Lotus — AI Citation Intelligence is an MCP server with 16 tools an agent can call, among them activate_artifact, analyze_geo, approve_artifact. It answers at https://lotus.clicon.app/mcp/ over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Measure how AI assistants cite your brand. Returns measured data and ready-to-apply fixes.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
activate_artifact | Activate an artifact by its ID. The artifact must belong to the authenticated client's domain. Activation makes the artifact live — only one version of a given type can be active at a time. Use when an agent needs to deploy an approved arti Inputs: artifact_id |
analyze_geo | Analyze a domain's visibility across AI-generated answers. Without an API key: returns a limited preview (1/day per IP, 3/week). With a valid API key: returns the full analysis including measured metrics, revenue-at-risk estimates and scena Inputs: domain |
approve_artifact | Approve an artifact by its ID. The artifact must belong to the authenticated client's domain. Approved artifacts are ready for activation but are not yet live on the site. Use when an agent has reviewed a generated artifact and wants to mar Inputs: artifact_id |
generate_share_link | Generate a public report link for the authenticated client and persist it. Returns {report_url, slug}. Use when an agent needs to create a shareable report covering the client's full visibility status: crawler activity, revenue at risk, com |
get_artifact | Return the most recent artifact (llms_txt or json_ld) for the authenticated client: content, version, generated_at and status. Use when an agent needs to read the generated llms.txt or JSON-LD. artifact_type must be "llms_txt" or "json_ld". Inputs: artifact_type |
get_bleed_model | Return the traffic erosion model for the authenticated client: cascading metrics with their *_source provenance labels, plus the resulting revenue-at-risk calculation. Use when an agent needs to assess the economic impact of losing traffic |
get_bot_activity | Return AI crawler activity for the authenticated client's domain: total hits, breakdown per bot, most recent hits and last-seen per bot. Use when an agent needs to assess how frequently AI crawlers visit a site over the last N days. Inputs: days |
get_citation_verdict | Return the most recent citation score for the authenticated client, along with the measurements from that same week (safe fields only). Raw data — no healthy/critical classification applied. Use when an agent needs to audit how generative e |
get_competitor_actions | Return pending and completed competitor actions for a domain. Requires a valid API key (pro, growth or agency). Inputs: domain |
get_quick_win_code | Generate ready-to-install code for a quick win, identified by its hash. Only available for structured_data quick wins. Requires a valid API key. Inputs: hash, domain |
get_quick_wins | Return pending and applied quick wins for a domain. Requires a valid API key (pro, growth or agency). Inputs: domain |
get_report_data | Return the full report payload for a share link slug owned by the authenticated client. Returns the report even if the share link has expired. Use when an agent needs to read a report it previously generated with generate_share_link, withou Inputs: slug |
list_artifacts | Return artifacts (llms_txt, json_ld, defense_nodes) for the authenticated client, without their content payload. Optionally filter by exact status (e.g. "pending_review", "approved"). Use status="" to return all statuses. limit caps the num Inputs: status, limit |
mark_applied | Verify-before-mark: checks that the expected schema is actually present in the live DOM of the site before marking the quick win as applied. Only marks it if the expected @type is found among the schemas detected on the domain (best-effort, Inputs: hash, domain |
regenerate_artifacts | Regenerate the GEO artifacts (llms_txt, json_ld and supporting schema nodes) for the authenticated client. Respects a 6h cooldown and the daily generation budget. Use when an agent needs to force regeneration after changes to the site or to |
verify_installation | Check live whether llms.txt and JSON-LD are correctly installed on the authenticated client's domain. Returns an overall status (fully_deployed / partially_deployed / not_deployed) plus the detailed result for each artifact. Use when an age |
Every block below points at https://lotus.clicon.app/mcp/. Pick your client and copy.
claude mcp add --transport http lotus-ai-citation-intelligence https://lotus.clicon.app/mcp/
{
"mcpServers": {
"lotus-ai-citation-intelligence": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://lotus.clicon.app/mcp/"]
}
}
}{
"mcpServers": {
"lotus-ai-citation-intelligence": {
"url": "https://lotus.clicon.app/mcp/"
}
}
}{
"servers": {
"lotus-ai-citation-intelligence": {
"type": "http",
"url": "https://lotus.clicon.app/mcp/"
}
}
}{
"context_servers": {
"lotus-ai-citation-intelligence": {
"url": "https://lotus.clicon.app/mcp/"
}
}
}{
"mcpServers": {
"lotus-ai-citation-intelligence": {
"serverUrl": "https://lotus.clicon.app/mcp/"
}
}
}{
"mcpServers": {
"lotus-ai-citation-intelligence": {
"url": "https://lotus.clicon.app/mcp/"
}
}
}name: Lotus — AI Citation Intelligence
version: 0.0.1
schema: v1
mcpServers:
- name: Lotus — AI Citation Intelligence
type: streamable-http
url: https://lotus.clicon.app/mcp/{
"mcpServers": {
"lotus-ai-citation-intelligence": {
"httpUrl": "https://lotus.clicon.app/mcp/"
}
}
}{
"mcpServers": {
"lotus-ai-citation-intelligence": {
"type": "http",
"url": "https://lotus.clicon.app/mcp/"
}
}
}{
"mcpServers": {
"lotus-ai-citation-intelligence": {
"url": "https://lotus.clicon.app/mcp/"
}
}
}goose://extension?url=https%3A%2F%2Flotus.clicon.app%2Fmcp%2F&type=streamable_http&id=lotus-ai-citation-intelligence&name=Lotus%20%E2%80%94%20AI%20Citation%20Intelligence
It answered our last check on 17 October 2026 in 183 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by clicon.app and served from lotus.clicon.app, the vendor's own domain: https://lotus.clicon.app/mcp/.
16, as returned by the server's own tools/list on 9 September 2026: activate_artifact, analyze_geo, approve_artifact, generate_share_link, get_artifact, get_bleed_model, get_bot_activity, get_citation_verdict, and 8 more.
It answered our last check on 17 October 2026 in 183 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://lotus.clicon.app/mcp/. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: app.clicon. Endpoint host: lotus.clicon.app. ARD identifier: urn:air:app.clicon:mcp:lotus.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.