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
Markdown
[](/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
- {
- "name": "promptmentions-plugins",
- "owner": {
- "name": "PromptMentions",
- "email": "support@promptmentions.com"
- },
- "plugins": [
- {
- "name": "promptmentions",
- "source": "./",
- "description": "Read what ChatGPT, Perplexity, Claude and Google AI say about your brand or your clients, with saved answers and cited sources."
- }
- ]
- }
README.md · README · 80 lines
- # PromptMentions MCP server
- Connect an AI assistant to your [PromptMentions](https://promptmentions.com) 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:
- ```bash
- 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:
- ```json
- {
- "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`
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.