About TofuBofu AI Visibility
TofuBofu runs a free AI visibility scan for any B2B company, right inside your AI assistant. Ask it to scan a domain and it runs the questions real buyers ask across ChatGPT, Claude, Gemini, Perplexity, Google AI Overview.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://tofubofu.com/mcpclaude mcp add --transport http tofubofu-188ffe https://tofubofu.com/mcp{"mcpServers":{"tofubofu-188ffe":{"type":"http","url":"https://tofubofu.com/mcp"}}}Open in Cursor{"servers":{"tofubofu-188ffe":{"type":"http","url":"https://tofubofu.com/mcp"}}}Open in VS Code{"mcpServers":{"tofubofu-188ffe":{"type":"http","url":"https://tofubofu.com/mcp"}}}{"mcpServers":{"tofubofu-188ffe":{"serverUrl":"https://tofubofu.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
2| Parameter | Type | Required | Description |
|---|---|---|---|
| domain | string | Yes | The company's website or domain, e.g. "acme.com". |
| string | Yes | The user's work email. Required: we send the finished report there and it identifies the account. One free scan per email per month. | |
| geo_scope | string | No | Where do you sell? Getting this wrong skews the whole report: a national firm scored on one city's questions looks invisible, and a local one scored nationally looks unwinnable. One of: global (Anywhere); national (Across one country); national_local (National, with a local angle); local (My own city or region). Shapes every buying question. This is the single highest-leverage answer here. Omit it rather than guessing: an omitted answer is recorded as unknown, a guessed one is indistinguishable from a real answer. |
| locations | any | No | Which places? The country you sell across, or the cities you are bound to. Shapes which geography goes into a localized buying question. Omit it rather than guessing: an omitted answer is recorded as unknown, a guessed one is indistinguishable from a real answer. |
| competitors | any | No | Who would a buyer otherwise pick? Companies the user says a buyer would pick instead of them. We track whoever the engines name either way, so this is the user's own view rather than the whole comparison set. Shapes the comparison set, the mismatch between who you name and who the engines do, and which of those two a given finding is about. Omit it rather than guessing: an omitted answer is recorded as unknown, a guessed one is indistinguishable from a real answer. |
| buyer_questions | any | No | Questions your buyers ask. Questions this company's buyers actually ask. They are put to the engines verbatim and tracked scan over scan, which is what makes a trend line mean anything. Shapes the questions themselves, pinned ahead of the generated ones. Omit it rather than guessing: an omitted answer is recorded as unknown, a guessed one is indistinguishable from a real answer. |
| sells_to | any | No | What size and type of customer? SMB and enterprise are different questions with different winners. Shapes the same. 'Best sales engagement platform for SMB teams' is not the same question as 'for enterprise revenue orgs'. Omit it rather than guessing: an omitted answer is recorded as unknown, a guessed one is indistinguishable from a real answer. |
| capacity | string | No | Who will do the fixes? We size and sequence the plan to match. A solo founder does not get a list built for a five-person team. One of: solo (Just me); one_marketer (One marketer); small_team (A small team, 2 to 4); full_team (A full team, 5 or more). Shapes the fix plan, which is generated in the tail after the engines answer. Omit it rather than guessing: an omitted answer is recorded as unknown, a guessed one is indistinguishable from a real answer. |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.