Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@coven-mcp Run a COVEN scan on example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP tools for website auditing and AI visibility measurement, scored against the COVEN v2.0.1 methodology.
Measurement, not middleware.
https://api.covenai.io/mcpRelated MCP server: aeo-mcp
Scans use the COVEN v2.0.1 rubric. Five dimensions are scored and combined into an overall score; one further signal is surfaced separately for research, with no weight on the score.
Dimension | Weight | Field |
Structure | 25% |
|
Citability | 25% |
|
Discoverability | 15% |
|
Agent Interface | 20% |
|
Transactability | 15% |
|
Agent Correlation (research signal, not scored) | 0% |
|
Scan responses include methodology_version: "2.0.1", the per-dimension fields
above, and an overall_score.
Tool | Description | Auth |
| v2.0.1 site scan across the five scored dimensions, with Agent Correlation reported as a research signal | Optional |
| Score a site's readiness for agent traffic — 0–85, A–F grade | Optional |
| Content citability analysis under the v2.0.1 Citability dimension | Required |
| Generate a ready-to-deploy | Optional |
| Full agent-readiness audit with deployable content patches | Optional |
| List available audit reports and prices | Optional |
| Order a full AI audit report | Required (Pro+) |
| Poll audit delivery status | Required |
Add to your claude_desktop_config.json:
{
"mcpServers": {
"coven-ai": {
"url": "https://api.covenai.io/mcp",
"headers": {
"Authorization": "Bearer YOUR_COVEN_API_KEY"
}
}
}
}Add to .cursor/mcp.json:
{
"mcpServers": {
"coven-ai": {
"url": "https://api.covenai.io/mcp",
"headers": {
"Authorization": "Bearer YOUR_COVEN_API_KEY"
}
}
}
}Get an API key at covenai.io/developers.
check_geo_score("brightlocal.com")
→ Grade D, 46/85 — three priority fixes returned
geo_optimise("yoursite.com")
→ Four deployable patches: llms.txt, FAQ HTML block, schema JSON-LD, passage rewrite
generate_llmstxt("yoursite.com")
→ Complete /llms.txt file, ready to deploy
scan_website("example.com")
→ v2.0.1 report: Structure 72, Citability 64, Discoverability 58,
Agent Interface 49, Transactability 41, Agent Correlation 0.31 (research signal)Most tools work without authentication. Audit orders and the monitoring API require a COVEN API key.
Get one at covenai.io/developers.
Homepage: covenai.io
Docs: covenai.io/developers
Free tools: covenai.io/llms-generator
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
SEO MCP server: crawl your site, find AI-visibility gaps, and ship the fix from your coding agent.
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/covenai-dev/coven-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server