About Proofsource
Proofsource connects Claude to a workspace for measuring how AI assistants represent a brand in buyer-facing answers. It provides sourced visibility audits and a prioritized fix plan, with tracking for questions and shipped changes.
Key features
- 01Measure brand mentions in AI answers
- 02Compare competitor recommendations
- 03Inspect cited sources and recent changes
- 04Generate sourced visibility audits
- 05Prioritize gaps and track fixes
Use cases
- 01Checking whether buyer prompts mention a brand
- 02Reviewing competitors recommended by AI assistants
- 03Planning responses to visibility gaps
- 04Tracking shipped fixes and new buyer questions
MCP support
The remote MCP server connects clients to a Proofsource workspace. It offers read tools for brand visibility data and workspace-scoped write tools for adding brands, creating prompts, and marking fixes as shipped.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://app.proofsource.co/v1/mcpclaude mcp add --transport http co-proofsource-proofsource https://app.proofsource.co/v1/mcp{"mcpServers":{"co-proofsource-proofsource":{"type":"http","url":"https://app.proofsource.co/v1/mcp"}}}Open in Cursor{"servers":{"co-proofsource-proofsource":{"type":"http","url":"https://app.proofsource.co/v1/mcp"}}}Open in VS Code{"mcpServers":{"co-proofsource-proofsource":{"type":"http","url":"https://app.proofsource.co/v1/mcp"}}}{"mcpServers":{"co-proofsource-proofsource":{"serverUrl":"https://app.proofsource.co/v1/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
14This tool takes no parameters.
Details
From the project READMEProofsource 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
/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/mcpto 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
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.