Tonaily

npx add-mcp 'https://app.tonaily.com/mcp/tools'

Connect your agent to Tonaily.

Claude Code, Claude Desktop, Cursor. Any MCP client works straight on your product.

A free server for any public site. Kira MCP, the account server included from Growth, for your keywords, your sequences and your AI visibility.

Works with

claude · tonaily

> where am I losing to competitors in AI answers?

• tonaily:llm-visibility-report

✓ Share of voice 18% · 30 questions replayed

• tonaily:llm-answers promptId 14

✓ 3 answers read · ChatGPT, Gemini, Grok

• tonaily:what-to-write

✓ 12 themes · top opportunity 90/100

They win on comparison pages you have yet to write.

Want me to plan the sequence? Everything stays a draft.

>

Who proposes, who publishes.

Kira is the AI inside Tonaily. Kira MCP, from Growth, opens your account to your own assistant. Every publication goes through you.

• Inside Tonaily, every plan

  Kira

  Proposes Keywords, topics, sequence plans, edits for an article that slips. Drafts Articles, social posts and whitepapers, on click or on a sequence date. Approves You do. Every suggestion waits for your approval. Publishes Only at your request.
• In the app

  You

  Proposes The topic, the angle, the dates. Drafts Any change, in the editor. Approves Every article, post and edit. Publishes Articles to WordPress or Diggama, now or at a date, or through a sequence’s auto-publish once you switch it on. Social posts, yourself, on the network.
• Kira MCP, from Growth

  Your assistant, via MCP

  Proposes Reads your keywords, themes, sequences and AI visibility, then suggests a plan. Drafts With a write token: a draft sequence or an AI visibility question. Articles stay with Kira. Approves You do. A draft sequence waits for a human to activate it. Publishes Publishing stays with you.

Two doors, two audiences.

One is open to everyone and looks at public websites. The other is yours, and looks at your account.

• Free audit server

  https://app.tonaily.com/mcp/tools Authentication Open access Account Optional What it sees Any public website Tools 5 tools Rate limit 10 calls/min per IP How to install it

• Account server

  Token https://app.tonaily.com/mcp Authentication API token (Bearer) Account Growth or Pro plan What it sees The token's organisation only Tools 16 tools + 1 prompt Rate limit 120 calls/min per token How to connect it

Both run over remote HTTP, hosted by Tonaily: your machine stays as it is. One address is enough. Browse the 22 tools → Step-by-step guide for Claude, ChatGPT and Cursor →

The free audit server.

Open to everyone, free and anonymous. Any agent can analyse any public website. A prospect asks their assistant “take a look at my site”, and gets a real diagnosis.

Claude Code

claude mcp add --transport http tonaily-tools \
  https://app.tonaily.com/mcp/tools

Claude Desktop / Cursor

{
  "mcpServers": {
    "tonaily-tools": {
      "type": "http",
      "url": "https://app.tonaily.com/mcp/tools"
    }
  }
}

Guardrails

• 10 calls per minute per IP, on every tool.
• 300 analyses per day, all visitors combined.
• 24 h reuse: a domain already analysed today returns the existing report.
• check-ai-crawlers stays outside that cap, since it runs a quick direct check.
• Public addresses only, so the tool stays out of internal networks.

Two regimes, and that’s the first thing to understand

check-ai-crawlers answers in the same call. Four HTTP requests, and the answer comes straight back in a single step. An agent can check twenty domains in a row, each answered instantly.

The other three go through an analysis of thirty seconds to two minutes. get-audit-report is called back with the token from audit-website; compare-sites and generate-llms-txt are called back with the same parameters, so each turn stands on its own.

Two families to tell apart.

Blocking one makes your site invisible inside assistants. Blocking the other is a defensible choice, and the server explicitly instructs the agent to present it as such. All twelve bots, one by one, and the robots.txt to go with them: the AI crawlers guide.

Citation crawlers

They fetch a page to quote it inside an answer. Blocking them makes the site invisible in assistants.

OAI-SearchBotChatGPT-UserClaude-SearchBotClaude-UserPerplexityBotPerplexity-User

Training crawlers

They collect content to train a model. Blocking them is a legitimate, defensible choice.

GPTBotClaudeBotGoogle-ExtendedApplebot-ExtendedMeta-ExternalAgentCCBot

With includeFile: true, the tool returns the corrected robots.txt: it unblocks citation crawlers while keeping existing rules and any deliberate training block intact.

Googlebot and Bingbot are deliberately left off the list: AI Overviews go through the first, Copilot through the second. Blocking them falls under classic SEO.

The account server.

Kira MCP, included from Growth: your own assistant plugged into your account, distinct from Kira inside the app. A token carries one organisation. The agent sees exactly what its user would see in the interface, for that organisation only.

Claude Code

claude mcp add --transport http tonaily \
  https://app.tonaily.com/mcp \
  --header "Authorization: Bearer tny_your_token"

Claude Desktop / Cursor

{
  "mcpServers": {
    "tonaily": {
      "type": "http",
      "url": "https://app.tonaily.com/mcp",
      "headers": {
        "Authorization": "Bearer tny_your_token"
      }
    }
  }
}

• 01

  Read

  The agent reads the account: keywords, themes, sequences, AI visibility. The account stays exactly as it is.
• 02

  Read and write

  It can also create a draft sequence and add a question to the AI visibility panel. Those two actions, and only those.
• 03

  Where to create it

  Settings → API, admins only. The token starts with tny_ and is shown once. Ten active tokens max, revocable at any time.

With a read-only token, the write tools disappear from the list entirely. The model sees only the read tools, so those are the only ones it can propose or call, even from memory.

Three that deserve a word

• llm-answers The report says "you appear in three answers out of ten and this competitor wins". This one gives you the answer itself, the only way to understand why they win. Called on its own, it lists the questions with an excerpt; with promptId, it returns the full text per engine.
• competitor-gap Returns both gaps in a single call: the keywords they own that you still lack, and the domains that link to them and are still missing from your backlink profile. Both were already measured and paid for at analysis time, so reading them simply reuses those results.
• internal-link-suggestions The only free, immediate lever on the list: the text is written, the pages exist, only a link is missing. One internal link per 300 words, with a floor of three. An article already at quota is left as it is, because too many links dilute each one.

Every tool, in one place.

Twenty-two entries across the two servers. Filter by server, by right or by category, or just type what you are after.

22 of 22 tools

• check-ai-crawlers read Tells you whether a site lets AI assistant crawlers through. Returns bot-by-bot access, llms.txt presence and homepage schema.org markup. Audit Free server domain, includeFile Instant
• audit-website read Runs a full analysis of a domain and returns a tracking token. Scores the site out of 100 across 8 checks and recommends 5 article topics. Audit Free server domain 30 s to 2 min
• get-audit-report read Returns the finished report, including a shareable web permalink. Called with the token handed back by audit-website. Audit Free server token Instant
• compare-sites read Compares two sites on the same 100-point grid: score gap, check-by-check winner, editorial volume and blocked AI crawlers on both sides. Competitors Free server domain, competitor 30 s to 2 min
• generate-llms-txt read Writes the site's llms.txt, ready to drop at the root, plus a corrected robots.txt. It reuses the pages already collected by the analysis. Audit Free server domain 30 s to 2 min
• list-sites read The organisation's sites: domain, language, analysis status. Call it first: every other tool takes a site. Account Account server
• brand-profile read Positioning, industry, business model, promises, favourite topics, tone, vocabulary, personas. Read it before proposing a single topic. Strategy Account server
• what-to-write read Themes ranked by opportunity, with volume, difficulty, business relevance, still-free keywords and the pillar keyword. Strategy Account server
• search-keywords read The keyword corpus, filterable by theme, text and state, sortable by opportunity, volume, difficulty or AI search volume. Keywords Account server
• competitor-gap read The gap with tracked competitors, both ways: keywords they own that you still lack, and domains that link to them and are still missing from your backlink profile. Competitors Account server
• llm-visibility-report read Brand visibility inside AI answers: share of voice, appearance rate per question, winning competitor, per-engine split, sentiment, history. AI visibility Account server
• llm-answers read The text of the assistants' answers, question by question: who got cited instead of you, and what the assistant used to justify it. AI visibility Account server
• ai-readiness read Whether the site lets AI crawlers through. Also returns, on demand, the corrected robots.txt and a generated llms.txt. Audit Account server
• list-sequences read Editorial sequences: theme, status, progress, and the step-by-step detail on demand. Content Account server
• list-contents read Produced content (articles, whitepapers, social posts): metadata and primary keyword only (the body text stays in the app). Content Account server
• internal-link-suggestions read Internal links to add: articles ranked from worst to best linked, then the target page, exact anchor and its context. Links Account server
• quota-status read What the plan still allows this month, the delay before the next AI visibility measurement, and the token's permissions. Account Account server
• plan-sequence write Asks for an editorial plan on a theme: which articles, which one is the pillar, with keyword, title, metadata and angle. Asynchronous: it returns a proposal and leaves the account untouched. Content Account server
• get-suggestion write The state of a planning job (pending, running, done, failed) and its result once finished. Content Account server
• create-sequence write Creates the sequence from the validated plan: briefs, scheduled content, internal linking, keyword reservation, calendar. As a draft. Content Account server
• add-llm-prompt write Adds a question to the AI visibility panel. A question naming your brand or a competitor is refused: it would force the citation. AI visibility Account server
• tonaily-briefing prompt The prompt that kicks off a working session: reads the brand profile, the corpus health, the themes to write and the AI visibility, then proposes the next actions. Optional argument: site. Strategy Account server site

Production stays in your hands.

The line is economic: reading is free, planning costs cents, writing an article costs dozens of times more and uses a monthly quota. A model explores freely, and spending stays a human decision.

Three gestures therefore stay in the interface, because they commit the account’s budget and quota.

• 01

  Activating a sequence

  That is what starts the writing. A sequence created by an agent stays a draft until a human activates it.
• 02

  Re-running an AI visibility measurement

  Billed, and subject to a cooldown. llm-answers only reads answers already collected.
• 03

  Finding new competitors

  And refreshing the backlink profile. competitor-gap only reads measurements already taken.

The agent screen.

Next to Track, the agent tab carries three screens, because they are three reading rhythms.

• Dashboard

  What the server is, the install command, the three counters and the full tool catalogue. Once, to understand

• Access

  The account tokens with their scope and last use, the three install commands, and the commitments the server always keeps. The day you create a token

• Usage

  Calls per day over thirty days, and the most-served tools. Regularly, the only screen that changes by itself

The counter is fed per call: every request to the MCP server increments a counter per day and per tool. Only accepted calls are counted. Refused ones (invalid token, inactive subscription) are filtered out, so a misconfigured loop stays out of your activity figures.

Prompts that already work.

With the free server

• > Does example.com let ChatGPT and Claude crawlers through?
• > Analyse example.com with the Tonaily MCP server. Run audit-website, wait for the report, then summarise the score out of 100, what blocks AI assistant crawlers, and the five recommended article topics.
• > Compare example.com to competitor.com: who wins, on which criteria, and by how much?
• > Write the llms.txt for example.com and tell me where to drop it.

With your account

• > Give me the state of my SEO: read the brand profile, the themes to write and my visibility in AI assistants, then tell me the three next actions.
• > Which theme should I write on first? Dig into it, then propose a sequence plan. Wait for my approval before creating anything.
• > On which panel questions is a competitor cited instead of me? Read the answers and tell me what gives them the edge.
• > Which articles are the worst internally linked, and which internal links should I add?

The words the servers impose on agents.

So you may as well use them everywhere.

Cluster

A group of keywords covering the same subject. It is the unit of production: you cover a whole theme, article after article.

Sequence

An editorial plan on a cluster. One pillar article surrounded by satellites pointing to it, published at a regular cadence.

Opportunity

The score that ranks themes. Search volume weighted by difficulty and by relevance to the client's business.

Share of voice

The proportion of brand mentions inside AI answers, over the total of your brand plus tracked competitors.

Panel

The list of questions replayed periodically to the assistants. A stable question makes two measurements comparable.

What crosses, and what stays protected.

• The free server is anonymous and stays fully separate from Tonaily account data. The audit report lives outside the per-organisation partition; its permalink is long and unpredictable, and points at a report while keeping the requester anonymous.
• The account server is partitioned per organisation, on every read and every write. A token stays confined to its own organisation in every case: when context is missing, queries return an empty result by default, for safety.
• An expired or revoked token is refused immediately (401). An organisation with an inactive subscription is refused too (402), with the reason in plain text so the agent can repeat it to its user.

Frequently asked questions

Everything about connecting an agent to Tonaily.

Still have a question?

A real person answers within a few hours.

Talk to us

One address.Your agent does the rest.

Start with the free server, open to everyone. Plug in your own account, from the Growth plan, when you want to work on your keywords, your sequences and your AI visibility.