Skip to content
Back to search

promptmentions-plugins

MarketplaceWorks with Claude CodeGitHub

Connect an AI assistant to PromptMentions AI-visibility data (hosted MCP server, OAuth, read-only)

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/jimbob1414--promptmentions-mcp/badge.svg)](/listings/jimbob1414--promptmentions-mcp)

HTML

<a href="/listings/jimbob1414--promptmentions-mcp"><img src="/api/listings/jimbob1414--promptmentions-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 14 lines
  1. {
  2. "name": "promptmentions-plugins",
  3. "owner": {
  4. "name": "PromptMentions",
  5. "email": "support@promptmentions.com"
  6. },
  7. "plugins": [
  8. {
  9. "name": "promptmentions",
  10. "source": "./",
  11. "description": "Read what ChatGPT, Perplexity, Claude and Google AI say about your brand or your clients, with saved answers and cited sources."
  12. }
  13. ]
  14. }
README.md · README · 80 lines
  1. # PromptMentions MCP server
  2. Connect an AI assistant to your [PromptMentions](https://promptmentions.com) AI-visibility data.
  3. PromptMentions tracks what ChatGPT, Claude, Gemini, Grok, Meta AI, Perplexity and Google's AI Overviews and AI Mode
  4. say about a brand. It asks your buyers' questions on a schedule and keeps every answer with the pages it cited. This
  5. MCP server gives an assistant **read-only** access to one workspace's results.
  6. This repository holds connection instructions and directory metadata only. The server is hosted by PromptMentions;
  7. there is nothing to install or run.
  8. ## Connect
  9. | | |
  10. |---|---|
  11. | Server URL | `https://promptmentions.com/api/mcp` |
  12. | Transport | Streamable HTTP |
  13. | Sign-in | OAuth 2.1, with dynamic client registration and PKCE. An API key also works. |
  14. | Access | Read-only: it cannot change anything, run checks or spend your allowance |
  15. ### With OAuth (recommended)
  16. Add the server URL to any MCP client that supports remote servers, such as Claude, Claude Code, Cursor or VS Code.
  17. The client opens a PromptMentions sign-in page. You choose the workspace, and the clients it may read, then press
  18. **Allow**. To disconnect the app, go to **Settings › API & MCP › Connected apps**.
  19. Claude Code:
  20. ```bash
  21. claude mcp add --transport http promptmentions https://promptmentions.com/api/mcp
  22. ```
  23. ### With an API key
  24. Create a key in **Settings › API & MCP**, then send it as a header:
  25. ```json
  26. {
  27. "mcpServers": {
  28. "promptmentions": {
  29. "type": "http",
  30. "url": "https://promptmentions.com/api/mcp",
  31. "headers": { "Authorization": "Bearer YOUR_API_KEY" }
  32. }
  33. }
  34. }
  35. ```
  36. Without a key or a sign-in, only `initialize`, `ping` and `tools/list` answer, so a client can see what the server
  37. offers before you connect.
  38. ## Tools
  39. All tools are read-only.
  40. | Tool | What it returns |
  41. |---|---|
  42. | `get_workspace` | The workspace, the connection's permissions and the client projects it can read |
  43. | `list_projects` | Client projects with their brand, aliases, tracked competitors and locale |
  44. | `get_project` | One client project |
  45. | `list_prompt_sets` | Prompt sets for a client, with every saved revision, its locale and prompts |
  46. | `list_runs` | Monitoring runs for a client, newest first, with sample counts |
  47. | `get_run_metrics` | One run's labelled metrics (mention rate, citation rates, mention share) and competitor share of voice |
  48. | `list_samples` | Every answer in a run: provider, model, prompt, locale, time, status, mentions and citations |
  49. | `get_citations` | Domains and pages cited in a run's answers, classified, with citation gaps |
  50. | `get_sample_evidence` | The saved evidence of one answer: answer text, citations and extraction summary |
  51. | `list_opportunities` | Tasks and opportunities for a client, with their source evidence |
  52. | `get_looker_rows` | Flat rows for Looker Studio and spreadsheets |
  53. | `get_report` | A client report for a date window: runs with labelled metrics, opportunity changes and caveats |
  54. Each figure is labelled with the AI engine, the date and the number of answers behind it. Failed answers are left out.
  55. ## Links
  56. - Product and free trial: https://promptmentions.com
  57. - Developer docs: https://promptmentions.com/developers
  58. - Privacy: https://promptmentions.com/privacy
  59. - Terms: https://promptmentions.com/terms
  60. - Support: support@promptmentions.com
  61. - Official MCP Registry: `com.promptmentions/promptmentions`

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.