, Perplexity, Claude and Google AI for a brand. Gives the topic_id create_prompt needs.
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, average position, citation share and sentiment per engine, with the change from…
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_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 ranks.
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 the category.
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.
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_samples. Fixes marked "Not a fix" are left out; auto-detected page changes carry…
create_prompt
Adds a buyer question to a topic so Proofsource asks it 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.
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 the brand's mention rate. Calling again with the same fix and description…
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, Google Maps, YouTube or Instagram link). Proofsource reads the site, picks…
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 complete, use get_visibility for the results.
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 which sources they cite. Returns the newest finished report's own unlisted link…
see_example
Shows what Proofsource measures, without signing in: a real visibility card for one example brand (Tesla), from answers Proofsource collected from ChatGPT, Perplexity, Claude and Google AI Overviews. It shows how often AI answers mention…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

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

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.