> ## Documentation Index > Fetch the complete documentation index at: https://docs.attensira.com/llms.txt > Use this file to discover all available pages before exploring further. # Brand MCP server > A public, read-only MCP server for your brand that any assistant or agent can connect to. It answers only from your product feed: the Brand Book facts you confirmed and marked public. Assistants and agents increasingly ask a company's own MCP server before they guess. The brand MCP server is that server for your brand. It holds no credentials and can write nothing. Every answer comes from your [product feed](https://docs.attensira.com/agent-readiness/feed.md), so it says exactly what the feed says: the facts you confirmed and marked public, and nothing else. ## Address ```text theme={null} https://mcp.attensira.com/b/{slug}/mcp ``` `{slug}` is your product feed's slug. The transport is streamable HTTP, and no key or sign-in is needed. An unknown slug answers `404`. If you turn your feed off, the address answers `410` within a minute, and serves nothing it served before. Turning it back on is picked up within a minute too. Each client IP has a rate limit; past it, the server answers `429` with `Retry-After`. This is a separate server from the [Attensira MCP server](https://docs.attensira.com/mcp/overview.md) you use to run your own workspace. It shares no credentials with it and never reads your workspace, only your published feed. ## Tools Every tool is read-only, and is marked so for clients (`readOnlyHint`, not destructive, idempotent). No tool writes anything. | Tool | Parameters | What it answers | | - | - | - | | `get_overview` | none | Name, one line, category, tagline, founded, headquarters, products, markets, languages and links. | | `list_products` | none | What you sell and what you plug into. | | `get_pricing` | `plan`, `currency`, `market`, all optional | Your plans and prices as you wrote them. `plan`, `currency` and `market` narrow it. A plan whose price you did not state has `price: null`; it is never estimated. A `currency` filter keeps only plans priced in that currency, so it leaves out free plans. Prices are not stated per market, and the answer says whether you list a market by the name asked about. | | `compare` | `competitor`, required | Your own facts for a comparison with a named competitor: products, integrations, compliance, pricing summary and plans. It says nothing about the competitor: your feed publishes no cited source about other companies, so `competitor_claims` is empty and `refused` is `true`, with the reason. | | `answer_requirement` | `question`, required | Whether you have an approved answer to a requirement such as "Does it work with Shopify?", quoted as you approved it, best match first and at most three. An approved answer counts only when every word that matters in its question is in the one asked, and a "not" or "without" on one side only means it does not count: "Does it work without Shopify?" is not answered by an answer to "Does it work with Shopify?". It also lists the products, integrations or standards the question names, but naming one is not an answer: "Are you GDPR and HIPAA compliant?" comes back unanswered, with GDPR listed. If you have published no answer, it says so and tells the assistant not to infer one. | | `get_signup_link` | `plan`, optional | Your sign-up link, tagged `utm_source=ai_assistant`, `utm_medium=mcp`, `utm_campaign=brand_mcp` and, with a `plan`, `utm_content`. If your link already carries UTM tags, it is returned as you wrote it. | | `get_policies` | `kind`, optional: `security`, `refunds`, `data`, `privacy` or `terms` | Your security, refunds, data, privacy and terms policies. `kind` narrows it. | The resource `brand://{slug}/facts` is the whole feed, exactly as it was published. Every answer carries a `source`: the feed's address, its `version` and `updated_at`, and the `fact_ids` of the Brand Book facts it came from. ## Freshness The server reads your feed at most once a minute per brand. See [how fast an edit reaches the feed](https://docs.attensira.com/agent-readiness/feed.md#how-fast-an-edit-reaches-it). ## How agents find it Two files on your own site point agents at the server. Each is filed as a change to your site, the same way a page fix is: a pull request to your connected GitHub repository, and your [approval settings](https://docs.attensira.com/agent/approval.md) for your own site decide whether to open now, open after the veto window, or hold for your yes. Closing or reverting the pull request undoes it. * **`/.well-known/mcp.json`**: a small card naming the server's address, its transport (streamable HTTP), that it needs no sign-in, and where your product feed and llms.txt are. It lists no tools, so it never goes stale when your Brand Book changes. * **One line in your `llms.txt`**: a `## MCP` section with a link to the server. Nothing else in the file is changed. If your site has no `llms.txt`, a short one is created. Both files go where your site serves its root from: the repository root, `public/` or `static/`, wherever your `llms.txt` or `robots.txt` already lives. If a file already says what it would say, nothing is filed. Your product feed must be on: a pointer to a server that answers `404` is worse than none. `.well-known/mcp.json` is the only file under a dot-directory we ever write. If your site already serves a `/.well-known/mcp.json` that we did not write, we leave it alone at every approval level: it comes back as `conflict`, with a reason, and nothing is filed for it. Add the server's address to your own file if you want agents to find it there too. The `llms.txt` line is still filed, because it only adds to that file. A `mcp.json` we wrote earlier is updated when its card changes, for example after you rename the brand. Ask for both files with `POST /v1/agent-readiness/brand-mcp/discovery` (body `{repo?, dir?}`, the `steer` scope). Each file in the answer has an `outcome`: `proposed` (with the change's id), `unchanged`, `finding_only` (at your approval level for your own site we only report it, and nothing is filed) or `conflict`. During a [trial](https://docs.attensira.com/account/plans.md#the-trial) the files are proposed as on a paid plan: they are drafts in your Inbox, and the pull request opens on your yes. ### The MCP registry We do not list your server in the public [MCP registry](https://registry.modelcontextprotocol.io) for you. The registry removes mass-created servers as spam, and one copy of the same server per brand under our name is exactly that. Instead you get a ready `server.json` named in your own domain's namespace (for `acme.com`, `com.acme/brand`), pointing at your server's address. Publish it with the registry's `mcp-publisher` after proving your domain (`mcp-publisher login dns` or `http`). Get it from `GET /v1/agent-readiness/brand-mcp/registry-entry` (`?domain=`, your workspace's domain by default). Its `published` is always `false`, because the entry is yours to publish. ## What agents ask `analyze(view=brand_mcp_queries)` (over REST, `GET /v1/views/brand_mcp_queries`) shows what agents asked your server over the last 1 to 90 days (30 by default; a longer window is cut to 90): * `total` calls, and counts `by_tool` and `by_client`. * `top_questions`: the questions asked most, grouped regardless of case, spacing and closing punctuation, each with its `count`, how many different `clients` asked it, and `last_asked_at`. `limit` sets how many (1 to 50, 10 by default). * A question's text is shown only once it was asked at least twice (`min_count`). Questions asked once are counted in `unshown`, never printed, so a one-off question that named a person stays out of the view. Queries are kept for 90 days. Turning your feed off stops new queries being counted. ## What is logged For each tool call we keep your slug, the tool, the client's product name (the first word of its User-Agent, for example `Claude-User`, and only when it looks like a product name) and the text of the tool's own parameters. Email addresses and phone numbers are removed from that text, and it is cut to 200 characters. Arguments a tool does not take are not kept, their names included. We never keep the IP address or any other header. When we file the call under your workspace, we remove email addresses and phone numbers again, along with the query string and fragment of any link in the text. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.