mcp server
Lotus — AI Citation Intelligence
Measure how AI assistants cite your brand. Returns measured data and ready-to-apply fixes.
Description as published by the maintainer. Source
- version 1.27.0
- active
active — Most recent push to the repository was 2026-07-28.
What this server can do
16 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
activate_artifact(artifact_id)- 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 artifact to production. Required: artifact_id.
analyze_geo(domain)- 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 scenario simulations. Required: domain.
approve_artifact(artifact_id)- 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 mark it as ready for deployment. Required: 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, competitive intelligence and competitors.
get_artifact(artifact_type)- 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". Required: 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 to AI-generated answers.
get_bot_activity(days)- 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.
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 engines cite a client: citation rate, average position, sentiment, competitors mentioned and entity fidelity.
get_competitor_actions(domain)- Return pending and completed competitor actions for a domain. Requires a valid API key (pro, growth or agency). Required: domain.
get_quick_win_code(hash, domain)- 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. Required: hash.
get_quick_wins(domain)- Return pending and applied quick wins for a domain. Requires a valid API key (pro, growth or agency). Required: domain.
get_report_data(slug)- 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, without opening the public URL in a browser. Required: slug.
list_artifacts(limit, status)- 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 number returned (default 20, max 100); the "total" field always reflects the real unfiltered count for the domain. Use when an agent needs to discover which artifact IDs are available before approving or activating a specific one.
mark_applied(hash, domain)- 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, fails safe). Requires a valid API key. Required: hash.
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 the competitor/advantage configuration.
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 agent needs to confirm that GEO artifacts are serving correctly on the client's site.
Last successful function declaration observed on . Source: https://lotus.clicon.app/mcp/. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://lotus.clicon.app/mcp/.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 0 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-07-28 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 0 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 1.27.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-30 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | MIT | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-07-30 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 16 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | lotus.clicon.app | |
| mcp endpoint status | ok | The server listed 16 functions when asked. | as of probe | lotus.clicon.app |
Where to get it
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json