Proofsource

Official14 tools

by lcbasu

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

MCP Server: co.proofsource/proofsource

co.proofsource/proofsource is an MCP server focused on “AI visibility.” It describes which buyer questions mention a brand across major AI services, including ChatGPT, Perplexity, Claude, and AI Overviews.

🛠️ Key Features

Brand-related visibility in AI platforms
Question-level matching for buyer queries
Coverage includes ChatGPT, Perplexity, Claude, and AI Overviews

🚀 Use Cases

Identify which buyer questions name a specific brand in AI search/chat
Assess how brand mentions appear across multiple AI assistants
Compare question coverage for AI Overviews versus conversational AI tools

⚡ Developer Benefits

Provides a targeted capability centered on brand mention visibility
Aligns outputs to buyer-question context across supported platforms

⚠️ Limitations

Available information includes name and description only; no tool count, readme excerpt, or additional capabilities are provided

Topics

aeoai-visibilitybrand-monitoringchatgptclaudegenerative-engine-optimizationgeomcpmcp-serverperplexityremote-mcpseo

Captured live from the server via tools/list.

list_brands

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

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.

Parameters1

brand_id

string

optional

Brand id from list_brands. May be omitted when the workspace tracks a single brand.

Raw schema

{
  "type": "object",
  "properties": {
    "brand_id": {
      "description": "Brand id from list_brands. May be omitted when the workspace tracks a single brand.",
      "type": "string"
    }
  },
  "additionalProperties": false
}

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 the previous period. by=question: each buyer question's mention rate and rank.

Parameters4

brand_id	string	optional	Brand id from list_brands. May be omitted when the workspace tracks a single brand.
by	string	optional	engine (default) or question.
engines	array	optional	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 adds); the reply's counted_engines names them.
window_days	integer	optional	Trailing window in whole UTC days ending today. Default 30.

Raw schema

{
  "type": "object",
  "properties": {
    "brand_id": {
      "description": "Brand id from list_brands. May be omitted when the workspace tracks a single brand.",
      "type": "string"
    },
    "by": {
      "description": "engine (default) or question.",
      "enum": [
        "engine",
        "question"
      ],
      "type": "string"
    },
    "engines": {
      "description": "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 adds); the reply's counted_engines names them.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "window_days": {
      "description": "Trailing window in whole UTC days ending today. Default 30.",
      "maximum": 90,
      "minimum": 1,
      "type": "integer"
    }
  },
  "additionalProperties": false
}

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.

Parameters3

brand_id	string	optional	Brand id from list_brands. May be omitted when the workspace tracks a single brand.
engines	array	optional	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 adds); the reply's counted_engines names them.
window_days	integer	optional	Trailing window in whole UTC days ending today. Default 30.

Raw schema

{
  "type": "object",
  "properties": {
    "brand_id": {
      "description": "Brand id from list_brands. May be omitted when the workspace tracks a single brand.",
      "type": "string"
    },
    "engines": {
      "description": "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 adds); the reply's counted_engines names them.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "window_days": {
      "description": "Trailing window in whole UTC days ending today. Default 30.",
      "maximum": 90,
      "minimum": 1,
      "type": "integer"
    }
  },
  "additionalProperties": false
}

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.

Parameters4

brand_id	string	optional	Brand id from list_brands. May be omitted when the workspace tracks a single brand.
engines	array	optional	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 adds); the reply's counted_engines names them.
limit	integer	optional	Max sites per ranking. Default 25.
window_days	integer	optional	Trailing window in whole UTC days ending today. Default 30.

Raw schema

{
  "type": "object",
  "properties": {
    "brand_id": {
      "description": "Brand id from list_brands. May be omitted when the workspace tracks a single brand.",
      "type": "string"
    },
    "engines": {
      "description": "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 adds); the reply's counted_engines names them.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "limit": {
      "description": "Max sites per ranking. Default 25.",
      "maximum": 100,
      "minimum": 1,
      "type": "integer"
    },
    "window_days": {
      "description": "Trailing window in whole UTC days ending today. Default 30.",
      "maximum": 90,
      "minimum": 1,
      "type": "integer"
    }
  },
  "additionalProperties": false
}

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.

Parameters2

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

Raw schema

{
  "type": "object",
  "properties": {
    "brand_id": {
      "description": "Brand id from list_brands. May be omitted when the workspace tracks a single brand.",
      "type": "string"
    },
    "window_days": {
      "description": "Trailing window in whole UTC days ending today. Default 30.",
      "maximum": 90,
      "minimum": 1,
      "type": "integer"
    }
  },
  "additionalProperties": false
}

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.

Parameters2

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

Raw schema

{
  "type": "object",
  "properties": {
    "brand_id": {
      "description": "Brand id from list_brands. May be omitted when the workspace tracks a single brand.",
      "type": "string"
    },
    "include_closed": {
      "description": "Also return gaps that were checked and no longer apply. Default false.",
      "type": "boolean"
    }
  },
  "additionalProperties": false
}

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 source auto_detected.

Parameters3

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

Raw schema

{
  "type": "object",
  "properties": {
    "brand_id": {
      "description": "Brand id from list_brands. May be omitted when the workspace tracks a single brand.",
      "type": "string"
    },
    "fix_event_id": {
      "description": "Optional: just this fix.",
      "type": "string"
    },
    "limit": {
      "description": "Most recent fixes to return. Default 20.",
      "maximum": 50,
      "minimum": 1,
      "type": "integer"
    }
  },
  "additionalProperties": false
}

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.

Parameters4

confirm_new_engines	boolean	optional	Set true to confirm using an engine this workspace has never used before.
target_engines	array	optional	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.

Raw schema

{
  "type": "object",
  "properties": {
    "confirm_new_engines": {
      "description": "Set true to confirm using an engine this workspace has never used before.",
      "type": "boolean"
    },
    "target_engines": {
      "description": "Optional: limit to these engines. Omit for the plan's engines.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "text": {
      "description": "The question, phrased the way a buyer would ask an AI assistant.",
      "maxLength": 500,
      "type": "string"
    },
    "topic_id": {
      "description": "Topic id from list_topics.",
      "type": "string"
    }
  },
  "required": [
    "topic_id",
    "text"
  ],
  "additionalProperties": false
}

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 returns the existing record.

Parameters5

brand_id	string	optional	Brand id from list_brands. May be omitted when the workspace tracks a single brand.
content_draft_id	string	optional	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	optional	The gap finding the fix addresses (one of gap_id or content_draft_id).
shipped_at	string	optional	When it shipped: RFC 3339 timestamp or YYYY-MM-DD. Default now.

Raw schema

{
  "type": "object",
  "properties": {
    "brand_id": {
      "description": "Brand id from list_brands. May be omitted when the workspace tracks a single brand.",
      "type": "string"
    },
    "content_draft_id": {
      "description": "A published content draft (one of gap_id or content_draft_id).",
      "type": "string"
    },
    "description": {
      "description": "What shipped, in one or two sentences.",
      "maxLength": 1000,
      "type": "string"
    },
    "gap_id": {
      "description": "The gap finding the fix addresses (one of gap_id or content_draft_id).",
      "type": "string"
    },
    "shipped_at": {
      "description": "When it shipped: RFC 3339 timestamp or YYYY-MM-DD. Default now.",
      "type": "string"
    }
  },
  "required": [
    "description"
  ],
  "additionalProperties": false
}

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 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.

Parameters2

description	string	optional	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.

Raw schema

{
  "type": "object",
  "properties": {
    "description": {
      "description": "Optional: what the brand sells, in a sentence. Only needed when add_brand says it couldn't read the website.",
      "maxLength": 1000,
      "type": "string"
    },
    "link": {
      "description": "The brand's website, like acme.com, or its app store, Google Maps, YouTube or Instagram link.",
      "maxLength": 2048,
      "type": "string"
    }
  },
  "required": [
    "link"
  ],
  "additionalProperties": false
}

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.

Parameters1

brand_id

string

optional

Brand id from list_brands or add_brand. May be omitted when the workspace tracks a single brand.

Raw schema

{
  "type": "object",
  "properties": {
    "brand_id": {
      "description": "Brand id from list_brands or add_brand. May be omitted when the workspace tracks a single brand.",
      "type": "string"
    }
  },
  "additionalProperties": false
}

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. Reports are built automatically after a brand's first scan.

Parameters1

brand_id

string

optional

Brand id from list_brands or add_brand. May be omitted when the workspace tracks a single brand.

Raw schema

{
  "type": "object",
  "properties": {
    "brand_id": {
      "description": "Brand id from list_brands or add_brand. May be omitted when the workspace tracks a single brand.",
      "type": "string"
    }
  },
  "additionalProperties": false
}

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 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.

Parameters1

brand

string

optional

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

Raw schema

{
  "type": "object",
  "properties": {
    "brand": {
      "description": "Optional: the brand the person asked about. The example card is shown either way, with a note to sign in to check that brand.",
      "maxLength": 200,
      "type": "string"
    }
  },
  "additionalProperties": false
}

README.md2 KBView on GitHub

Proofsource for Claude

Proofsource measures how AI assistants talk about your brand. It asks ChatGPT, Perplexity, Claude and Google AI Overviews the questions your buyers ask, and shows how often you are mentioned, which competitors are recommended instead, and which sources the answers cite.

This plugin connects Claude to your Proofsource workspace and adds two skills:

ai-visibility-audit: a sourced summary of your AI visibility, competitors, cited sources and recent changes.
fix-plan: a prioritized plan from your open gaps, plus tracking new buyer questions and shipped fixes (always asks first).

Install

code

/plugin marketplace add lcbasu/proofsource-plugins
/plugin install proofsource@proofsource-plugins

Then run /mcp, pick proofsource and sign in with your Proofsource account. Try: "Is my brand mentioned in ChatGPT answers?"

Connect without the plugin

The connector URL is https://app.proofsource.co/v1/mcp (OAuth 2.1; you sign in with your Proofsource email and a one-time code).

Claude (web or Desktop): Settings → Connectors → Add custom connector → paste the URL → Connect.
ChatGPT: Settings → Apps & Connectors → Advanced → turn on Developer mode → Create → paste the URL, choose OAuth.
Claude Code: claude mcp add --scope user --transport http proofsource https://app.proofsource.co/v1/mcp, then /mcp to sign in.
Cursor, VS Code, Cline, Windsurf and other MCP clients: add a remote (Streamable HTTP) server with the URL above; see llms-install.md.

Also listed in the official MCP Registry as co.proofsource/proofsource (server.json).

Full guide: https://proofsource.co/docs/chatgpt-and-claude

Tools

Read: list_brands, list_topics, get_visibility, get_competitors, get_citations, get_changes, list_fix_opportunities, get_fix_verification, get_scan_status, get_report_link, see_example (works without signing in). Write (your workspace only, by your plan and role): add_brand, create_prompt, mark_fix_shipped.

New accounts with a work email get two free scans. Personal email addresses get an account without scans.

Support: https://proofsource.co/contact · Privacy: https://proofsource.co/privacy · Terms: https://proofsource.co/terms

Install

Tools (14)

list_brandslist_topicsget_visibilityget_competitorsget_citationsget_changeslist_fix_opportunitiesget_fix_verification

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://app.proofsource.co/v1/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "proofsource": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://app.proofsource.co/v1/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

MCP Server: co.proofsource/proofsource

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

list_brands

list_topics

get_visibility

get_competitors

get_citations

get_changes

list_fix_opportunities

get_fix_verification

create_prompt

mark_fix_shipped

add_brand

get_scan_status

get_report_link

see_example

Proofsource for Claude

Install

Connect without the plugin

Tools

Install

Remote endpoint

Related servers