# Ottom Muse connector

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

## Ottom

Check whether AI shopping agents can read and buy from your online store.

- Record: https://musedirectory.ai/connector/ottom
- Category: Shopping & Commerce
- Developer: Ottom (https://ottom.io/developers/mcp)
- 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, 396ms, checked 2026-11-13T22:56:10Z
- Endpoint: https://ottom.io/mcp
- Auth: Needs an access key; Pricing: unknown
- Screening: Screened, no issues found (2026-11-13T22:56:10Z)
- Source: Found in the official MCP Registry (io.ottom/ottom) https://registry.modelcontextprotocol.io/v0/servers?search=io.ottom%2Fottom

Connects to Ottom's readiness scanner. Muse can check a store page for robots.txt, llms.txt, product feeds, structured data and readable prices, then explain each finding with a fix. It also pulls public category benchmarks on where AI agents stall during shopping.

Example request: "Check whether my product pages are readable by AI shopping agents and tell me what to fix."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Ottom to help me. It is a free service with an MCP server at https://ottom.io/mcp. It needs an API key from Ottom; ask me to enter it through your secure credential prompt. 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:
- check_store_readiness: Runs a light check of one store page, the way an AI shopping agent reads it: robots.txt, llms.txt, the product feed, the UCP manifest, structured data (product, price, availability, GTIN) and whether the price is in text an agent can read. Each finding comes with a plain explanat
- get_benchmark: Returns Ottom’s published benchmark for a store category: how far AI agents get at each stage, the stalls that stop them most often, and the score spread. Aggregate figures only, never a named store, published under CC BY 4.0. Use "all" for every store. An unknown category answer
- list_checks: Lists what check_store_readiness reads on a store, what it never does, and what a full scan on ottom.io adds.

Screening checks:
- MCP handshake: pass (Answered in 396ms)
- Domain against threat feeds (Cloudflare security DNS): pass (ottom.io 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 (3 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (No redirects off the domain)
- AI review of purpose and tool behavior: pass (No concerns)