# MentionedOn Discovery Evidence Tools [Verified owner] [Health: Active]

**Category:** 🎯 Marketing  
**Repository:** https://mentioned-on.com/developers/mcp  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/mentionedon-discovery-evidence-tools

## Description
Review supplied AI-discovery evidence and prioritize visibility improvements.

## Tools
Capabilities this server exposes over MCP:

- **analyze_discovery_readiness** — Use when the user has no account: scores signals you collect yourself (schema present, name/address/phone consistency, profiles, reviews) for AI discovery readiness. Returns a score, the gaps in priority order and what still needs verifying. Free; it does not fetch the website, run a scan, store anything or confirm inclusion in any AI product.
- **build_visibility_action_plan** — Use after analyze_discovery_readiness, or with findings you already have: turns them into a short ordered list of fixes for one goal and effort budget, with the reason and a check for each. Free; it does not edit a website, contact anyone, store data or promise rankings or mentions.
- **summarize_scan_evidence** — Use when you captured AI answers yourself: calculates how often the business is mentioned and how often its own site is cited, overall and per assistant, with the statements that support each number. Free; it does not call AI providers, fetch URLs or store anything, and it says nothing beyond the answers supplied.
- **list_monitored_businesses** — Needs a connected MentionedOn account. Start here: lists the businesses in the account with each one's id and monitoring status, or a setup link when there are none. Pass the id as businessId to the other tools. Read-only; starts no scan, trial or charge.
- **get_visibility_report** — Needs a connected MentionedOn account. Use when the user asks how their business shows up in AI answers: returns the latest saved check (score, mention and citation rates, answer excerpts per assistant, competitors, cited sources) and up to 30 earlier checks, with dates, provider gaps and a score change only when checks are comparable. Needs businessId from list_monitored_businesses. Read-only; runs no new scan, so results are dated, not live.
- **get_improvement_results** — Needs a connected MentionedOn account. Use for 'did my new page work?': returns the question being improved, the page published for it, and before/after evidence: saved assistant answers in equal windows either side of publication (same settings only), any Google AI Overview follow-up, and AI-referred visits to that page. Needs businessId. Read-only; runs no scan. A change after publication does not prove the page caused it.
- **get_share_of_voice** — Needs a connected MentionedOn account. Use for 'who does AI recommend instead of us?': returns how often saved answers name this business versus every other business they name, its rank over saved checks, and the kinds of sites cited (own site, directories, community, press, competitors). Needs businessId. Read-only; built from saved checks, no scan.
- **list_articles** — Needs a connected MentionedOn account. Use to fetch drafted articles: returns up to 20 recent drafts with the questions each targets, the buyer it was written for and the Markdown (first 4,000 characters), plus this month's usage. Needs businessId. Read-only; new drafts are made in MentionedOn and count against the plan's monthly allowance.
- **get_ai_referrals** — Needs a connected MentionedOn account. Use for 'are people arriving from ChatGPT?': returns the last 30 days of website visits that came from AI assistants, by assistant and landing page, and the install snippet when one has been issued. Needs businessId. Read-only. Counts are a floor: some assistants send no referrer.
- **get_website_fixes** — Needs a connected MentionedOn account. Use after inspect_business_website to see the current revision of saved facts, schema and copy, and whether each fix is installed. Needs businessId from list_monitored_businesses. Read-only; returns the revision number you must pass to draft_website_fixes (and to inspect_business_website and verify_website_fixes).
- **inspect_business_website** — Needs a connected MentionedOn account with a paid or 7-day trial monitoring slot (Local is $99/month). Use first when fixing business information: fetches a few public pages of the saved business website and saves candidate facts with where each was found. Pass revision from get_website_fixes (0 if none) and authorizationAcknowledged: true once the user confirms they own the site. Saves a new revision; refused once drafts exist; up to 20 website checks a day. Runs no AI scan and publishes nothing.
- **draft_website_fixes** — Needs a connected MentionedOn account with a paid or 7-day trial monitoring slot (Local is $99/month). Use after the user confirms the facts from inspect_business_website: generates and saves business schema, website copy and a business-profile description from those facts only. Pass the current revision and confirmed: true; never invent missing facts. Saves a new revision; no AI model cost, nothing is published or sent.
- **verify_website_fixes** — Needs a connected MentionedOn account with a paid or 7-day trial monitoring slot (Local is $99/month). Use after the user installs the fixes: fetches one page on the business's own website and checks it for the saved schema and text, saving found, not-found or unknown results against that revision. Up to 20 website checks a day. A found fix does not prove better AI visibility.

## Claude Desktop Quick Installation
Remote MCP endpoint (confidence: medium). Install path inferred — verify against the README before running it. Add as a URL/SSE server in your client:

```json
"mcpServers": {
  "mentionedon-discovery-evidence-tools": {
    "url": "https://mentioned-on.com/developers/mcp"
  }
}
```

## Documentation

## What the MentionedOn Discovery Evidence Tools MCP server does

MentionedOn Discovery Evidence Tools MCP server supports evidence review and website-fix workflows for businesses connected to a MentionedOn account. It can score supplied website and business signals, calculate rates from supplied captures, and turn findings into a prioritized action plan. These analysis operations work on information provided by the caller; they do not independently scan a site, contact AI providers, or confirm inclusion in an AI product.

The server can also expose account-owned monitoring information. You can list monitored businesses, read a saved visibility report, inspect stored website observations, and review proposed fixes for an owned business. The account list includes monitoring and setup status, while an empty account receives a setup link without starting a scan, subscription, or charge.

## How it works

The MentionedOn Discovery Evidence Tools MCP server separates supplied evidence from saved account data and authorized website operations. Analysis tools calculate results from caller-provided inputs. Report tools read saved captures, competitors, source links, and up to 30 earlier snapshots. Score comparisons are appropriate only when the model, prompt, capture recipe, and completion state match between captures; reports also show provider gaps and timestamps.

Website inspection requires explicit authorization, an eligible paid or trial monitoring slot, the exact current revision, and bounded public HTML requests. The inspection saves candidate facts with source receipts and preserves existing draft content. After the user confirms facts, drafting can save reviewable business schema, website copy, and a business-profile description without filling in missing facts. Verification compares reviewed artifacts with a page on the same owned website and records dated found, not-found, or unknown results against the exact revision.

## Setup and configuration

Connect the server to a MentionedOn account with owned businesses and monitoring status. For an empty account, begin with the setup link returned by `list_monitored_businesses`; that response does not initiate billing or a scan. Before inspection or verification, obtain authorization and ensure the business has a paid or trial monitoring slot. Preserve and pass the exact current revision when starting an inspection, drafting fixes, or verifying them.

## Tools and capabilities

- `analyze_discovery_readiness` scores supplied discovery signals.
- `build_visibility_action_plan` ranks fixes with a deterministic rubric.
- `summarize_scan_evidence` calculates mention and business-citation rates from supplied captures.
- `list_monitored_businesses` returns owned businesses and monitoring or setup status.
- `get_visibility_report` reads saved captures, sources, competitors, and historical snapshots.
- `get_website_fixes` reads facts, proposed schema and copy, the current revision, and installation checks.
- `inspect_business_website` fetches bounded public HTML and saves candidate facts with receipts.
- `draft_website_fixes` saves reviewable schema, copy, and profile text from confirmed facts.
- `verify_website_fixes` records dated comparisons between reviewed artifacts and the owned site.

## Limitations and notes

The MentionedOn Discovery Evidence Tools MCP server does not query AI models, run AI scans, fetch arbitrary websites through its analysis tools, persist caller-supplied analysis data, edit or publish websites, send messages, or contact third parties. Saved reports describe captured observations rather than guaranteed current consumer-app inclusion. Installation checks do not demonstrate a visibility improvement, and the tools make no promise of rankings or mentions.

_Full upstream README: https://allmcps.com/mcp/mentionedon-discovery-evidence-tools/readme_