Marketing

howseen.ai

Tracks and analyzes a brand's visibility in AI-generated answers across engines, including prompts, competitors, and cited sources.

1 endpoint29 known toolsFirst detected October 21, 2026Last detected October 21, 2026

ENDPOINT 1

https://app.howseen.ai/api/mcp

No auth detected

MCP server metadata

Name: howseen
Version: 1.2.0

Capabilities

tools.listChangedprompts.listChanged

Server instructions

Howseen tracks how often AI engines (ChatGPT, Gemini, Perplexity, Google AI Overviews, Google AI Mode) name the user's brand when buyers ask questions. Work in a loop: SEE THE GAP, then CLOSE IT. 1) See the gap: get_changes (what moved since the last scan), get_prompt_gaps (questions where a competitor is named and the brand is not), get_easiest_wins (sites cited in those lost answers: where to get listed), get_action_plan. Also: list_brands, get_visibility, get_competitors, get_top_sources, search_responses (real answer excerpts), list_prompts, list_articles, get_article_performance, suggest_prompts, get_usage (quotas and what this key may do). 2) Close the gap (only with an API key created with "Read + actions"): mark_action_done, dismiss_action, add_prompts, archive_prompts, remove_prompts, add_competitor, remove_competitor, draft_article (draft only), refresh_article (rewrite a written article with the current brand profile, free once after a profile change), create_share_report, run_scan. 3) Publish (same key): publish_article (live on the brand's CMS or its own site's feed, or scheduled), request_indexing. Prompts weekly_review and client_report chain these steps. CONFIRM RULE: every change tool first returns a PREVIEW and changes nothing. Show the user exactly what will change and the quota impact, and call the same tool again with confirm: true ONLY after the user explicitly agrees to that preview. Never set confirm: true on your own initiative, and never chain several confirmed changes from one approval. Plan limits apply exactly as in the app (prompt and competitor quotas, article allowance, a manual scan at most once per plan cadence: every 3 days, every day on Business); a refusal explains why and changes nothing. Percentages are 0-100. avg_position is the brand's average rank among the brands named in an answer (1 = named first). Data comes from the latest completed scans.

Known tools 29

list_brands

List the brands (websites) tracked in this Howseen account, with their id, name and domain.

Inferred read-only

get_visibility

Headline AI visibility of a brand: % of AI answers that name it, share of voice vs competitors, average position, sentiment, per engine, plus the trend over the period (one point per scan).

Inferred read-only

list_prompts

The buyer questions (prompts) tracked for a brand, with per-prompt visibility, share of voice, position, which engines name the brand, and which brands and domains are cited.

Inferred read-only

get_competitors

Compare the brand with its competitors in AI answers: visibility %, share of voice, average position and sentiment, overall and per engine.

Inferred read-only

get_top_sources

The domains and URLs AI engines cite most when answering the brand's buyer questions, overall and per engine.

Inferred read-only

search_responses

Read real AI answers collected for the brand: excerpts around the brand mention, whether the brand and which competitors were named, and the cited URLs.

Inferred read-only

get_action_plan

Prioritized actions to raise the brand's AI visibility (off-page: get listed on the pages AI cites; content: answer uncovered buyer questions), ranked 20/80 like the dashboard Action plan, with steps.

Inferred read-only

list_articles

Articles Howseen wrote for the brand (drafts, scheduled and published), with status, target question, GEO score and published URL.

Inferred read-only

get_prompt_gaps

Tracked prompts where AI names at least one competitor but not the brand, per engine, with the competitors named and the domains cited.

Inferred read-only

get_easiest_wins

Third-party sites and pages cited in the answers the brand loses (competitor named, brand not), ranked by how many lost answers cite them, with the matching action-plan item.

Inferred read-only

get_changes

What changed between the last two completed scans (or since a date): prompts gained and lost, visibility delta per engine, tracked competitors newly named, and the likely causes (sources that started or stopped citing the brand).

Inferred read-only

suggest_prompts

Buyer questions worth tracking that the brand does not track yet: real questions from Hacker News discussions (ranked by engagement) plus AI suggestions for the category.

Inferred read-only

get_article_performance

Articles written for the brand with status, GEO score, published URL and search-engine indexing status (Google URL Inspection, Bing), plus impressions and clicks when Search Console or Bing is connected.

Inferred read-only

get_usage

Plan, quotas used and left (prompts, competitors, articles, manual scans), next automatic scan estimate, what this API key may do, and the API rate limits.

Inferred read-only

mark_action_done

Mark an action-plan item as done (same state as the dashboard Action plan).

Inferred read-only

dismiss_action

Dismiss an action-plan item the user does not want to do (moves it to Archived in the dashboard, out of the next best actions).

Inferred read-only

add_prompts

Track new buyer questions (prompts) for the brand, checked against the plan's prompt quota (the whole list is refused if it would exceed it).

Inferred read-only

remove_prompts

Stop tracking prompts and remove them from the prompt list (past scan results stay in history).

Potential side effects

archive_prompts

Archive prompts: they stop being scanned (frees prompt quota) but keep their history and stay listed as archived in the dashboard, restorable.

Inferred read-only

add_competitor

Track a competitor from a name or a website URL (resolved to name + domain like in Settings), within the competitor quota.

Inferred read-only

remove_competitor

Stop tracking a competitor (by name or domain).

Inferred read-only

draft_article

Write a DRAFT article answering one buyer question, with the same quality pipeline as the app (brand context, sources AI cites, GEO checks).

Potential side effects

refresh_article

Rewrite a WRITTEN article with the brand's current profile (offer, category, offerings, competitors) after it changed: same article id, slug, question and date, previous version kept (restorable in the app).

Inferred read-only

create_share_report

Create a public, frozen report link (visibility, competitors, top prompts, recommendations) with the account's agency branding, like the dashboard Share button.

Potential side effects

run_scan

Scan the brand's prompts on the AI engines now, with the same limit as the dashboard Run now button (a fresh scan at most once per brand per plan cadence: every 72h, every 24h on Business; prompts added since the last scan can be scanned alone; an unfinished scan can be continued).

Inferred read-only

publish_article

Publish a written article (e.

Potential side effects

request_indexing

Submit a published article to the search engines connected for the brand: Google (sitemap re-submit through Search Console when connected with indexing), Bing (Webmaster key) or IndexNow for pages hosted by Howseen.

Inferred read-only

delete_article

Move an article (planned, draft or published) to the Trash, like the dashboard delete button: restorable with restore_article or in Howseen > Content > Trash, and its topic is not planned again.

Potential side effects

restore_article

Bring back an article from the Trash (e.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.howseen]
url = "https://app.howseen.ai/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "howseen": {
      "type": "http",
      "url": "https://app.howseen.ai/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: howseen
Remote MCP URL: https://app.howseen.ai/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "howseen": {
      "url": "https://app.howseen.ai/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "howseen": {
      "type": "http",
      "url": "https://app.howseen.ai/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "howseen",
  "transport": "streamable-http",
  "url": "https://app.howseen.ai/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.