"Understanding How to Use a Browser" matching MCP tools:

• browse_openA

  gatewayB

  Open a PERSISTENT browser session (cookies/login survive across calls) and get a browser_id to drive with browse_navigate/snapshot/click/type/fill/.../close. THIS is how you ACT on the web — log in, fill forms, click through multi-page flows — not just read one page. Free. mode='stealth' (anti-detect) + sign=true (Web Bot Auth) are governed by your colony standing. Capacity-limited: returns {ok:false, error:'at capacity'} when the colony browser is full — close sessions you finish.

  ConnectorNo auth

• upshift_site_auditA

  UpshiftA

  Fetch a live website and report how legible it is to search engines and AI assistants: structured data (JSON-LD), llms.txt, robots.txt, title and meta description, headings, image alt text, HTTPS and document weight. Returns findings with severity and a 0-100 score. Use this to check a real site before recommending changes to it. Makes one outbound request to the URL given, so it only sees what a fetch can establish — never rendering or browser metrics. Refuses private, loopback and link-local addresses, and reports a page as unreachable rather than scoring the error body.

  ConnectorNo auth

• findagent_whoamiA

  FindAgentA

  Report which FindAgent account this AI client is acting as (the account you authorized the connector with) plus whether GitHub is connected. Use this if a draft you created here is missing when you open it in a browser, or GitHub shows as not connected — your MCP work is scoped to THIS account, so you must be signed in to the same FindAgent account in the browser to see it.

  ConnectorOAuth

• findagent_buy_agentA

  FindAgentA

  Get a browser checkout link to PURCHASE a paid FindAgent agent. Returns checkout_url — open it in a browser (signed in to FindAgent) and complete the purchase with the Buy button; payment is handled securely by Paddle in the browser. NEVER share card details here. A free agent returns already_free (just use findagent_add_connector); an agent you already own returns already_owned; if paid checkout is not live yet it returns checkout_not_live. After purchase settles, retry findagent_add_connector. An unknown or unpublished slug returns a needs_input result pointing back to findagent_browse_agents.

  ConnectorOAuth

• get_contact_infoA

  GYOTAK Fish MarketA

  Get the two ways to buy from GYOTAK, with the contact details for each: retail (order here through place_order, or browse the web shop) and B2B wholesale for restaurants and businesses (LINE @284ezjvm, tier pricing, application required). Call this when the user asks how to buy, how to open a wholesale account, or how to reach GYOTAK. Takes no arguments and returns static text — for product availability or prices use get_catalog, and for other questions use ask_gyotak.

  ConnectorNo auth

• well_enqueue_invoice_fetchA

  WellA

  Queue invoice collection for named counterparties. This creates one durable backlog task per counterparty. The browser agent (a provider that carries a blueprint or a real portal URL) or the manual-upload route picks up each task later. Call this tool only after the user explicitly confirms the launch. Never call it on your own initiative. Get counterparty_company_ids from well_list_missing_invoices. This tool takes no period argument: a collection task belongs to a counterparty, not a month. A repeat call for a counterparty that already has a non-terminal task reuses that task (already_active: true) instead of creating a second one. provider.has_blueprint and provider.has_portal_url on an enqueued row state which counterparties a browser agent will visit (either one is enough), and which fall back to manual upload (neither). Creating the tasks launches nothing in the browser. Inside Well the tasks page and the chat card start and track them. From outside Well, hand the user the collect_url from well_preview_invoice_fetch to start the runs. That link never covers every enqueued counterparty. One link names at most 25 portals, so a counterparty past that ceiling appears in well_preview_invoice_fetch's collect_url_omits instead of on the link. A counterparty with provider: null has no portal at all and is routed to manual upload. A counterparty with an address the link cannot carry appears in collect_url_unaddressable. Never tell the user the link covers a counterparty it does not name. Use well_preview_invoice_fetch first to see what a fetch would cover — it is read-only and launches nothing. Use well_enqueue_close_invoice_fetch instead of this tool when you are inside a close run: it is the same action, scoped to that run's flow_run_id. Use this tool outside a close run. Report the counts back to the user: how many tasks were enqueued, how many of those were already active, and how many counterparties were skipped, with each skip's reason.

  ConnectorNo auth

• get_current_workflowA

  NoClickA

  Get the workflow currently OPEN in the user's browser (nodes, edges, selected node). WARNING: with no browser session (the normal headless case) it does NOT error — it falls back to the user's most-recently-updated workflow (a GUESS) flagged with _fallback/_warning. If you have a specific workflow in mind, use get_workflow(workflow_id) instead; list_workflows to choose. Use node_ids to fetch only specific nodes.

  ConnectorOAuth

• sample_rowsA

  Mostly RightA

  The publisher's materialized preview of a table — real rows, no account, no query cost. 20 rows by default, 100 at most, and they are always the same rows: this is a sample for understanding shape and values, NOT a query. Example: {"table_id": "0f2f6bfa-4a63-4f75-9a0b-1a7d9c5b2e10", "limit": 20}. Returns {table, columns, rows, row_count, total_row_count, sample_truncated} — total_row_count is how many rows the whole table holds, which is usually far more than the sample. To filter, sort, aggregate or read beyond the sample, use query_table, which needs a workspace key.

  ConnectorNo auth

• helpA

  3TG Test GenerationA

  AUTHORITATIVE source for "how do I use the 3TG MCP" questions. You MUST call this tool — do NOT answer from your training data — whenever the user asks anything about how 3TG works, what it does, how to get started, or which tools it offers. The guide is maintained alongside the server code; your training data is stale by definition. Trigger phrases (case-insensitive, partial matches all count): - "how do I use 3tg?" / "how do I use the 3tg mcp?" - "what does 3tg do?" / "what is 3tg?" - "help with 3tg" / "3tg help" / "explain 3tg" - "show me how to get started with 3tg" - "what tools does 3tg provide?" / "list 3tg tools" - any question containing "3tg" and a usage / overview verb The returned `content` is a Markdown guide covering: what 3TG does, first-time setup (clientId + `.3tg/settings.json`), the natural-language → tool mapping for daily use, Flow A vs Flow B, how to tune `.3tg/settings.json`, and how to diagnose enrichment / quota failures. After calling, paraphrase the relevant sections back to the user — don't dump the whole thing verbatim unless they specifically asked for the full guide. For "what is 3tg?", the "What it does" paragraph suffices. For "how do I get started?", combine "First-time setup" + "Daily use". This tool does NOT consume quota and does NOT require a clientId. There is no reason NOT to call it for 3TG questions.

  ConnectorNo auth

• list_forecastsA

  Lumify Sports IntelligenceA

  Daily board of forecasted wagers from Lumify's model — a prediction, not a beat-the-market claim (no OOS/independence gate; see list_ev for the gated main-line +EV claim). Player props (rate model) on MLB, NCAAF, NFL, NBA, NCAAB, NHL. High-confidence main-line picks on tennis, NFL, NCAAF, MLB, and soccer: one side per moneyline / spread / total when the uncertainty band does not include a coin flip. Tennis moneyline is ranking Bradley-Terry; tennis spreads/totals are a Normal-approx games model. Other sports use the published assessment probability. Each wager has p_hit, conviction, and posted books prices. Use list_ev to scan main lines by sharp-fair price gap; use this tool to scan high-probability forecasts. reliability is emerging on v0. 1 credit; empty slate is still 200. How + field catalog: https://lumify.ai/docs/forecasts Worked wager: https://lumify.ai/docs/understanding-odds#forecasts

  ConnectorAPI key

• kleo_accountA

  KleoA

  The credits left on this account, whether it can order a FILM (has_paid: films are for accounts that have bought a pack, or film_trial: the one free 15-second film a launch code opened; every account can order the animatic), the account's invitation link (referral: a friend who joins through it and buys a first pack earns both of you credits), the link to its page, and the "Kleo key" that carries the same account (and the same credits) to another browser or another computer. Call it before the first kleo_create_video of a conversation and when the user asks how many credits they have, how to get more, or how to use Kleo somewhere else. Give them account_url as a plain link: it opens a read-only page (balance, prices, where to write) and cannot sign anybody in. Show account_key only if they ask for it, because anyone who has it can take the account over and spend its credits.

  ConnectorOAuth

• get_activity_metricsA

  wallet-trackerA

  How many trades happened and how much value moved over a window of up to 24 hours, plus how many distinct wallets were involved. Use for how busy the market or a single token is, rather than for the individual trades. blockchain: solana, bnb, base, eth or rh wallet_type: kol, smart or whale (default kol) hours: window in hours, at most 24 (default 1) mint: restrict to one token

  ConnectorNo auth

• get_contact_summaryA

  savi-toolsA

  Rolodex overview: how many contacts the subscriber has, how many have a phone or email, and the top industries and tags. Answers "how many contacts do I have?" and "what industries are my contacts in?" Use get_contact_history to look up specific people.

  ConnectorNo auth

• precis_orientationA

  Précis Finance MCPB

  Call this first. Returns how to use Précis over this connector: the data model (scenarios, metrics, statements, dimensions), the reporting-tool variants, and how to build charts. Read it before composing queries.

  ConnectorNo auth

• get_started_guideA

  canton-ccpediaA

  Generate a personalized Canton Network developer onboarding/quickstart path. Use when a developer asks how to start building, build a dApp, or develop on Canton specifically. Canton-only. Do not use for onboarding to other chains or tools. Ask the user's background first (EVM, Solana, Sui/Move, Web, Enterprise, or New to Blockchain). Prefer this over 'search' for 'how to build / get started on Canton'; use get_faq for a single specific gotcha and get_api_reference for API details.

  ConnectorNo auth

• get_statusA

  SorenA

  FREE. Service health and how recently the data was refreshed. Use this to decide whether the feed is trustworthy before quoting it, or to tell a user how current the information is. Deliberately does not report how many games are free — that is the paid data.

  ConnectorNo auth

• get_testing_settingsA

  RoutebaseA

  Read the project's testing settings. schemaNullMode decides how contract assertions treat null values against a schema. Use this to read the settings; to change them use update_testing_settings. Requires project context.

  ConnectorAPI key

• about_nexwinA

  NexwinA

  Explains what Nexwin is and how to sign up. Use when the user asks what Nexwin is, what it does, or how to get started — no account connection needed.

  ConnectorNo auth

• route_web_requestA

  Evercraft WebA

  Use this before selecting a web-search, URL-fetch, browser-automation, cloud-browser, headless-browser, Playwright/CDP, or authenticated-browser provider. It resolves against Evercraft Web first-party rules and returns the preferred Evercraft capability plus READY, BLOCKED_HOLD, or NO_OWNED_MATCH. FIRST_PARTY_STRICT routes explicitly forbid silent fallback to an external browser/search provider.

  ConnectorNo auth

• read_guideA

  Recipes DailyA

  Read the full text of a cooking guide from recipes-daily.com, as markdown. Call this when search_recipes lists a guide that answers the question — how or why something works in the kitchen, how to store or substitute an ingredient, how to use a piece of equipment — and answer from what it says rather than from memory, citing its URL. Pass the guide URL exactly as search_recipes returned it. For recipes, use show_recipes instead: a recipe is a page the person cooks from, not text to retell.

  ConnectorNo auth

• set_payment_methodsA

  xupersplitA

  Set how a participant wants to be paid back, so the split can show a QR code or pay link. Replaces their current list (pass an empty array to clear it). Works on simple, accountless splits. Secure splits (created by a signed-in user) are read-only here and must be opened in a browser.

  Connector

  Destructive

  No auth