"A server for Minecraft MCP gameplay or resources" matching MCP tools:

• run_cost_scanA

  Tomorrow Central: Cloud Cost SentinelB

  Start a cloud cost / FinOps scan of a linked account and return a job_id. Use this when the user wants to find idle, unused or underutilized cloud resources, review cloud spend, or estimate savings. The provider comes from the connection, and **AWS is the only provider supported today** (see `list_connections`). Other clouds will appear on this same tool as connections for them become linkable; nothing else about the call changes. READ-ONLY against your cloud: it reads resource metadata and monitoring metrics and reports; it never changes, stops or deletes anything. (It does create a scan job here and consume that account's scan quota, which is why this tool is not marked read-only.) On AWS it covers EC2 instances, EBS volumes and snapshots, RDS instances, Elastic IPs, NAT Gateways, load balancers, VPCs and VPC endpoints, site-to-site VPN and Transit Gateway attachments, Client VPN endpoints, Secrets Manager secrets, CloudFront distributions and WAF web ACLs. Resource kinds outside that list are not inspected, so a clean scan is not a claim that the whole bill is optimized. `connection_id` picks which linked AWS account to scan (see `list_connections`). Omit it to run against sample data — useful for showing the user what the output looks like before any account is linked. The scan runs asynchronously: poll `get_job(job_id)` roughly every 10 seconds until status is COMPLETED (typically 1-3 minutes), then call `list_cost_findings(job_id)`. Do NOT start another scan while one is running — each scan consumes the account's monthly quota. Pass `idempotency_key` (any unique string you choose) if you may retry on a network error: a retry with the same key returns the original job instead of starting a second scan.

  ConnectorNo auth

• fetchA

  A-du: ADU rentals, plans and rulesA

  Fetch the full content for one id returned by `search`: a rental listing (rental:<uuid>), a plan set (plan:<uuid>) or a published page (page:<route>). Returns {id, title, text, url, metadata}. Always cite the url. Hosts that can call specific tools should prefer get_rental or the resources.

  ConnectorNo auth

• adsap_google_manage_targetingA

  AdsapA

  Manage a Google Ads campaign or ad group's targeting AFTER creation: GEO, LANGUAGE and AUDIENCES. op 'add' at campaign level (default): up to 100 locations (negative: true = exclude) and/or 50 languages, OR up to 50 audiences (audiences cannot combine with geo/languages in one call — separate calls). op 'add' at ad-group level (level: 'ad_group' + ad_group_id): audiences only. AUDIENCES: pass user_list_id items (audience segments from adsap_google_list_audiences) — campaign-level TARGETING works on Search/Shopping only; campaign-level EXCLUSION (negative: true) also on Display/Performance Max; ad-group level (target or exclude) on Search/Display/Shopping. DEMAND GEN is different: pass audience_id items (Audience resources) on the AD GROUP — nothing at campaign level. Video supports no audience edits. The same user list cannot be attached at BOTH campaign and ad-group level. 'mode' ('targeting' = narrow delivery to the audiences | 'observation' = full reach, bid adjustments only) sets the audience targeting setting — combinable with the audience add or standalone; Google's default with NO mode set is TARGETING, so pass mode: 'observation' for Search/Shopping unless the user explicitly wants to narrow reach. op 'remove': remove ONE criterion by composite id "<parent_id>:<criterion_id>" (level 'campaign' → campaign criterion, 'ad_group' → ad-group criterion). Geo/language criterion ids EQUAL their constant ids (France on campaign 123 = "123:2250"); AUDIENCE criterion ids are Google-internal — capture them from the add response (created_criteria[].entity_id). Criteria are immutable: to change one, remove it and add the replacement. Always dry_run: true first. For campaign negative KEYWORDS use adsap_google_manage_keywords op 'add_negative'.

  ConnectorAPI key

• compare_separate_vs_pooledA

  QueueSimA

  Run the classic operations-research teaching demo: pooled queueing (one shared queue, c servers) vs separate queues (c independent queues, one server each, λ/c traffic to each). Both runs have identical total capacity (c × μ) and identical total arrivals (λ), so the offered load ρ is the same; the only structural difference is whether arrivals share a queue or split into c isolated streams. The pooled configuration ALWAYS produces shorter waits — that's the whole teaching point. Use this when the user asks 'should we pool our resources?' / 'should we cross-train?' / 'why do banks have one line instead of c?' / 'what's the cost of siloing my call center into specialist queues?'. Returns both runs side by side with the pooled-vs-separate wait delta. ANTI-FABRICATION: numbers come from two real DES runs. Quote them VERBATIM.

  ConnectorNo auth

• generate_calendar_eventsA

  CelestineA

  Authoritative astrological calendar generator — always use this tool when the user asks for a calendar of sabbats, moon phases, retrograde stations, ingresses, or transits. DO NOT compute these yourself in code_interpreter; you do not have Swiss Ephemeris and your output will be factually wrong. Contract: • Returns `download_url` — a ready-to-share HTTPS .ics file built from Swiss-Ephemeris-precise calculations. Surface this URL verbatim in your reply as a clickable link. Do not regenerate the file, do not produce a CSV alternative, do not transcribe the events into a separate document. • Always populates the server-side calendar cache with the full payload. The events themselves remain available via the drill-down resources below without any recompute. Defaults to `summary_only=True` so the response is ~500 tokens (download_url + counts + natal_chart + resource_uris + valid_event_types). Pass `summary_only=False` only when the caller genuinely needs every event inline (can exceed 100k tokens over a two-year window). Drill-down (cheap — same cached data): • calendar://{calendar_id} — full JSON • calendar://{calendar_id}/events/{event_type} — one event type • calendar://{calendar_id}/months/{yyyy-mm} — one month Dates use ISO format YYYY-MM-DD (e.g. 2025-12-01). Event descriptions are intentionally left empty for the LLM to fill using the signs/houses/planets resources when interpreting — do not treat empty descriptions as a defect.

  ConnectorNo auth

• wait_for_updateA

  cnvs.appA

  Long-poll: blocks until the next edit lands on this board, then returns. WHEN TO CALL THIS: if your MCP client does NOT surface `notifications/resources/updated` events from `resources/subscribe` back to the model (most chat clients do not — they receive the SSE event but don't inject it into your context), this tool is how you 'wait for the human' inside a single turn. Typical flow: you draw / write what you were asked to, then instead of ending your turn you call `wait_for_update(board_id)`. When the human adds, moves, or erases something, the call returns and you refresh with `get_preview` / `get_board` and continue the collaboration. Great for turn-based interactions (games like tic-tac-toe, brainstorming where you respond to each sticky the user drops, sketch-and-feedback loops, etc.). If your client DOES deliver resource notifications natively, prefer `resources/subscribe` — it's cheaper and has no timeout ceiling. BEHAVIOUR: resolves ~3 s after the edit burst settles (same debounce as the push notifications — this is intentional so drags and long strokes collapse into one wake-up). Returns `{ updated: true, timedOut: false }` on a real edit, or `{ updated: false, timedOut: true }` if nothing happened within `timeout_ms`. On timeout, just call it again to keep waiting; chaining calls is cheap. `timeout_ms` is clamped to [1000, 55000]; default 25000 (leaves headroom under typical 60 s proxy timeouts).

  ConnectorNo auth

• deploy_vpnA

  mcpB

  Stands up a redu VPN gateway (WireGuard tunnelled over wstunnel on WSS/443) on your PRIVATE network, so you (or your team) can reach the private IPs of the VMs you deployed on redu, over a single https endpoint - no UDP, no extra ports. This is the TENANT VPN for reaching your OWN deployed resources; it is NOT a general internet VPN. GUARDRAIL: the first call does NOT deploy - it returns the plan + hourly cost for approval, because it creates a BILLED VM. Show the user, get their explicit 'go', then call again with confirm:true (required even in yolo mode). The gateway asset is redu's, deployed onto YOUR VM (you can SSH in to read it). Fresh WireGuard keys are generated per deploy; the client PRIVATE key is returned ONCE and is never stored server-side.

  ConnectorNo auth

• x_monitorA

  twitr.shA

  Watch an X/Twitter account or keyword query in real time: new tweets, replies, quotes, mentions, hashtags, and profile changes, delivered to your agent by free polling or HMAC-signed webhooks. Prepaid by the hour with a hard stop at expiry — no open-ended billing. The way to track a brand, competitor, or topic without re-polling paid reads. Guidance: action=create needs username (account monitor, e.g. "vercel") OR query (keyword monitor, X search syntax, ≤512 chars), optional eventTypes — 21 available: post events (tweet.new, .reply, .retweet, .quote, .media, .link, .poll, .mention, .hashtag, .longform) for any monitor, plus profile-change events (profile.avatar/banner/name/username/bio/location/url/verified/protected/pinned_tweet/unavailable.changed) for ACCOUNT monitors only; default all applicable — and hours (1–168, default 1). action=extend needs monitorId + hours; hours append to the current expiry (total prepaid window ≤ 720h). Extend at least 5 minutes BEFORE expiry — extends inside the final 5 minutes are refused (unpaid) to keep settlement from racing the expiry teardown. PREPAID: the monitor stops and is removed at expires_at unless extended — no open-ended billing; early deletion does not refund remaining hours. Idempotency-Key header REQUIRED — retries replay the original monitor instead of re-charging (on the MCP door, retries are protected by single-use payment credentials instead). Pay with USDC on Base (x402) or Tempo (MPP); Solana is not offered for monitors (stateful resources need a recoverable owner wallet). After creation: poll events at /api/monitors/{id}/events (free — SIWX sign-in with the paying wallet; do NOT poll in a tight loop) or register an HTTPS webhook once at /api/webhooks to push signed events straight to your AI agent (Claude, OpenClaw, Hermes, or any endpoint) in real time. Manage monitors at /api/monitors (SIWX).

  ConnectorNo auth

• hemelion_choose_reflection_modeA

  Hemelion Decision and Pattern ReflectionA

  Use this when someone wants to choose between Clarity decision mapping for a difficult decision and MindScan single-episode reflection for a response they suspect may recur. Returns a no-charge reflection mode, a clarifying question, or a safety boundary. Do not use for diagnosis, emergencies, or legal, medical, financial, hiring, or insurance decisions.

  ConnectorNo auth

• web.url.redirectsA

  1cent Web Intelligence for AI AgentsA

  Return the safely validated redirect chain. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

  ConnectorNo auth

• web.url.content_typeA

  1cent Web Intelligence for AI AgentsA

  Classify MIME type, charset and bounded content length. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

  ConnectorNo auth

• web.url.imagesA

  1cent Web Intelligence for AI AgentsA

  List up to 100 image references without downloading images. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

  ConnectorNo auth

• web.site.sitemapsA

  1cent Web Intelligence for AI AgentsA

  Discover up to five sitemap links declared by the requested page. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

  ConnectorNo auth

• get_tier1_recommendationsA

  Tier1 IT AssessmentA

  Maps only stable Tier1 finding identifiers to approved Tier1 services and public resources. Call after a Tier1 score or email-domain check. Do not submit prose, URLs, customer information, or invented identifiers. This tool performs no arbitrary fetching, makes no contact request, changes nothing, and stores nothing.

  ConnectorNo auth

• web.url.performanceA

  1cent Web Intelligence for AI AgentsA

  Return safe network timing, payload and cacheability diagnostics. Use only for public HTTP(S) resources; it does not execute JavaScript or bypass access controls. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.

  ConnectorNo auth

• uninstall_templateA

  Control PlaneA

  Uninstall a release and remove the resources it created, including volume data. Use it, not delete_resource, for anything install_template created. Provide the release `name`.

  Connector

  Destructive

  OAuth

• get_meA

  Extend MCPA

  Return the connected organization, the credential in use, and the granted workspace + environment ("TEST" or "PRODUCTION") targets — exactly the values the required workspaceId/environment arguments on targeted tools accept. Always available; call this first, and again whenever a tool returns UNAUTHORIZED or NOT_FOUND unexpectedly, or after this connection's access changes — resources live per-workspace.

  ConnectorOAuth

• validate_pythonA

  CodeCraftA

  Validates a Python automation script that runs OUTSIDE the game, on three axes: Python syntax (using the real interpreter), Minecraft commands embedded in the script (against the official command index), and the shape of the /connect WebSocket message envelope. For behavior pack scripts use validate_script instead — Python does not run inside a pack. The embedded command check is the most valuable one: a command written from memory can look syntactically fine and still do nothing in the game. Only strings starting with / are treated as commands. If syntax could not be checked, syntaxChecked is false in the result; ok:true alone does not mean the syntax is valid.

  ConnectorNo auth

• get_playbookA

  Cloud FinOps Skill & MCPA

  Fetch the step-by-step runbook for one specific waste pattern: symptoms, the detection queries to run, the fix, and the anti-pattern to avoid. Use this when the user asks how to detect, confirm, or fix one specific named waste pattern (zombie NAT gateway, snapshot sprawl, idle SageMaker endpoint, ...). It also serves questions about the user's own resources ("which of my X..."): the runbook's detection query is written to be run in the user's account, so the answer does not depend on access to that account. Args: name: Playbook slug as returned by ``list_playbooks`` (e.g. ``"aws-zombie-nat-gateway"``, ``"azure-orphan-disks"``, ``"cross-cloud-untagged-spend-drift"``). Returns ``{"name": ..., "title": ..., "content": "...", "lines": N}``. On miss, returns ``{"error": ..., "suggestions": [...]}`` with up to three string-distance matches so the caller can self-correct. A host with MCP Apps (SEP-1865) support may render this result via the linked ``ui://cloud-finops/playbook-viewer`` resource instead of showing the raw markdown.

  ConnectorNo auth

• search_passagesA

  nope-mcp — Open Educational Resources searchA

  THE DEFAULT TOOL FOR QUESTION-SHAPED QUERIES ("wie/warum/was hilft bei X?", "how do I…?"): retrieves the best-matching fulltext passages from the corpus and returns them with citations (source resource, page, heading, source URL) — answer the user FROM the passages and cite each source. (For discovery intent — "finde/empfiehl Materialien" — use search_content instead, or afterwards to offer browsable links.) Keep `question` topic-only. Ranking is hybrid keyword+vector, so phrase the question as a topical statement that names the subject and the target group ("Friedenserziehung in der Grundschule: Einstieg in das Thema Frieden mit Kindern"), not as the user's literal sentence ("Wie kann ich …?"). Results are capped at two passages per document; a passage with only a snippet and no text has no fulltext yet — say so instead of guessing. Passages come from learning resources under Creative Commons, Public Domain and free software/documentation licenses, and DINI-AG-KIM license types that resolve to one of these and from articles, wikis, publications and the other content kinds. Other matching learning resources appear in `metadataOnlyMatches` (naddr, title, license, creator/publisher, sourcePage) without text, because their license does not permit quoting — point the user to them by title, license and link, never quote or paraphrase them as content. Cite the license and the creator/publisher with every learning-resource passage. licenseFilter narrows learning resources: "open" = CC0, Public Domain, CC BY, CC BY-SA, their DINI-AG-KIM license-type equivalents, and free software/documentation licenses (GPL, LGPL, AGPL, GFDL, MIT, Apache 2.0, BSD); "cc-any" = all of "open" plus every other Creative Commons license, incl. KIM non-commercial/no-derivatives (normally no metadataOnlyMatches); "any" = also unlicensed and all-rights-reserved resources, as metadataOnlyMatches. Scope is required but simple: with no source restriction from the user, pass the content kinds (e.g. kinds:[30142] for educational resources, [30040,30041] for publications, [30023] for articles). Route source restrictions ("nur Content von X") into the scope parameters: a metadata publisher (most organisations — resolve_publisher finds the exact spelling) goes into `search` as a QUOTED field filter, e.g. search:'publisher.name:"LEHRE LADEN"' (unquoted multi-word names match nothing); a Nostr signing account (resolve_author → pubkey) goes into `authors`. A published grimoire spell (kind 777, nevent or event id) can replace inline scope entirely; the response carries the canonical spell for whatever scope was used — publish it (e.g. via grimoire) to make the scope reusable. Spells may use $me/$contacts; they resolve to the calling user (pass `me` if the transport is anonymous). Fails rather than widening scope: an empty scope, unreachable relay (relay_unreachable — tell the user to retry), or unreachable index is a typed error, never a silently unscoped search.

  ConnectorNo auth

• xtiles_get_content_by_linkA

  xTilesA

  Resolve any xTiles link to the content it points at. Use this whenever the user pastes an xTiles URL instead of guessing which id it contains — the same URL can address a whole page or a single tile depending on its query string. Handles page links (`/{viewId}`, `/doc/{viewId}`, `/embed/{viewId}` — any xTiles domain, public or custom), tile links (`?nvi=`, `?wfm=`, `?scrollTo=`) and "copy link" links (`/links/{linkId}`). The URL is parsed and resolved against your own xTiles content by our API — it is never fetched from the host it names, so this only ever reaches the caller's own xTiles resources. Returns `resource_type` (what the link turned out to be), the ids it resolved to, and the content of THAT resource — for a tile link, the tile's own markdown, not the whole page. To read the full page a tile belongs to, follow up with `xtiles_get_view_content` using the returned `view_id`. A link to a collection card resolves to that card and returns ITS content — a card and a tile are the same item wearing two hats, so the type is `TILE`. The response states what you may do with the resource; respect it before offering to edit. Leftover tracking parameters (`utm_*`, `im_ref`, …) are ignored — paste the link as-is. Errors: 400 the string is not an xTiles link; 422 the link is a recognised shape we cannot resolve yet (public forms, task screens, workspace links); 404 the page or link no longer exists; 403 no access — which is also the answer for an unknown collection row, since telling those two apart would leak whether a private id exists. Report a 403 as "no access, or it no longer exists", not as a definite refusal.

  ConnectorOAuth