
promptmentions
com.promptmentions/promptmentions
Read-only AI visibility data: brand mentions, cited sources and answers across AI engines.
Documentation
PromptMentions MCP server
Connect an AI assistant to your PromptMentions AI-visibility data.
PromptMentions tracks what ChatGPT, Claude, Gemini, Grok, Meta AI, Perplexity and Google's AI Overviews and AI Mode say about a brand. It asks your buyers' questions on a schedule and keeps every answer with the pages it cited. This MCP server gives an assistant read-only access to one workspace's results.
This repository holds connection instructions and directory metadata only. The server is hosted by PromptMentions; there is nothing to install or run.
Connect
| Server URL | https://promptmentions.com/api/mcp |
| Transport | Streamable HTTP |
| Sign-in | OAuth 2.1, with dynamic client registration and PKCE. An API key also works. |
| Access | Read-only: it cannot change anything, run checks or spend your allowance |
With OAuth (recommended)
Add the server URL to any MCP client that supports remote servers, such as Claude, Claude Code, Cursor or VS Code. The client opens a PromptMentions sign-in page. You choose the workspace, and the clients it may read, then press Allow. To disconnect the app, go to Settings › API & MCP › Connected apps.
Claude Code:
claude mcp add --transport http promptmentions https://promptmentions.com/api/mcp
With an API key
Create a key in Settings › API & MCP, then send it as a header:
{
"mcpServers": {
"promptmentions": {
"type": "http",
"url": "https://promptmentions.com/api/mcp",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}
Without a key or a sign-in, only initialize, ping and tools/list answer, so a client can see what the server
offers before you connect.
Tools
All tools are read-only.
| Tool | What it returns |
|---|---|
get_workspace | The workspace, the connection's permissions and the client projects it can read |
list_projects | Client projects with their brand, aliases, tracked competitors and locale |
get_project | One client project |
list_prompt_sets | Prompt sets for a client, with every saved revision, its locale and prompts |
list_runs | Monitoring runs for a client, newest first, with sample counts |
get_run_metrics | One run's labelled metrics (mention rate, citation rates, mention share) and competitor share of voice |
list_samples | Every answer in a run: provider, model, prompt, locale, time, status, mentions and citations |
get_citations | Domains and pages cited in a run's answers, classified, with citation gaps |
get_sample_evidence | The saved evidence of one answer: answer text, citations and extraction summary |
list_opportunities | Tasks and opportunities for a client, with their source evidence |
get_looker_rows | Flat rows for Looker Studio and spreadsheets |
get_report | A client report for a date window: runs with labelled metrics, opportunity changes and caveats |
Each figure is labelled with the AI engine, the date and the number of answers behind it. Failed answers are left out.
Links
- Product and free trial: https://promptmentions.com
- Developer docs: https://promptmentions.com/developers
- Privacy: https://promptmentions.com/privacy
- Terms: https://promptmentions.com/terms
- Support: support@promptmentions.com
- Official MCP Registry:
com.promptmentions/promptmentions
No installation packages available.