Skip to content
Agentmart
Submit a tool

LightSpot

Audit a website for SEO and AI search visibility (ChatGPT, Perplexity, Gemini) and read the fixes.

Connector by nmarijane · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/nmarijane-lightspot-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Audit a website for SEO and AI search visibility (ChatGPT, Perplexity, Gemini) and read the fixes.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
8 read · 2 write · 1 delete
Secrets
1 (API keys, tokens or passwords)
Install scripts
Not scanned yet
Runs as
Node.js package

Tools by what they do 11

Read from the source code; the running server may list different tools.

Read 8 · Look things up without changing anything.

  • get_audit
  • get_audit_status
  • get_competitors
  • get_editorial_calendar
  • get_expert_report
  • get_site
  • list_site_audits
  • list_sites

Write 2 · Create, change, send or run things.

  • audit_and_wait
  • run_audit

Delete 1 · Delete, drop, revoke or wipe things.

  • create_editorial_calendar

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • LIGHTSPOT_API_KEY

Other settings (environment variables or headers).

  • LIGHTSPOT_BASE_URL

Tools (11)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • audit_and_waitAudit a URL and wait for the result

    Runs a LightSpot SEO and AI-visibility audit on a URL, waits for it to finish, and returns a summary (score, top actions, main issues). Ideal for "audit this site and tell me what to fix". Can take 1 to 3 minutes; past the time limit, it returns the id so you can follow up with get_audit_status / get_audit.

  • create_editorial_calendarCreate or update an editorial calendarcan change or delete data

    Imports up to 50 dated editorial slots into a LightSpot site's calendar. The import is idempotent: externalId lets you update a slot without creating a duplicate. This action only creates the schedule; it does not generate, schedule or publish any content and consumes no AI credit.

  • get_auditGet audit resultsread-only

    Fetches the results of an audit: a summary by default (score, top actions, main issues), or the full payload with full=true (all pages and all issues).

  • get_audit_statusGet audit statusread-only

    Lightweight status of an audit (PENDING/RUNNING/DONE/FAILED) with a progress value from 0 to 1.

  • get_competitorsGet a site's competitor analysisread-only

    Fetches a site's latest existing competitor analysis (detected competitors, tiers, citations, recommendations). Requires the Zenith plan. Does NOT trigger a new analysis — if none has been started from the app yet, returns status: "NONE".

  • get_editorial_calendarRead a site's editorial calendarread-only

    Reads a site's LightSpot editorial calendar over a period: imported slots, content being prepared, scheduled or published, and upcoming autopilot runs.

  • get_expert_reportGet a site's expert reportread-only

    Fetches the latest report from our 8 experts (technical SEO, editorial quality, AI visibility, structured data, sitemaps, performance, visual analysis, brand authority) produced after a site audit: prioritized findings, recommended actions with their steps, limitations and ready-to-apply artifacts (JSON-LD, sitemap…). Summary by default (findings + actions); full=true adds the rationale of the actions, the limitations, the artifacts and the evidence; expert=… limits the read to a single expert (useful with full=true to read one whole chapter without loading everything). auditId targets the ana…

  • get_siteGet a siteread-only

    A site's metadata and its recent audits.

  • list_site_auditsList a site's audit historyread-only

    Paginated audit history of a site.

  • list_sitesList your sitesread-only

    Paginated list of your LightSpot team's sites (with their latest score).

  • run_auditStart an audit (non-blocking)

    Starts an SEO and AI-visibility audit on a URL without waiting. Returns the id and status. Use get_audit_status to follow progress and get_audit for the results.

Signals

Stars
0
Forks
0
Open issues
0
Weekly downloads
28
Last commit
Oct 4, 2026 (25 days ago)
Last release
Oct 4, 2026 (25 days ago)
Last package publish
Oct 4, 2026 (25 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.nmarijane/lightspot-mcp
Version
0.6.0
Auth
API key
Packages
npm @lightspot/mcp
License
MIT
Repository
github.com/nmarijane/lightspot-mcp
Website
lightspot.ai
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

LightSpot MCP server. Agent Mart. https://agentmart.dev/connectors/nmarijane-lightspot-mcp (last updated 2026-10-24)