
Ai Visibility
io.github.sharozdawaPublished by GitHub account sharozdawav1.0.0Updated Oct 24, 2026
Track brand visibility across ChatGPT, Perplexity, Claude, and Gemini.
Overview
A local MCP server that reports how AI platforms such as ChatGPT, Perplexity, Claude and Gemini mention a brand, with scores, sentiment and competitor data.
- What you can do
- Check a brand's visibility across the four AI platforms, with mention rates, positions, sentiment and competitor analysis, or test a single query on one platform for mention status, position, context and sentiment. Calculate an overall 0-100 visibility score with tier rating, per-platform breakdown and improvement recommendations. Compare two to ten brands side by side with ranked results and per-platform scores. List the supported platforms and how each sources brand information.
- When to use it
- Useful for marketers or brand owners who want a quick, repeatable read on how AI assistants describe their brand versus competitors, and prioritized suggestions for improving that presence.
- Requirements
- Runs locally over stdio, typically launched with npx from the npm package ai-visibility-mcp, so Node.js is needed. No accounts, API keys or environment variables are declared. The optional self-hosted web dashboard needs a database connection string.
Installation
In SourceWeft
- Open Ai Visibility in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
[npm version] [GitHub stars] [License] [PRs Welcome] [AI Visibility MCP server]
Know exactly how AI platforms talk about your brand.
Track mentions, sentiment, position, and competitors across the AI platforms that shape buying decisions.
Features
- Multi-Platform Tracking — Monitor visibility across ChatGPT, Perplexity, Claude, and Gemini simultaneously
- Visibility Scoring — Get a 0-100 score with tier ratings (Excellent / Good / Moderate / Low / Very Low)
- Sentiment Analysis — Understand whether AI platforms describe your brand positively, neutrally, or negatively
- Competitor Intelligence — See which competitors appear alongside your brand in AI responses
- Brand Comparison — Compare up to 10 brands side by side with per-platform breakdowns
- Actionable Recommendations — Get prioritized steps to improve your AI visibility
- MCP Server — Works with Claude Desktop, Cursor, and any MCP-compatible client
- Consistent Results — Seeded randomness ensures reproducible results for the same brand
MCP Server Installation
Claude Desktop
Add to your claude_desktop_config.json:
Cursor
Add to your Cursor MCP settings (.cursor/mcp.json):
npx (standalone)
MCP Tools
How Scoring Works
The visibility score (0-100) is calculated from three components:
Score Tiers:
- 80-100 Excellent — Strong presence across platforms
- 60-79 Good — Visible but room to improve
- 40-59 Moderate — Appears in some responses
- 20-39 Low — Limited visibility
- 0-19 Very Low — Rarely mentioned
Self-Hosting
Clone the repo and build the MCP server:
Run the MCP server directly:
Or point your MCP client to the local build:
Run the Web Dashboard
The project includes a Next.js dashboard for visual tracking:
Platforms Tracked
Why AI Visibility vs Paid Alternatives
More Open Source SEO Tools
License
MIT
Built by Sharoz Dawa
[GitHub]
Source: README.md at commit ba0253d
Tools
0Version history
1- v1.0.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts