Koskamo

TofuBofu MCP

An MCP server that allows AI agents to run free AI visibility scans for B2B companies. It checks how often AI engines like ChatGPT, Claude, Perplexity, Gemini, and Google AI Mode recommend a specific company, providing an AI Visibility Index and identifying missing citation opportunities.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

TofuBofu MCP logo, by TofuBofuVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by TofuBofu
MCP endpoint (Streamable HTTP)
https://tofubofu.com/mcp
Vendor documentation

What its tools do

3 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Can change data (1)

3 of 3 have a description · 3 of 3 declare behavior hints · 2 of 3 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to tofubofu.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Run a free AI visibility scan for a B2B company
  • Check AI engine recommendations for a brand
  • Identify missing citation opportunities in AI answers

Source and maintenance

Vendor evidenceRegistry 1.0.0

Protocol and capabilities

Server
TofuBofu AI Visibility 1.28.1
MCP protocol negotiated in check
2025-11-25
Tools
3 advertised
Resources
0 advertised
Resource templates
0 advertised
Prompts
0 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  },
  "resources": {
    "subscribe": false,
    "listChanged": false
  },
  "experimental": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Tools to check how often the AI engines TofuBofu tracks recommend a company when buyers ask for vendors, and what to fix. The flow is the TofuBofu scan form's own: call research_company with the user's website, walk the user through the steps it returns, show them the answers and the queries and get a yes, ask for their work email, then call scan_ai_visibility with every answer. Read the results with get_visibility_report. research_company names the engines and the query count.

Tools

3 advertised

research_company
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Step one of a scan: read the company's website and return the scan form's steps, pre-filled with what we read. Call this first, walk the user through `steps` in order, show them the answers and the queries, and get a yes before calling scan_ai_visibility. Every value is a guess from the website (or, for a signed-in workspace's returning brand, what the brand already holds) for the user to confirm or correct. Returns brand_name, steps (each with title and fields: param, question, help, kind, options, value, suggestions), scan (engines, queries_per_engine, queries_total) and how_to_ask.

research_company input schema
{
  "type": "object",
  "title": "research_companyArguments",
  "required": [
    "domain"
  ],
  "properties": {
    "domain": {
      "type": "string",
      "title": "Domain",
      "description": "The company's website or domain, e.g. \"acme.com\"."
    }
  }
}
research_company annotations
{
  "title": "Read a company's website for the scan",
  "readOnlyHint": true,
  "openWorldHint": true
}
scan_ai_visibility
Advertised by the server during the last successful anonymous check.
Open-world

Start an AI-visibility scan of a company's website. It asks ChatGPT, Claude, Perplexity, Gemini, Google AI Mode real buying queries and records which companies they name. A free scan asks 5 queries on each engine, 25 in all. A call carrying a TofuBofu API key (Authorization: Bearer tb_live_...) re-scans that workspace's existing brand for the website, on its plan and quota. Before calling: call research_company, walk the user through its steps, show them the pre-filled answers and the queries (for a returning brand, the ones its last scan asked, which this scan asks again), and get a yes. Ask where they sell if you do not know it: geo_scope changes every query. Omit a field you do not know rather than inventing a value. The scan runs in the background (a few minutes); call get_visibility_report with the returned report_id. Returns report_id, report_url, assumed (answers not supplied) and query_warnings (buyer_questions that read as a topic, each with its reason; every one is still asked as sent). status "not_started" with report_id null means no scan ran: the email already has an account, or this website's free scan already ran this month. A sign-in link went to that inbox; show the note and stop.

scan_ai_visibility input schema
{
  "type": "object",
  "title": "scan_ai_visibilityArguments",
  "required": [
    "domain",
    "email"
  ],
  "properties": {
    "email": {
      "type": "string",
      "title": "Email",
      "description": "The user's work email. Required: we send the finished report there and it identifies the account. One free scan per website a month."
    },
    "domain": {
      "type": "string",
      "title": "Domain",
      "description": "The company's website or domain, e.g. \"acme.com\"."
    },
    "not_for": {
      "type": "string",
      "title": "Not For",
      "default": "",
      "description": "Who are you NOT for? The buyer you turn away, and why. Saying it costs nothing and it is what makes the rest of the answer specific. Omit it if the user did not say."
    },
    "capacity": {
      "type": "string",
      "title": "Capacity",
      "default": "",
      "description": "Who will do the fixes? Who on the user's side will make the changes. One of: solo; one_marketer (One marketer); small_team (A small team, 2 to 4); full_team (A full team, 5 or more). Omit it if the user did not say."
    },
    "hired_by": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Hired By",
      "default": null,
      "description": "Who usually hires you? Who signs the contract, in their words. Up to three. Omit it if the user did not say."
    },
    "platform": {
      "type": "string",
      "title": "Platform",
      "default": "",
      "description": "What is your site built on? Decides which publishing route we can offer you. One of: wordpress (WordPress); webflow (Webflow); hubspot (HubSpot); shopify (Shopify); squarespace (Squarespace); wix (Wix); framer (Framer); custom (Something custom). Omit it if the user did not say."
    },
    "sells_to": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Sells To",
      "default": null,
      "description": "What size and type of customer? SMB and enterprise are different queries with different winners. Omit it if the user did not say."
    },
    "services": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Services",
      "default": null,
      "description": "Which services do you want to be recommended for? Up to three services this brand wants AI engines to recommend it for, in a buyer's words. Omit it if the user did not say."
    },
    "confirmed": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Confirmed",
      "default": null,
      "description": "The params above that the user confirmed or answered, as opposed to values you passed through from research_company unchallenged. A value not listed here is recorded as our guess, not as their answer."
    },
    "geo_scope": {
      "type": "string",
      "title": "Geo Scope",
      "default": "",
      "description": "Where do you sell? Where the brand's buyers are. One of: global (Anywhere); national (Across one country); national_local (National, with a local angle); local (My own city or region). Omit it if the user did not say."
    },
    "locations": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Locations",
      "default": null,
      "description": "Which places? The country you sell across, or the cities you are bound to. Omit it if the user did not say."
    },
    "tg_people": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Tg People",
      "default": null,
      "description": "Which people? The consumer group this brand sells to, e.g. parents or students. Consumer brands only. Omit it if the user did not say."
    },
    "brand_name": {
      "type": "string",
      "title": "Brand Name",
      "default": "",
      "description": "Is this you? The company name as buyers say it, read from the website and confirmed or corrected by the user. Omit it if the user did not say."
    },
    "competitors": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Competitors",
      "default": null,
      "description": "Who else would a buyer consider? 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. Omit it if the user did not say."
    },
    "tg_occasions": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Tg Occasions",
      "default": null,
      "description": "When do they buy it? The occasion or moment this brand is bought for. Consumer brands only. Omit it if the user did not say."
    },
    "buyer_audience": {
      "type": "string",
      "title": "Buyer Audience",
      "default": "",
      "description": "Who buys from you? Whether this brand's buyers are businesses or people, as the user said. One of: business (Businesses); consumer (Consumers). Omit it if the user did not say."
    },
    "differentiator": {
      "type": "string",
      "title": "Differentiator",
      "default": "",
      "description": "What makes you different? One line. Leave it blank if nothing stands out. Omit it if the user did not say."
    },
    "buyer_questions": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Buyer Questions",
      "default": null,
      "description": "Queries your buyers ask. Queries this company's buyers ask. Each is put to the engines as written, every scan. Omit it if the user did not say."
    },
    "product_category": {
      "type": "string",
      "title": "Product Category",
      "default": "",
      "description": "What would a buyer search for to find you? What a buyer would type to find a company like yours, in their words. Omit it if the user did not say."
    },
    "segment_industries": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Segment Industries",
      "default": null,
      "description": "Which industries do you sell into? The verticals your buyers work in. Leave it empty if you sell across all of them. Omit it if the user did not say."
    },
    "segment_buyer_roles": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Segment Buyer Roles",
      "default": null,
      "description": "Who reads the shortlist? The roles who compare vendors and hand up a recommendation. Omit it if the user did not say."
    }
  }
}
scan_ai_visibility annotations
{
  "title": "Run AI visibility scan",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}
get_visibility_report
Advertised by the server during the last successful anonymous check.
Advertised read-only

Fetch the results of an AI-visibility scan started with scan_ai_visibility. Args: report_id: The id returned by scan_ai_visibility. Returns: While running: {status: "running", progress}. When done: the Tofu Index (named in the consideration set) and the Bofu Index (picked head to head), each with its fraction, the Tofu Index per engine, share of voice, sentiment, the top competitors winning the answers, any gap between the competitors the user named and the ones AI names, and top_fixes, the open items at the top of the brand's Fixes list (the same list the app's Fixes page shows; empty when there is none), plus the report_url.

get_visibility_report input schema
{
  "type": "object",
  "title": "get_visibility_reportArguments",
  "required": [
    "report_id"
  ],
  "properties": {
    "report_id": {
      "type": "string",
      "title": "Report Id"
    }
  }
}
get_visibility_report annotations
{
  "title": "Get AI visibility report",
  "readOnlyHint": true,
  "openWorldHint": false
}

Prompts

0 advertised

No prompt definitions available.

Resources

0 advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (3 of 3 answered).

  1. 2026-11-07: 2 of 2 checks answered
  2. 2026-11-09: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
699 ms
95th percentile latency
699 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 699 ms · metadata changed · 3 tool(s), 0 resource(s), 0 resource template(s), 0 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http tofubofu-mcp https://tofubofu.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add tofubofu-mcp --url https://tofubofu.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable tofubofu-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "tofubofu-mcp": {
      "url": "https://tofubofu.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "tofubofu-mcp": {
      "type": "streamableHttp",
      "url": "https://tofubofu.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start tofubofu-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "tofubofu-mcp": {
      "type": "http",
      "url": "https://tofubofu.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http tofubofu-mcp https://tofubofu.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://tofubofu.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "tofubofu-mcp": {
      "serverUrl": "https://tofubofu.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like TofuBofu MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run TofuBofu MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing