# Scamstats Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## Scamstats

Compare scam rates, losses and common scam types across countries, with sources for every figure.

- Record: https://musedirectory.ai/connector/scamstats
- Category: Research & Data
- Developer: Scamstats (https://scamstats.org/data/#ai-connector)
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 93ms, checked 2026-11-20T17:45:46Z
- Endpoint: https://scamstats.org/mcp
- Auth: No account needed; Pricing: unknown
- Screening: Screened, no issues found (2026-11-18T01:16:27Z)
- Source: Found in the official MCP Registry (io.github.Rand0mThoughts/scamstats) https://registry.modelcontextprotocol.io/v0/servers?search=io.github.Rand0mThoughts%2Fscamstats

Connects to the Scamstats open catalogue of fraud statistics. Muse can look up how many people are scammed in a country, the share of adults affected, money lost and money returned, compare measures across up to 20 countries, break down a scam type like investment or romance fraud, and trace each figure back to its source.

Example request: "How common is investment fraud in Canada compared with the US, and where do those numbers come from?"

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Scamstats to help me. It is a free service with an MCP server at https://scamstats.org/mcp. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- list_countries: Lists the countries Scamstats covers, with the people scammed in a year and the share of adults in each.
- get_country: Gives one country's figures, scam types, money returned and sources, from its two-letter code such as PE.
- compare_countries: Compares one measure across up to 20 countries, and names any differences in how the figures were counted, such as different periods.
- get_world: Gives the world estimate: the people scammed in a year, the share of adults and the money lost.
- get_scam_type: Gives one scam type's people and money lost in every country Scamstats covers, from its code such as investment.
- search_sources: Searches the catalogue of scam data sources by country, publisher, topic or what is measured. Give at least one of query, area or measure.
- get_source: Gives one catalogue entry in full, with its editions and how Scamstats uses it, from its id.

Screening checks:
- MCP handshake: pass (Answered in 117ms)
- Domain against threat feeds (Cloudflare security DNS): pass (scamstats.org not flagged)
- Published packages against the OSV malicious-package database: n/a (No npm or PyPI package published)
- Hidden instructions or invisible characters in tool text: pass (7 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (Domain registered 52 days ago)
- AI review of purpose and tool behavior: pass (No concerns)
