Mike Fluff

Reviewed 21m ago. Tool definitions changed on Oct 15, 2026.

tools

10 tools scanned

metadata

scanned

• mediumReviewTool definitions changed after an earlier review

  A server that changes its tool descriptions after being approved ("rug pull") can slip new instructions to agents. Re-check what changed before trusting it.

  changed 2026-10-15

• search_answers

  Search the answers Mike Fluff Press publishes (questions about crypto history, Bitcoin, stablecoins, fraud, AI agents, software after AI: "what happened to FTX", "who is Satoshi", "what is MCP") and the interactive experiments from the books. Use this first whenever the user asks a factual question these books cover. Returns up to 8 hits, each with the title, a 40-60 word lead answer you can quote, the canonical URL, the book, and the chapter it draws on. Read-only.

• get_answer

  Fetch one published answer by its id (from search_answers): the full direct answer, the explanatory sections, the FAQ, the chapters and experiments it cites and related answers, all with canonical URLs. Use after search_answers when the lead answer is not enough. Read-only.

• list_books

  List the books by Mike Fluff Press with title, subtitle, synopsis, status, canonical book page URL and the table of contents (which chapters are free to read). Use it to answer "what has Mike Fluff written" or before get_chapter_preview. Read-only.

• get_chapter_preview

  Return the text of one chapter as an anonymous reader sees it on the site. Free chapters come back in full. Paid chapters come back as their public lead-in only (about a fifth of the chapter); the rest requires buying the book, and this tool never returns it. Where the site sells chapters over x402, the result says how an agent can buy the whole chapter itself in USDC (`x402`). Get book slugs and chapter ids from list_books. Read-only.

• run_diagnostic

  The self-diagnostic from mikefluff.com/diagnostic: ten multiple-choice questions about how a business runs, scored into one of five named operational conditions (e.g. "one queue, one person", "manual conveyor", "SaaS obesity") with a severity, an annual cost estimate built only from the user's own answers, and a recommended next step with its URL. Call it with answers = {} first to get the questionnaire (question ids, option ids, which questions are conditional), ask the user, then call again with {questionId: optionId} (an array of option ids for multiple-choice questions). Read-only: nothing is stored or mailed.

• check_text

  Run the writer linter behind mikefluff.com/ai-text-checker on a text: it flags the stock phrases and rhythms readers recognise as machine-written ("in today's fast-paced world", "it's important to note", em-dash habits in Russian) and returns a density verdict (clean / borderline / neuroslop suspected), a pass/fail gate for hard bans, and each hit with line, column, category and the matched words. English and Russian only. Up to 20000 characters. It judges the text, not who wrote it. Read-only: the text is not stored.

• get_booking_slots

  List the open 30-minute slots for a free video call with Mike Fluff (business diagnosis, AI automation, compliance, Architect Mode), as ISO 8601 UTC start times. Use before book_call; pass one of these exact values as its "slot". Read-only.

• book_call

  SIDE EFFECT: books a real 30-minute video call in Mike Fluff's calendar, emails a confirmation with a calendar invite to the given address, alerts Mike, and records the booking as a lead. Only call this when the user has explicitly asked to book and chosen the time. "slot" must be one of the exact values returned by get_booking_slots. Name and email: either the ones the user gave for this purpose, or leave them out and the call is booked in the name of the person signed in with INITE ID (OAuth scope "mikefluff:booking"; without a token such a call is answered with HTTP 401 and the client is sent to sign in). Topics: diagnostic (general business consultation), automation (AI automation), compliance (privacy/GDPR/LGPD around AI systems), architect-mode (the one-day intensive). The confirmation email has a link to move or cancel. Limited to 3 bookings per hour per caller and 2 upcoming calls per email.

• buy_course

  SIDE EFFECT: opens a checkout for one of Mike Fluff's paid courses and records the user as a lead. Returns a payment link (billing's hosted page; works without signing in) and the price in the currency for the locale. Nothing is charged until the user pays on that page; after payment the course access link is emailed to the given address. Courses: parasites (parasites-course), freeMini (vibe-coding-course), contentFactory (content-factory-course). Only call when the user has asked to buy and given the email the course should go to — or leave the email out to use the account of the person signed in with INITE ID (OAuth scope "mikefluff:purchase"; with that scope the course is also attached to their account). Give the user the payment link; do not try to pay.

• buy_book

  SIDE EFFECT: opens a checkout for a Mike Fluff Press book for the person signed in with INITE ID, and returns the payment link to give them. Books are bought into an INITE account (the reader unlocks paid chapters for the account that paid), so this needs the person: OAuth scope "mikefluff:purchase". Called without a token it is answered with HTTP 401 and the client is sent to sign the person in. Nothing is charged until the person confirms the payment on the link (it opens the payment page directly, no second sign-in); the agent never pays. If they already own the book it says so instead. Only call when the user has asked to buy.