"Elastic Cloud" matching MCP tools:
- 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
- Start linking a cloud account so it can be scanned. `provider` is "aws", the only provider supported today; `account_id` is the 12-digit AWS account number. `software` is the Tomorrow Central software the link is for; omit it for Cloud Cost Sentinel. Each software has its own read-only role, so link once per software. This is a two-party flow and you cannot finish it alone — creating the read-only IAM role requires the human's AWS credentials. Returns a `launch_url`. Hand the human these instructions verbatim: 1. Open the launch_url (a pre-filled CloudFormation quick-create link). 2. Review the read-only role it creates, then click Create stack. 3. Tell you when the stack says CREATE_COMPLETE. Then call `verify_connection` with the returned connection_id. Verification fails with a clear message until the role exists, so polling it every ~15 seconds is safe and expected. No ARN or secret needs to be copied by anyone.ConnectorNo auth
- The person's cloud boxes, newest first: state (waking, working, idle, asleep), what it's doing now, the last ask and the last reply. With `box`, that one box with its recent thread and the whole last reply — poll this every 20–30 s after start_box or message_box until state is idle and last_reply is set (a turn takes from seconds to many minutes).ConnectorOAuth
- Run a multi-step attack chain against a cloud account connected to Mitigant. Returns the result if every step finishes within wait_seconds (default 20); a multi-step scenario usually takes longer, so expect it to return at once with the attackId and status RUNNING while it keeps running -- then poll get_attack_status with that attackId, and never launch it again (that would start a second scenario). This performs real actions on real cloud infrastructure, as several attacks in sequence -- it is not a simulation, and its blast radius is the combined blast radius of every step. Confirm with the user before calling: if their request could match more than one scenario in list_scenarios, show them the matching candidates with their names and descriptions and have them pick one -- don't guess which scenario they meant.ConnectorDestructiveNo auth
- Compare 2-3 developer tools, libraries or programming languages side by side. Returns each entry's full Markdown-KV block separated by "===". Alternatives and worksWith are enriched with tagline + agent-readiness for resolved slugs. If any requested slugs are not found, they appear in a trailing "Note: slugs not found: ..." line; the comparison still returns for the ones found. Examples: - Three search engines: {slugs: ["meilisearch-oss", "algolia", "elasticsearch-oss"]} - Two ORMs: {slugs: ["drizzle-orm", "prisma"]} - Three auth providers: {slugs: ["auth0", "clerk", "keycloak"]} - Hosted vs self-hosted for the same vendor: {slugs: ["redis-cloud", "redis-oss"]} — shows deployment trade-off - Postgres engine vs hosted offerings: {slugs: ["postgresql", "supabase-cloud", "cockroachdb-cloud"]} - Two languages for a CLI: {slugs: ["go", "rust"]} Edge cases: - Cross-category comparisons (e.g., {slugs: ["auth0", "redis-cloud"]}) are allowed but rarely useful. Same-category comparisons answer "which should I pick?" better; cross-category answers "these coexist in my stack" — a compatibility question. - Minimum 2 slugs, maximum 3. Four or more is a validation error; for more, run pairs. - Invalid or unknown slugs are listed under "slugs not found"; the partial comparison returns for valid ones. - Duplicate slugs in the array are deduplicated. - A few tools are single entries (no -cloud/-oss split): stripe, auth0, firebase, twilio, openai, pinecone, algolia. Don't pass "stripe-cloud" — it doesn't exist. Risk: read-only, closed-world, idempotent — no state change possible.ConnectorNo auth
- Score the next nights for stargazing at a location (0-100 per night). Use for "when should I stargaze this week near X", "is Saturday any good for the Milky Way", trip planning. Each night combines the three-layer cloud-cover forecast, moon illumination and up-fraction, and the astronomical-darkness window; `best_window` names the best upcoming night. Also returns the location's light-pollution estimate (approximate Bortle class + what's visible at that darkness). Args: lat: Latitude in decimal degrees (-90..90). You know city coordinates — pass them. lon: Longitude in decimal degrees (-180..180). nights: How many nights ahead to score, 1-16 (default 7; forecasts beyond ~7 nights are increasingly uncertain). Returns {timezone, light_pollution, nights:[{date, darkness, moon, cloud, score:{value, band, summary}}], best_window, uncertainty_note, attribution}. Present scores/verdicts verbatim; skies beyond ~7 days are provisional.ConnectorNo auth
Matching MCP Servers
- AlicenseAqualityAmaintenanceEnables MCP-compatible AI clients to retrieve FinOps-aligned knowledge and runbooks on demand, covering cloud cost optimization across AWS, Azure, GCP, and OCI, AI inference economics, Kubernetes, data platforms, allocation, chargeback, anomaly management, and waste detection.775CC BY-SA 4.0
- AlicenseAqualityBmaintenanceEnables AI clients to assess infrastructure-as-code deployment risk, generate incident response runbooks, review CI/CD delivery readiness, and calculate SLO error budgets through structured advisory tools. Runs locally over stdio without cloud credentials or external API calls, returning guidance for platform work, pull request review, and production readiness checks.12119 npmMIT
Matching MCP Connectors
Fatture in Cloud MCP server for ChatGPT, Claude and any AI agent: create invoice, send to SDI, add client, record expense and list unpaid invoices in your own Fatture in Cloud account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Fatture in Cloud yourself; Cotlet does not store your password and you need no Fatture in Cloud API key. About the official Fatture in Cloud API: Yes, Fatture in Cloud has a documented REST API (v2) for issued invoices, clients, received documents, e-invoices to SDI and attachments (checked 14 Oct 2026), but it has no official MCP server. To use it you register an OAuth 2.0 app, or create a manual access token in the web app, choose scopes and pick the companies the token applies to. Setup and FAQ: https://cotlet.dev/integrations/fatture-in-cloud-api-mcp-server
Transfer and sync files between 19 cloud storages (Yandex, Google, VK, Telegram, S3)
- Turn the Cloudflare proxy (orange cloud) on or off for a domain's DNS records. NOTE: connecting a domain deliberately imports every record DNS-only (grey cloud), because changing how traffic is served at the same time as changing who serves DNS makes failures hard to diagnose — so proxying is a separate, explicit step, best done AFTER confirming the site still works. Defaults to every proxiable record; pass `records` to target specific names ("@" = apex, bare labels like "www" are expanded). Only A/AAAA/CNAME can be proxied; anything else comes back under `skipped` with a reason rather than failing. Proxying hides the origin IP, so if MX points at a name you're proxying, mail to it breaks — that comes back in `warnings`. Reversible: call again with enabled=false. Use dry_run to preview.ConnectorDestructiveOAuth
- Starts a backup of the server’s system disk now (the option must be enabled; at most 2 manual backups kept). The server is BRIEFLY INTERRUPTED (shut down then restarted automatically, a few minutes). Two steps: call without confirmationToken to get the warning and a token, ask the user, then call again with the token. (permission: servers:backup) [Requires a free GPU Cloud account and MCP key]ConnectorNo auth
- List the provisioned VM nodes of an Ankra-managed cluster (Hetzner, OVH, UpCloud, DigitalOcean, Scaleway, AWS, Ankra Cloud, Proxmox, or HPE Morpheus): every control-plane and worker server plus the cluster's single bastion/gateway node, with id, name, role, node group, instance type, observed Kubernetes version, location, lifecycle state, IPs, and the cloud provider's live status/power state when available. Use this before restart_node to find the exact node to target - each node's 'is_bastion_or_gateway' flag identifies the bastion/gateway even though its name varies by cluster. The per-node kubernetes_version identifies which nodes sit on the wrong side of a kubelet version skew. Deleted machine rows (workers a scale down or a stop removed) are left out unless include_deleted is true; deleted_nodes_omitted says how many were. Not available for imported (non-Ankra-provisioned) or managed-Kubernetes clusters. Read-only.ConnectorOAuth
- Read the cloud-init status and the tail of /var/log/cloud-init-output.log for one node of an Ankra-provisioned cluster (Hetzner, OVH, UpCloud, DigitalOcean, Scaleway, AWS, or Ankra Cloud), over SSH-via-bastion. This is the debug surface for node-group user_data: that document runs once, at first boot, before anything else can observe it, so a failed provisioning script is invisible to every other tool - the node either joins looking perfectly healthy (cloud-init's growpart fallback restores an ordinary full-disk root when a carve fails) or never appears at all. Use it when a node group carries user_data and a node came up wrong: partitions or mounts that are missing, a package that should have been installed, a first-boot script whose effect is absent. Returns cloud-init's own status (including whether it reported an error) plus the output-log tail, and runs nothing that changes the node. Repeated calls attach to an in-flight fetch instead of dispatching a duplicate. Identify the node with node_id (preferred, from list_cluster_nodes) or node_name. Not available for imported or managed-Kubernetes clusters. For OS-level failures unrelated to first boot, use ssh_diagnose_node.ConnectorOAuth
- Stop an Ankra-provisioned self-managed cluster (Hetzner, OVH, UpCloud, DigitalOcean, Scaleway, AWS, Ankra Cloud, Proxmox VE, or HPE Morpheus). On Hetzner, OVH, UpCloud, DigitalOcean, Proxmox VE and Morpheus a stop TERMINATES every VM of the cluster at the provider (control planes, workers, bastion/gateway); on Scaleway, AWS and Ankra Cloud the servers are instead powered off and kept with their volumes (etcd and the cluster's state survive; retained storage, gateway and IPs remain billable). On the terminating providers the platform first captures the cluster's state - an encrypted etcd snapshot uploaded to the organisation's backup vault - and tears the VMs down only once it is stored (k3s and kubeadm clusters on Hetzner, OVH, UpCloud, DigitalOcean, Proxmox VE and Morpheus); start_cluster then restores it so Secrets, ConfigMaps, custom resources and PersistentVolume/Claim bindings come back and StatefulSets reattach their existing cloud disks. preserve_state=false skips the capture (data on the VMs' disks is then destroyed; only the cluster's Ankra configuration is preserved and start_cluster re-provisions from it); preserve_state=true refuses a stop whose state cannot be captured. Cloud block volumes are never deleted by a stop. mode 'pause' (k3s on Hetzner, UpCloud and DigitalOcean) instead powers the servers off and keeps them with their disks, exactly like a Scaleway, AWS or Ankra Cloud stop: etcd, local data and the nodes' identities survive and start_cluster powers them back on, at the price of compute and storage still billing while paused - offer it when the user wants a short stop with everything intact, and the default teardown when they want to stop paying for the VMs. Use before change_control_plane on a single-controller cluster (a 3-controller cluster resizes live without stopping). Confirm with the user before calling.ConnectorDestructiveOAuth
- Create and provision a new self-managed Kubernetes cluster on Ankra Cloud: k3s or kubeadm on Ankra Cloud servers in one zone, reached through a bastion server. By default the cluster is IPv6-only (network_mode ipv6_only): the bastion holds only its public IPv6, which the platform reaches through an Ankra Cloud port forward, and the nodes reach IPv4 through the zone's NAT64 (the zone must offer NAT64 and port forwarding; the preflight refuses otherwise). Only when the user asks for public IPv4, network_mode ipv4_nat adds a router with NAT for the nodes' egress and gives the bastion a public IPv4 (a paid add-on under the account's public IPv4 quota). Ankra creates a private network (or adopts private_network_id) and a firewall that admits only the private network to the nodes; the Ankra Cloud cloud controller manager is always installed. The organisation's built-in Ankra Cloud credential is used unless credential_id names a stored one (list_provider_credentials with provider='ankracloud'). Zones and plans come from list_managed_k8s_options with provider='ankracloud_k8s': its locations are the zones and its node sizes are the plans, with monthly prices. The create runs a preflight first (credential, billing standing of the built-in account, zone offers compute, every plan and the template exist, an adopted network lives in the zone, quota) and refuses with every failing item when it cannot proceed; nothing is written on refusal. A managed Ankra Cloud Kubernetes cluster (Ankra Cloud runs the control plane) is create_managed_cluster with provider='ankracloud_k8s', not this tool. Only available to organisations with Ankra Cloud enabled.ConnectorDestructiveOAuth
- Submit a new WhatsApp Business message template for Meta's review on one of your Business (Cloud API) numbers. Meta reviews it (usually minutes, sometimes longer); it can be sent with wa_send_message's template option only once wa_list_templates shows it APPROVED. Categories: MARKETING or UTILITY. Number body variables {{1}}, {{2}}, … in order and give one body_examples value per variable. Templates apply only to Business numbers.ConnectorOAuth
- DEPRECATED in favour of get_component_prompt. Mechanical substitution does not fit this corpus: the prompts narrate their own numbers in prose, so replacing only the code values makes prose and code specify different components (judged 11/30). Coverage is deliberately narrow: 164 of 219 components have ZERO substitutable values because their prompts narrate their own numbers in prose ('over 4s', 'durations are 1'), and substituting those would make prose and code contradict each other. For those components this returns the prompt unchanged. See DECISIONS.md D15. Returns the component's build prompt with its motion tokens (ease/duration/stagger) replaced by the chosen motion system's values, so several components share one timing language. Values that are STRUCTURAL to the effect (elastic overshoot, loop cadence, scrub linearity, shader/physics constants) are never substituted — they come back listed under 'Valores no parametrizables'. Omit `system` to use the component's native one.ConnectorNo auth
- Returns one page of NetActuate's technical documentation (netactuate.com/docs) in full: how-to guides (cloud-init, Terraform, Ansible, Kubernetes, BGP and anycast, firewalls, load balancers, Secrets Manager, storage), product and platform reference pages, and each marketplace appliance's setup page. Gives the page's description and its body in order, headings marked '## ' and code blocks fenced, with its URL, and the marketplace listing for an appliance page. Accepts a URL or path from search_netactuate, a marketplace listing's docsUrl, or a page title such as 'Building VMs with Cloud-Init'. A title matching several pages returns up to ten candidates rather than a guess; a page longer than the server keeps is cut, with a note. An API reference page returns its endpoint instead of a body: to find endpoints, use find_api_endpoints. For marketing pages, get_netactuate_page.ConnectorNo auth
- Look up one Redpanda configuration property (cluster, broker, or topic) by exact name and return its documented type, default, description, restart and enterprise flags, Redpanda Cloud availability, related properties, and docs URL. Deterministic: it reads the generated property dataset for the requested docs version, so a property that does not exist returns found=false with close-name suggestions instead of a guess, and no LLM or search is involved. Use this before ask_redpanda_question for any question about a specific property's default, type, or availability. Pass platform='cloud' to learn whether the property is supported or editable in Redpanda Cloud. name is one exact identifier, not a search: to find properties by keyword or topic, use list_config_properties.ConnectorOAuth
- Send one real WhatsApp text message from the workspace's WhatsApp number into one WhatsApp group, after the user confirms. Every member of that group (real people outside LetsBot) receives it, and a sent message cannot be recalled or edited. Works on a number connected to LetsBot by QR code (the number's own WhatsApp groups), and on an official green-tick Cloud API number (not Coexistence) for groups created with Meta's Groups API under Channels › WhatsApp groups — their chat_id contains letters; @mentions are not supported there. On the official Cloud API, WhatsApp does not deliver the number's existing group chats. Identify the group with "group_id", set to the group's "chat_id" from get_groups (e.g. 120363041234567890@g.us); "chat_id" is accepted as an alias. Group names are not accepted. One group per call: this is not a broadcast or bulk-messaging tool.ConnectorDestructiveOAuth
- Hourly clear-sky UV index for one day at any point, with the day's peak UV, the time of the peak and the WHO exposure band (low, moderate, high, very high, extreme) with plain protection advice. For sun-safety, outdoor work and holiday planning. Source: MET Norway Locationforecast 2.0. Values assume a cloudless sky, so real UV is lower under cloud (cloud cover is included); UV is only given for the first few days of the forecast. Needs lat and lon: for a UK place name or postcode, get coordinates from geocode or postcode_lookup first. (cost: 1 credit)ConnectorNo auth
- Hourly clear-sky UV index for one day at any point, with the day's peak UV, the time of the peak and the WHO exposure band (low, moderate, high, very high, extreme) with plain protection advice. For sun-safety, outdoor work and holiday planning. Source: MET Norway Locationforecast 2.0. Values assume a cloudless sky, so real UV is lower under cloud (cloud cover is included); UV is only given for the first few days of the forecast. Needs lat and lon: for a UK place name or postcode, get coordinates from geocode or postcode_lookup first. (cost: 1 credit)ConnectorNo auth
- Get sales report in the user's own Salonized account from ChatGPT, Claude or any AI agent. Returns how to do it in Salonized step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's Salonized Cloud Browser. Salonized's official API: Salonized has no public API, webhooks or MCP server (checked 31 Oct 2026).ConnectorNo auth
- Copy every image of an order to a cloud bucket outside SkyFi (Amazon S3, Google Cloud Storage or Azure Blob Storage). Free of charge. Use `skyfi_list_orders` to find the order; for one image, use `skyfi_deliver_image`. Analytics results in the order are skipped. Each image is delivered on its own: a delivered image is copied now, one that is not ready yet is copied when it completes, and one failure does not stop the others. **Consent required.** The copy cannot be undone and exposes the imagery to everyone who can read the destination. Without `confirm=true` the tool asks the user in-chat (where supported) and delivers nothing unless they agree. Use the exact `delivery_method` / `delivery_params` the receiving service gave you. Returns a per-image summary and a JSON block with `order_id`, `destination`, `scheduled` / `failed` counts, and `items[]` (`item_id`, `status`, `outcome`, `error`).ConnectorDestructiveOAuth