"How to check differences between files" matching MCP tools:

• connect_domainA

  LayeroA

  Connect a custom domain to a site. IMPORTANT: between this call and a working domain stands A PERSON. You get DNS records — show them to the user and explain they go in at their domain registrar. Do not wait for readiness: DNS propagates in minutes to an hour, the platform re-checks on its own, and you check later via `check_domain`. Spinning here burns time and context for nothing. The address can be passed as-is: the platform reduces `https://shop.example.com/page` to `shop.example.com` itself.

  ConnectorAPI key

• get_standingsA

  Agent Coliseum MCPA

  Check public rankings after battles. Returns agents with wins, losses, Elo-style rating, and tournament_id. Use this after get_result if you want to see how FREE Gladiator Badge winners stack up; it is not needed for the fastest fight flow.

  ConnectorNo auth

• campaignstack_explain_capabilitiesA

  campaignstackB

  Explain how the pieces of this workspace fit together, so you can pick the right tool without opening several to compare them. Call this when you are choosing between similar tools, when a request does not obviously map to one tool, or when an error tells you to consult it. topic: overview (default), watchers (how to choose between the eight ways to monitor something), workflows (how a workflow gets its leads, and which tool creates which kind), platforms (what can be acted on and what is tracking-only), outreach_and_safety (who sends, what the limits are, and what to confirm with the user first). It is a static reference and returns no live counts: each topic names the list tool that does (campaignstack_get_signal_agents, campaignstack_get_workflows, and so on). Costs nothing and reads no workspace data.

  ConnectorAPI key

• get_dataset_filesA

  gdex-mcpA

  Return a paginated file listing for a dataset or a specific group. Depending on how deep gindex is in the group hierarchy, this returns either actual file rows or another layer of subgroup summaries — there's no way to tell in advance which you'll get. If you get subgroups, read the gindex (or url) off a row and call again with that gindex to go one level deeper; gindex values are dataset-specific and can't be guessed. A shallow gindex on a large dataset can return a very large response (thousands of files) — the file-row portion of the response is capped at 500 rows (look for "_truncated": true). Two ways to avoid hitting that cap instead of drilling down group by group: pass filter_wfile with a filename pattern (e.g. a date like "20220808") to filter down to matching files, or page through a known group's results with `page`. filter_wfile only filters actual file rows, so it has no effect at a gindex that's still returning a subgroup summary rather than files — if a first attempt comes back unfiltered, descend one level (see get_file_groups) and retry there. Args: dsid: Dataset ID (dNNNNNN), e.g. d083002 gindex: Optional group index to filter files page: Page number to fetch (for a group with more files than fit on one page) filter_wfile: Filter files by name pattern, e.g. "20220808" to match a date fl: File list source (defaults to "web" server-side)

  ConnectorNo auth

• dropyour_whoamiA

  DropyourA

  Check how this session is authenticated: resolved tier (anonymous / free / pro) and its limits. Call this after configuring an account token (dyk_...) to confirm it is recognized — an invalid token silently degrades to anonymous.

  ConnectorNo auth

• assay_graveyardA

  mcpA

  Use this when you want to check, for free, how often a signal family (e.g. sma_cross) has already been falsified and what usually kills it, before spending a check. Anonymised stats only -- no buy/sell advice. Free lookup: how often has this signal family already died? Anonymised falsification statistics per structural signal family -- tested / killed / survived counts, top kill reasons, and the crowd prior your submission would be deflated by. Check BEFORE you spend weeks on an idea whether the crowd already buried it. k-anonymous: families with fewer than 5 distinct submitters fall back to coarser taxonomy stats. Price: free.

  ConnectorNo auth

• get_deployment_statusA

  NovenceA

  Poll publish state after deploy (queued, checking, promoting, live, failed). queued = waiting for a check runner (queuePosition shows your place); wait recommendedPollSeconds between polls. Omit deployment_id for the latest. Use get_checks_results for Lighthouse/a11y scores and get_preview_url once live. Read-only; do not retry deploy while queued, checking, or promoting.

  ConnectorNo auth

• match_invoiceA

  Ardaro Purchase Document ReviewA

  USE THIS WHEN the question is a quantity-allocation question: how much of this PO has been invoiced, whether an invoice is fully, partially, or over billed against the PO, or how much quantity remains. Aggregates split invoice lines against one PO line and returns a status per line - fully_invoiced, partially_invoiced, uninvoiced, or overbilled - plus remaining quantity. Matches by explicit PO line ID or a unique exact product code only, never by description. Inputs: one invoice plus one PO; it does not accept a receipt. DO NOT USE THIS to compare a receipt against an invoice, or for a general list of differences with no allocation question - call reconcile_purchase_documents instead; it is free and does not require calling this tool first or after. Paid: 0.50 USDC per accepted comparison, explicit buyer-authorized x402 payment. Call get_document_service_status with service='invoice' first to confirm current readiness and price. Advisory output only: human review required; no delivery verification, payment execution, prior-invoice history, or accounting writes.

  ConnectorNo auth

• match_invoiceA

  Ardaro Purchase Document ReviewA

  USE THIS WHEN the question is a quantity-allocation question: how much of this PO has been invoiced, whether an invoice is fully, partially, or over billed against the PO, or how much quantity remains. Aggregates split invoice lines against one PO line and returns a status per line - fully_invoiced, partially_invoiced, uninvoiced, or overbilled - plus remaining quantity. Matches by explicit PO line ID or a unique exact product code only, never by description. Inputs: one invoice plus one PO; it does not accept a receipt. DO NOT USE THIS to compare a receipt against an invoice, or for a general list of differences with no allocation question - call reconcile_purchase_documents instead; it is free and does not require calling this tool first or after. Paid: 0.50 USDC per accepted comparison, explicit buyer-authorized x402 payment. Call get_document_service_status with service='invoice' first to confirm current readiness and price. Advisory output only: human review required; no delivery verification, payment execution, prior-invoice history, or accounting writes.

  ConnectorNo auth

• get_usageA

  URLpipeA

  What the organization's plan allows, how much of it is left this period, and what each operation costs. Worth reading before a run of expensive calls: the operations differ by seventeen times in price, so the difference between fetch_markdown and summarize_page over a hundred pages is 100 credits against 1,700. It is also how to read a refusal — a call that comes back with quota_exceeded is telling you this number ran out.

  ConnectorAPI key

• get_usageA

  URLpipeA

  What the organization's plan allows, how much of it is left this period, and what each operation costs. Worth reading before a run of expensive calls: the operations differ by seventeen times in price, so the difference between fetch_markdown and summarize_page over a hundred pages is 100 credits against 1,700. It is also how to read a refusal — a call that comes back with quota_exceeded is telling you this number ran out.

  ConnectorNo auth

• get_ai_recommendation_resultA

  AI Recommendation CheckA

  Use this to read the result of a check started with check_ai_recommendation, using the check_id it returned. Returns the status (queued, running, done, failed or refused). When done: for ChatGPT, Perplexity and Gemini, how many of their answers named the business, which businesses they named instead, and one fix. While a check is queued or running, poll_after_s is the suggested wait in seconds before reading it again. It waits up to about 20 seconds for a running check to finish. It does not start a new check.

  ConnectorNo auth

• livereacting_get_import_statusA

  LiveReactingA

  Check how far an import started by livereacting_import_media or livereacting_import_from_url has got. Returns the status, a progress percentage and pollAfterSeconds, the number of seconds to wait before asking again. Poll no more often than once every 10 seconds: the account is limited to 150 requests per minute in total, and a tight loop spends that budget on nothing. `done` only means the transfer finished. It does not mean the file can be used: an imported video very often still needs encoding, and a playlist built with it is refused until that is done. Read `usable`, which is true only when the file can go straight into a playlist, and `nextStep`, which names the tool to call when it cannot. A YouTube playlist import answers for the whole group: `isFolder` is true and `files` lists each video with its own status. The fileId keeps working after the import finishes and can be polled again at any time. The `files` list reflects the videos that exist now, so it shrinks if one is deleted later. It names the videos but not their ids; call livereacting_list_media to get those.

  ConnectorAPI key

• deploy_siteA

  Porkbun (official)A

  Publish a website's files to a domain's Secure Static Hosting. TEXT FILES GO IN `text`, AS WRITTEN: for .html, .css, .js, .svg, .json, .txt and .xml send { path, text } with the file's contents exactly as you wrote them. Do NOT base64-encode text files; base64 is slow and error-prone for you and is only for binary files (images, fonts, PDFs), sent as { path, content }. A `path` may include directories (e.g. `assets/css/style.css`) — missing parent directories are created automatically. ≤10MB total per call (split larger sites across calls). Only static-web file types are accepted (html/css/js/images/fonts/…); server-executable types are rejected. Hosting must be ACTIVE (check get_hosting first). To change an existing site, read the current files first with read_hosting_file and edit them, rather than rebuilding from the visible page. When you build or edit a website for a domain in the user's Porkbun account (or they mention Porkbun hosting), this is how it goes live: offer to publish with it instead of giving dashboard upload steps, and get their OK first, since files at the same path are replaced.

  Connector

  Destructive

  OAuth

• upload_fileA

  Put It OnlineA

  Put a file online and get a short public link. Pass text directly, or base64 with encoding="base64" for binary files (images, PDFs, zips). An .html file becomes a web page; a .zip containing index.html becomes a website. Returns the URL, expires_at and a manage_token (shown once; anonymous callers need it to check or delete the link). Status may be "checking"/"publishing" (call get_link before sharing) or "unpublished" (not published). Limit 20 MB inline; use create_upload_session for bigger files.

  ConnectorNo auth

• compare_day_lengthA

  Sunvane Golden HourA

  Use this when the user asks for day length differences and average change per day between two local dates, or the solstices and equinoxes of a year. Returns daylight duration for each date and signed changes. Limits: cities with population 50,000+ (plus Tromso), dates/years 1900–2100, flat sea-level horizon; use either date_a and date_b or year, and not both. Does not forecast weather.

  ConnectorNo auth

• verify_changeA

  VeriduA

  Have Veridu review a code change you just made, before you commit or open a pull request. Independent reviewers check the change against the files you send (for PHP, Veridu also traces callers and overrides within them), findings that cannot be grounded in the code are dropped, and only problems both reviewers confirm can block. You get an outcome (pass / review / block) and concrete findings with file, line, severity and evidence. Send: `diff` = `git diff --no-renames <base>` of your change (include new files: `git add -N` first), and `files` = the FULL current content of every file the diff adds or modifies, keyed by repo-relative path. You may add up to a few closely related unchanged files (callers, interfaces) to `files` for context. Text files only; no renames, mode changes, symlinks, submodules or binaries. Limits: diff 256 KB / 60 files, files 512 KB total. After fixing findings, call again with the new diff. Veridu links it to the previous check of the same files (last 24 hours) automatically; pass `parent_change` = an earlier change_id only to link a different one. Up to two follow-ups per change do not count as a new review. Sending exactly the same change again returns the earlier result. Every finding has a `finding_id` that stays the same across follow-ups while the problem persists. A follow-up also returns `followup`: which ids persist, which came back (reported earlier in the chain, skipped last time), which are new (possibly introduced by your fix), and which are no longer reported, with `code_changed` saying whether the flagged line changed. "No longer reported" is not proof of a fix. Low-severity findings can be left out of the list but are still counted in `followup`. An identical resend returns the earlier result as it was. Each other new change counts as one review on the signed-in Veridu account. Results are advisory: Veridu sees only what you send, not the rest of the repository. If the review is still running after ~45 seconds you get a change_id and stage_label (what Veridu is doing now): tell the user that line, then call get_change with the change_id (do not call verify_change again for the same change).

  ConnectorAPI key

• icx_sync_deltaA

  Calera Infinite Context (ICX) — Persistent Memory & Associative RecallB

  Extracts fine-grained deltas between previous text/document state and updated state, and crystallizes them into the Volumetric Memory lattice in sub-2ms on CPU with automatic secret scrubbing and SHA-256 deduplication. Use this tool for continuous incremental sync of code files, documentation, PRDs, and database schemas. Mutating operation. Requires X-License-Key authentication.

  ConnectorNo auth

• suggest_siteA

  SwarmIndexA

  Submit a missing agent discussion board for human review. Check find_site first; use report_problem to correct an existing entry. url should be its public HTTPS home or documentation page without embedded credentials. In why, explain what agents do there and how you found it. The receipt acknowledges submission, not acceptance; there is no review-status lookup or guaranteed reply. An eligible suggestion is checked by the nightly watcher (does it answer, does it publish instruction files) before the owner decides. Identical submissions can be deduplicated; the submission limit is 10 per client per hour, with shared queue limits.

  ConnectorNo auth

• suggest_siteA

  SwarmIndexA

  Submit a missing agent discussion board for human review. Check find_site first; use report_problem to correct an existing entry. url should be its public HTTPS home or documentation page without embedded credentials. In why, explain what agents do there and how you found it. The receipt acknowledges submission, not acceptance; there is no review-status lookup or guaranteed reply. An eligible suggestion is checked by the nightly watcher (does it answer, does it publish instruction files) before the owner decides. Identical submissions can be deduplicated; the submission limit is 10 per client per hour, with shared queue limits.

  ConnectorNo auth

• leggi_copertura_datiA

  DatiTuristici.itA

  Reads which tourism figures the service holds and how recent they are: the latest year, how many comuni are covered, the last import, what each metric means and the 2025 break in the series. Use it to check how current the figures are, what a metric means or why a comune has a gap; do not use it to read the figures themselves (use leggi_dati_comune instead) or to find a comune by name (use cerca_comune instead). With a 6-digit `cod_istat` it adds the years with figures and with capacity for that comune and whether it has a projection and why not; without one `per_comune` is null. `aggiornato_il` is the time of the last successful import, null if none is recorded, not of the last check for new files; `profilo_territoriale` gives the year and the last import of the sources of the territorial profile. Read-only, public, no authentication; 30 requests per minute per client, shared across tools.

  ConnectorNo auth