"An MCP that effectively manages other MCPs" matching MCP tools:
- Switch the project owner between Pro and Scale, or cancel the subscription (effectively dropping to Free at period end). Returns `{kind, newPlan, effectiveAt, applied}` — `applied=true` means Paddle was charged immediately, otherwise the change is queued for the current period end. Use preview_plan_change first to see the dollar impact. Owner-only; requires a token minted with the billing scope.ConnectorDestructiveNo auth
- List the ProductClank content spaces you can draft into — spaces the user owns, delegates for, or manages that have their content engine turned on. Returns { space_id, name }. Call this first to resolve the space_id for write_content_candidates, and confirm the target space with the user.ConnectorNo auth
- Show your account's credit balance, plan and auto top-up settings. `credits.available` is what generations can spend right now (plan_credits + extra - used); `resets_at` is when the plan's monthly credits refill (unix seconds). When `team_pool` is true the balance is your team's shared pool, and `auto_topup` is null because the team owner manages it. Check this before an expensive generation instead of waiting for a 402. Buying credits and changing auto top-up happen in the web app at `billing_url`. This is a free read-only lookup (no credits, no generation).ConnectorNo auth
- Delete a teammate by UUID (a soft delete; their emails are removed from signature deployment). Only available when the workspace manages its own team list — if a directory integration (Google, Microsoft or Zoho Mail) drives teammates, this returns a 409 conflict.ConnectorDestructiveOAuth
- Manages PyPI packages in a Managed Airflow environment. Use this tool to install and uninstall PyPI packages in the Managed Airflow environment, or change PyPI package versions or extras. To install packages or change versions or extras, use the `update_packages` field. To remove packages, use the `remove_packages` field. At least one package must be specified in one of these fields. The same package can't be specified in both fields. This tool triggers an environment update, which is a long-running operation that can take several minutes. The tool returns an operation object. Use the `get_operation` tool to poll its status. A completed operation will include the details of the updated environment.ConnectorNo auth
- USE WHEN asked to explain a crypto-agent concept (what x402 is, how agents hold wallets, what ERC-8004 does) and you want a sourced explainer you can cite. Find slugs with onchain_agent_list_wiki_pages. NOT FOR a specific project (use onchain_agent_get_resource instead) or how the Sato Score works (use onchain_agent_get_score_methodology). RETURNS (json): the full wiki page by slug: summary, why it matters, how it works, key components, examples, risks, related resources/pages. A near-miss slug that plainly means a page ("what-are-erc-8004" or the bare "erc-8004" for "what-is-erc-8004") serves that page and says which one in alias_of; when the slug is also a directory listing, also_listing names onchain_agent_get_resource. An unknown slug is a miss (not an error) carrying the nearest real slugs as suggestions; the Sato Score has no wiki page, so "what-is-sato-score" is a miss that points at onchain_agent_get_score_methodology. Read-only. Example: { slug: "what-are-mcps" }ConnectorNo auth
Matching MCP Servers
- AlicenseNot gradedqualityBmaintenanceA thin MCP server that securely enables AI agents to interact with Home Assistant, Mealie, and Nirvana via tools for automation, recipe management, and task tracking, while keeping credentials hidden.MIT
- AlicenseNot gradedqualityCmaintenanceExposes remote, agent-facing MCP endpoints over Streamable HTTP for web search, webpage parsing, local knowledge-base retrieval and document creation, and delegation of tasks to configurable LLM providers. Also bundles an admin console with onboarding, provider/model configuration, API-key management, and call logging.MIT
Matching MCP Connectors
send-that-email MCP — wraps StupidAPIs, keyless: analyze whether you should send that email…
Google is not the whole market. Your agent needs Bing, Yahoo, Baidu, Naver, Seznam and YouTube results — the engines that decide whether you exist in China, Korea, Japan or Central Europe. **What you can ask for** • "What ranks for this term on Baidu, and how different is it from Google?" • "Check Naver results for our Korean brand name." • "Compare Bing and Yahoo results for the same query." • "What comes up on YouTube search for this phrase in Japanese?" • "Take a screenshot of the results page as a user there sees it." **How to use it** Point any MCP client at https://mcp.aisa.one/seo-serp-other-engines/mcp and sign in with OAuth — there is no key to create or paste. 34 tools: organic results from Bing, Yahoo, Baidu, Naver and Seznam in live, regular and raw-HTML forms, YouTube search, an AI summary of a result set, and a rendered screenshot. **Why this rather than the source** The engines that matter outside the US, with the same call shape as the Google ones. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Check the local engine here, then ask the same agent what the site's traffic or backlinks look like in that market — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/seo-serp/mcp for Google itself. https://mcp.aisa.one/seo/mcp for all of it at once — rankings, keywords, backlinks, site health and AI-answer visibility across DataForSEO, Semrush and Ahrefs.
- Install a single Workbench component by id (e.g. `node`, `opencode`, `npm-mcps`, `skills`) on a target; `component` must be an id from describe_workbench. Overwrites that component's files when present (e.g. `skills`/`plugins` replace the copies under `<home>/.config/opencode`); global installs need write permission and can take minutes. Idempotent and consent-gated: without `confirm:true` it returns the plan. Parameter semantics: `component` is required; `workspace` defaults to `~/opencode-workbench`; `confirm` defaults to false (plan only). Use it for one targeted component; use apply_clone to install the full default set.ConnectorDestructiveNo auth
- Admin-only membership controls. list returns members and pending invites. invite adds/renews an email invite (default member; existing members refused); email_sent reports best-effort delivery. resend_invite renews by invite_id; revoke_invite withdraws. set_role never demotes the last admin. set_manager sets/clears a manager, rejecting self-reporting and cycles. set_read_scope (sees) and set_write_scope (edits/deletes) take own/team/all/null (role default), optionally include_reports; never admins. remove cannot target yourself or the last admin; records remain. Except list/revoke_invite, actions preview the person/change until confirm:true. This connection is bound to one membership; leave/switch your own workspace in the browser. When to use: An admin manages membership, invitations or an individual's access. Example: Invite sara@brightside.example as a manager.ConnectorDestructiveAPI key
- Install a single Workbench component by id (e.g. `node`, `opencode`, `npm-mcps`, `skills`) on a target; `component` must be an id from describe_workbench. Overwrites that component's files when present (e.g. `skills`/`plugins` replace the copies under `<home>/.config/opencode`); global installs need write permission and can take minutes. Idempotent and consent-gated: without `confirm:true` it returns the plan. Parameter semantics: `component` is required; `workspace` defaults to `~/opencode-workbench`; `confirm` defaults to false (plan only). Use it for one targeted component; use apply_clone to install the full default set.ConnectorDestructiveNo auth
- A mutual fund or ETF's profile from SEC Form N-CEN, the annual fund census: ETF/index/money-market status (an explicit flag, which N-PORT holdings filings do not carry), AUM, expense ratio, advisory fee, NAV and market price per share, and its investment adviser(s). Also covers ETFs organized as unit investment trusts (SPY, QQQ, DIA) via N-CEN's separate UIT section, fund_type "unit investment trust", total assets, and administrator(s), but no expense ratio/advisory fee/NAV (Part F does not report those). Give the fund or ETF name ("Vanguard Total Stock Market Index Fund", "SPDR S&P 500 ETF Trust"). Answers "is this fund an ETF", "what's this fund's expense ratio", "who manages this fund", "how big is this fund's AUM". Does NOT cover inception date, N-CEN carries no such field, or portfolio holdings (use nport_fund_portfolio for that). Response discloses a name_match grade (exact/starts_with/contains) and other candidates, since a substring match is never presented as the fund without saying so.ConnectorNo auth
- Emails a person an invitation to join this organization's team as a viewer (read only), for every workspace (scope "all") or only some (workspace ids from list_workspaces). The invitation link works for 7 days; inviting an address that already has an open invitation updates and resends it. Sends email to a person, so it needs the publish scope and a key whose human manages the team. Agents can't invite editors or managers, so a misled agent can't hand someone write access: the human does that in the app (Team page). At most 30 invitation emails per organization per day. (Not available in an unclaimed sandbox.)ConnectorDestructiveOAuth
- Manages the links from this model to items of other Layerz models (an external ref, like an Excel linked workbook), by `op`. `link`: creates (or retargets, with `uid`) a non-list assumption whose `values` hold a snapshot of the source item's computed series projected to this model's grain (`null` outside the source's coverage); requires read access to the source model; the line is referenceable in formulas like any assumption; up to 200 links in `links` (one form per call) load each source once, are validated whole (one failure writes nothing) and return `results`. `refresh`: re-reads every linked source (or `uids`) and rewrites the snapshots, the only way the values move; a per-link failure (source or item gone) leaves the stored values intact; when values change, the pre-refresh state is snapshotted first (`Auto-backup before refresh`). `unlink`: detaches the line `uid`, keeping its values as an ordinary assumption. A self-link is rejected; a cross-model cycle resolves one hop per refresh. Link status and staleness: `layerz_list_integrations { include_external_refs: true }`. Persists one version labelled with `summary`. Not advertised to read-only keys.ConnectorDestructiveOAuth
- List Fresha's treatment taxonomy and return the ids that fresha_search_venues accepts as treatment_category_id, treatment_tag_id and treatment_type_id, each with its display label, kind (TreatmentCategory, TreatmentTag or TreatmentType) and an icon for categories. Ids take the forms category:<slug>, tag:<slug> and treatment:<category-slug>/<type-slug>. With no query it returns the closed category page of 20 categories (a 21st is reachable only by text search), so categories are effectively complete; tags and treatment types appear only for a text query and are ranked by Fresha's own autocomplete, so treat them as a discovered set rather than a complete catalogue and page with next_start while has_next_page is true. Use words from a treatment name such as nail, haircut or massage. Call this before a filtered fresha_search_venues request instead of guessing an id, because a well-formed id Fresha does not know returns zero results with no error.ConnectorNo auth
- List Fresha's treatment taxonomy and return the ids that fresha_search_venues accepts as treatment_category_id, treatment_tag_id and treatment_type_id, each with its display label, kind (TreatmentCategory, TreatmentTag or TreatmentType) and an icon for categories. Ids take the forms category:<slug>, tag:<slug> and treatment:<category-slug>/<type-slug>. With no query it returns the closed category page of 20 categories (a 21st is reachable only by text search), so categories are effectively complete; tags and treatment types appear only for a text query and are ranked by Fresha's own autocomplete, so treat them as a discovered set rather than a complete catalogue and page with next_start while has_next_page is true. Use words from a treatment name such as nail, haircut or massage. Call this before a filtered fresha_search_venues request instead of guessing an id, because a well-formed id Fresha does not know returns zero results with no error.ConnectorNo auth
- Session-only: remembers which app later calls refer to. Changes nothing on the server and can be called again at any time to switch. Set the current app context for this session so app-scoped tools can omit their `appId` argument. On the hosted server the selection is remembered for the signed-in account (24 hours), so a client that opens a new session per call keeps it; `ethora-app-create` selects the new app by itself, and an account with exactly one app has it selected automatically. Stores `currentAppId` and, if given, `appToken` (which defaults the auth mode to app-token unless `authMode` overrides). Auth: none required to set the context. Errors: effectively none — a non-existent `appId` is not validated here; the first app-scoped API call surfaces the 404. Related: pairs with `ethora-auth-mode-set`.ConnectorNo auth
- Pro+ (any paid plan). The account's post board: post ideas and drafts in columns draft → needs_approval → approved → scheduled → posted (failed if publishing failed). Use it as a Kanban for post ideas, or for an approval flow on accounts someone manages. 'list' (newest first; filter by column), 'get' one card with its activity history, 'create' a card (content, optional title, kind 'post' or 'lead_magnet' with an automation {template_id, keywords, resource_link}, optional planned_for), 'edit' its fields and/or move it with column (draft, needs_approval, approved), 'schedule' it (scheduled_for, or the next free 15-minute slot), 'unschedule' a still-waiting post back to approved, or 'delete' a card that isn't scheduled. Roles: the account owner does everything and, on an account nobody manages, can schedule straight from draft. On a managed account the manager and the co-admins they mark as approvers approve and schedule; other co-admins draft and submit, and their edit on an approved card sends it back to needs_approval. Scheduling uses the same pipeline as schedule_post_with_automation (plan, LinkedIn connection, automation template) and never creates a second post for the same card. Scheduled and posted cards are read-only here: change them with edit_scheduled_post. Files are added in the dashboard.ConnectorOAuth
- Revoke an API key (soft-delete via `revokedAt`). Subsequent requests with the key return 401. Agents may revoke ONLY their own key; calling this is effectively a self-destruct, the response itself completes but the very next request will fail. Users may revoke any key they own. To swap creds without going dark in the gap, use `rotate_api_key` instead.ConnectorNo auth
- Cancel (delete) one reminder by its reminderId (ids come from list_reminders or create_reminder). The saved item itself is not touched. Reminders synced to Google Calendar cannot be cancelled here - the user manages those at mark-it.co or in Google Calendar.ConnectorDestructiveNo auth
- Save or rename a recipient The saved recipient names your human manages on their dashboard, so a request like "send $20 to the coffee vendor" can be resolved to an address instead of asking them for it. Free. It operates only on the authenticated account's own book — there is no user parameter to pass. **A name is a label, not an instruction.** `agentWalletTransfer` takes an address and deliberately does not accept a name: a rename between your human asking and you sending would otherwise move money somewhere they did not intend. When you resolve a name to an address, say the address back to them before sending. The address is the entry's key, so saving one that is already saved renames it rather than creating a duplicate. That makes this safe to retry.ConnectorOAuth
- List the Google Business Profile locations this sign-in manages, with the gbp_location_id every other gbp_* tool needs. Call this first; never guess a location id.ConnectorOAuth
- Create a flixconomy.ai account for yourself. No key needed. Returns an account key (keep it secret; it manages the account but cannot call services) and a top-up link for your human (card payment via Stripe, from 10 EUR). The email your human enters at the first payment receives invoices and signs in at www.flixconomy.ai/account. After the payment, call create_api_key.ConnectorNo auth