Tool search 164,478 tools · 10,067 live servers

Run the campaign's discovery pipeline: scrapes social platforms for posts matching the keywords and drafts a community reply for each. Costs 12 credits PER POST discovered (a typical run finds 5–20 posts, so 60–240 credits) and can take a few minutes. Check check_balance first and confirm the spend with the user. Then use get_posts to read results and review_posts to prune irrelevant ones.

Catch up on a campaign since the last check: posts discovered, replies claimed by community members, LIVE links to what they actually posted, and the engagement those replies drew. Free, and it never scrapes — safe to call at the start of every session. Pass `since` (the `checked_at` from the previous call) to get only what is new; omit it for the last 24 hours. Use this to resume a standing growth operation across chats, then get_campaign_results for the cumulative picture.

The cumulative scorecard for a campaign: the funnel (posts discovered → kept → replies drafted → claimed → posted → approved), the approval rate, whether posted replies survived on-platform, the engagement they drew, total credits spent broken down by operation, and the cost per usable reply. Free, and it never scrapes — unlike the web report it costs nothing to poll. Use it to answer 'is this working and what am I paying for it?'.

Paid plans only (trial 403). Create a Signals watch on a competitor domain for ads, units, inventory, and social. Tight watch cap; meters the key. No probe, no scrape.

Find barbershops and salons ranked by weekly booth rent, with chairs available, Google rating, review count and hiring status. Answers what a chair costs in a given city and which shops have one free. Booth rent is quoted directly by shops rather than scraped, so coverage is partial — the response states how many listings actually publish a rate.

WHAT: Curated internal footer paths including legal + /it + /mcp-hub + /angebot + /ankuendigungen. RETURNS items[] {path,url}. Not a pixel-perfect HTML scrape; external directory URLs live on get_links / MCP_PUBLIC_LINKS via get_mcp_hub. USE to discover legal slugs before get_legal. NEXT: get_legal(doc), get_it, get_mcp_hub.

Retrieve approved GOV.UK/HMRC trust and inheritance-tax guidance by topic. Returns a title, official URL, and short summary. Not a live scrape of GOV.UK.

Fetch one public web page (buyer-supplied URL, no login walls, robots.txt honoured) and return its main content as clean Markdown with title and word count. Price $0.02 per call, paid with USDC over x402.

Same as /v1/scrape/markdown plus a structured summary (≤200 words), key points and entities produced by an LLM from the page text. Price $0.04 per call, paid with USDC over x402.

Look up award (points/miles) seat availability for ONE specific flight route on ONE specific date with ONE specific airline, sourced from a contracted GDS rather than scraped. Returns the flights found with cabin and seat count. IMPORTANT — this tool is strictly literal. Every argument takes a single concrete value: • origin / destination: exactly one 3-letter IATA airport code each. Not a city, not a list, not a region. • airline: exactly one 2-letter IATA carrier code (e.g. VS, CX, NH). Not an alliance and not a loyalty programme. • date: exactly one date, YYYY-MM-DD. Not a range and not a month. To cover several airports, airlines or dates, CALL THIS TOOL ONCE PER COMBINATION and combine the results yourself. Award space is scarce and volatile, so an empty result for one date says nothing about another — checking several dates is normal and expected. Interpreting the result: • seats is an availability indicator, not a guaranteed bookable count, and not a reservation. Low counts are the more precise signal; treat higher ones as less certain. Do not present any count as a firm number of seats a user can book. • cabin is one of business, first, economy or premium_economy. • An empty result means no availability was surfaced for that exact combination at that moment; it is not proof that the route never has space. • Availability changes fast. Treat every result as a point-in-time observation, not a reservation. If the call is declined for want of an API key, say so plainly and point the user at https://awardsecrets.com/api.html — access is in limited release and keys are issued individually. Do not invent availability, and do not substitute a guess for a result you could not retrieve.

Search live hosting offers across ~75 providers by RAM, vCPU, price, country and type. Prices are rescraped daily, so they are at most a day old. Returns a claim_url for each offer that the HUMAN should open in their browser to sign up.

Auto-populate the user's BrandKit (palette / fonts / tagline / logo / wordmark / boilerplate / voice notes) from files, a URL, or pasted text. Additive by default: fills empty fields, leaves populated ones alone. Idempotent: re-running the same inputs doesn't double-write. Overwrite rule: if the target brand kit already has an identity (a tagline/boilerplate/voice for a different brand), do not silently overwrite it. First ask the user whether to replace it. If the account supports multiple brand profiles, prefer creating a separate brand instead: pass a new `brand_id` slug plus `brand_name` rather than clobbering the existing one. Only pass `replace=true` once the user has confirmed they want this brand re-learned from the new source. Use when the agent has brand assets in scope (a working directory with logos / press-kit / brand-guide PDFs, the user's portfolio or Substack URL, pasted boilerplate copy) and wants to populate Niche's BrandKit so future signal_scan and content generation inherit the brand context. Agent-side equivalent of the Niche web app brand-kit ingest surface, same backend engine. Async, then poll: a URL or multi-file ingest runs in the background, so this call returns fast with {ingest_id, status:'ingesting'}. Then poll niche_brand_kit_ingest_status(ingest_id) until status is 'done'; that response carries the populated BrandKit, the ingest report (detected[] / skipped[] / errors[]), and a diff[] of changed fields. (Loop: ingest, then poll status until done/failed; same pattern as niche_signal_scan to niche_session_state.) Do not re-call ingest while one is running; a duplicate of the same inputs attaches to the in-flight job. URL ingest also fills voice primitives when the page has post-shaped text (Substack/blog/X). If a URL is slow or thin to scrape, the visual fields may land before the voice pass completes; when the report flags this, paste the page's About/homepage copy via `text=` to complete the brand voice.

Extract voice primitives (register / sentence rhythm / lexicon preferences / punctuation habits) from post-shaped text and persist onto the user's VoiceProfile. The voice primitives thread into content generation so generated copy matches the user's actual writing voice. Two input shapes: pass `posts` (list of pre-collected text snippets, ≥80 chars each) or pass `url` (the server scrapes post-shaped snippets from the page: Substack / Medium / blog / X profile). Inline posts win when both are given. Inline post-shaped snippets need to be the user's own writing, not press articles or marketing copy. Returns the extracted primitives + a diff of what changed on the stored VoiceProfile.