"Using Windsurf and Claude Tools or Technologies" matching MCP tools:

• get_setup_instructionsA

  Vilix AIA

  Make Vilix automatic. Call this when the user asks "how do I make this automatic", "set this up so it remembers on its own", or right after a first connection when offering setup. Returns a short custom-instructions block the user pastes into THIS tool's personalization / custom-instructions settings so the AI starts calling Vilix (get_context / save_turn) on its own — plus exactly where to paste it. `recommended` is the block matched to the caller's tool; `blocks` lists every supported tool's block (and for headless always-on tools, an enforce-every-turn variant for an always-on rules file). `source` (optional) — the tool label you run in (e.g. "ChatGPT", "Claude", "Cursor", "Codex", "Copilot", "Windsurf"), used to pick the right block; omit to get the generic default. This is an OPT-IN setup you hand to the user — it is not auto-applied; Vilix logs nothing silently.

  ConnectorOAuth

• aw_healthA

  Agent WatchA

  Liveness check for the Agent Watch API. Returns ok, service name, and version. Call this first to verify connectivity before using other tools.

  ConnectorNo auth

• ask_agentA

  SwogeAgenticA

  Use this when a question needs several of these tools chained together and a written answer, for example comparing tokens or researching a launcher. SwogeAgentic, a Claude agent, picks the tools, reads the numbers and answers in Markdown with its sources and sample sizes. API key only: billed at its real cost, up to the quoted maximum ("quote": true gives it). Takes 10 to 60 seconds.

  ConnectorNo auth

• map_agent_oversightA

  7IT SolutionsA

  Use this when someone asks which actions their AI agent or its connected tools may take on their own, which need a person's approval, and which a person must do; or how to set up human oversight, permissions or AI governance for an agent (for example under the EU AI Act). Give either the address of a public MCP server, or the list of tools the agent has (name, description and annotations). Sorts every tool into green (runs alone: reads and prepares), yellow (a person approves: sending, updating, scheduling) or red (a person does it: money, permissions, deletion, code execution, commitments), flags tools with no risk annotations, and returns a ready policy, Claude Code permission rules (allow, ask, deny) and an oversight checklist. Reads tool lists only and never calls a tool. A working checklist, not legal advice.

  ConnectorNo auth

• petpooja_check_online_order_payoutsA

  Petpooja MCP Server and API by CotletA

  Check online order payouts in the user's own Petpooja account from ChatGPT, Claude or any AI agent. Returns how to do it in Petpooja step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's Petpooja Cloud Browser. Petpooja's official API: Petpooja publishes no API documentation or API keys page for restaurants (checked 31 Oct 2026).

  ConnectorNo auth

• sign_inA

  UpForkA

  Only when the user wants something that needs their UpFork account: saying a lesson worked or didn't, their account, installing a product that isn't free, a product's AI prompt, support tickets, their profile and résumé, articles, lesson drafts or team lessons. Ask the user first. Their AI app then opens upfork.dev for them to sign in (in Claude Code: /mcp, choose upfork, Authenticate) and connects again with the tools for those. Everything else here works without it.

  ConnectorNo auth

• pushpress_cancel_reservationA

  PushPress MCP Server and API by CotletA

  Cancel reservation in the user's own PushPress account from ChatGPT, Claude or any AI agent. Returns how to do it in PushPress step by step (screens, buttons, fields) and opens nothing by itself; then do it with the cotlet_browser_* tools in the user's PushPress Cloud Browser. PushPress's official API: PushPress has a Platform API and an SDK that doubles as a local MCP server, both using an API key from Settings > Security & Access, but they are mostly read-only beyond creating customers and invitations (checked 11 Oct 2026).

  ConnectorNo auth

• salonized_get_sales_reportA

  Salonized MCP Server and API by CotletA

  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

• list_makes_modelsA

  mcpA

  List the exact canonical car makes (brands) TransparentCars can search and price — or, given a make, that brand's models — using the exact strings the other tools expect. Call this FIRST (or whenever unsure of spelling) and pass the returned values verbatim into search_inventory / check_fair_price. No make = the list of brands; with a make = that brand's models.

  ConnectorNo auth

• list_makes_modelsA

  mcpA

  List the exact canonical car makes (brands) TransparentCars can search and price — or, given a make, that brand's models — using the exact strings the other tools expect. Call this FIRST (or whenever unsure of spelling) and pass the returned values verbatim into search_inventory / check_fair_price. No make = the list of brands; with a make = that brand's models.

  ConnectorNo auth

• check_serverA

  protogridA

  Probe a remote MCP server URL once, credential-free and without calling its tools, and get its quality checks and its readiness for the Claude and OpenAI directories. Pass `url` to start a check (waits up to 25 s for the result), or `id` to read one. Quota: a few checks per hour anonymously, more with an API key.

  ConnectorNo auth

• get_testA

  UxiaB

  Read metadata for one accessible test using testId from list_tests: title, goal, status, type, source, creation date, project, tags, version, result flag and Uxia link. Does not return findings, screenshots or session data; use result tools for those, or get_interview_study when type is ai-moderated.

  ConnectorOAuth

• pair_editorA

  FicturaB

  Connects to the paywall editor a person has open, using the 6-character code shown under “Pair an agent” in the Studio. Returns a pairing_id for the editor_* tools. The code works once and for 10 minutes; a pairing lasts 24 hours or until either side stops it.

  ConnectorNo auth

• pair_editorA

  FicturaB

  Connects to the paywall editor a person has open, using the 6-character code shown under “Pair an agent” in the Studio. Returns a pairing_id for the editor_* tools. The code works once and for 10 minutes; a pairing lasts 24 hours or until either side stops it.

  ConnectorNo auth

• list_supported_technologiesA

  YAMLToolsA

  List the configuration technologies YAMLTools understands, with what each supports (validation, diagram, risks, conversions) and its documentation link. Call it to decide whether analyze_config, config_diagram or convert_config can help with a file.

  ConnectorNo auth

• identify_modelA

  A2UI Atomic CatalogA

  CALL THIS FIRST, before any other a2ui-catalog tool, once per session. Declares your own model identity so this response can hand you capability-matched guidance up front — some models need simpler, judgment-free tools; skipping this just means you default to the full toolkit, including tools that require sizing/pagination judgment calls. HOW TO ANSWER — do not guess: - Copy your model name EXACTLY as stated in your own system prompt or developer context (look for phrasing like "you are powered by the model named X" or similar). Do NOT infer it from your training cutoff, your own behavior, or general capability. - Examples of valid values: "claude-haiku-4-5", "claude-sonnet-5", "claude-opus-4-8", "gemini-2.0-flash", "gpt-4o". Partial names are fine ("haiku", "sonnet"). - If your model name is genuinely not stated anywhere in your context, pass "unknown" — do NOT guess a plausible-sounding value. A wrong report is worse than no report: it can hand you tools you cannot reliably operate.

  ConnectorNo auth

• generate_imageA

  Claude ImagineA

  Generate an AI image from a text prompt using Claude Imagine credits. Returns the image inline plus its full-resolution URL. To change an existing image, use edit_image. For a YouTube thumbnail, book cover, album or podcast cover, poster, blog cover or product photo, call list_styles first and pass one of its ids as style.

  Connector

  Destructive

  OAuth

• company_profileA

  FreeTier Agent APIB

  3 free MCP calls per day (all tools together), then $0.0075 USDC via x402 or card credits (paid in-band: params._meta["x402/payment"]). Company enrichment: domain in, company profile out - name, description, language, logo, founding date, address (schema.org), official social profiles, key pages (contact, about, careers, pricing) and email provider (MX). Only the company's own website and DNS; robots.txt respected; no personal data. When to use: Use company-profile to enrich a domain; company-techstack for technologies; company-contacts for business contact details; company-batch for up to 10 domains.

  ConnectorNo auth

• find_mcp_serversA

  LazarettoA

  Find an MCP server for a job, free and with no key: describe what you need ("postgres", "send slack messages", "browser automation") and get matching servers from the official MCP registry, each with its endpoint, the command to add it to Claude Code, its tools, and what Lazaretto's latest read found. Only servers whose tools we read with nothing matching our tool-poisoning rules, or live servers that ask you to sign in before listing tools (said plainly), are returned; servers we flagged or could not reach are left out. Remote servers only: for a local stdio server, check its tool list with check_mcp_tools. Use it whenever you need a capability you do not have yet.

  ConnectorNo auth

• customer_vendor_detectionA

  Straelo RelayA

  Scan a customer domain to detect vendors and technologies currently present using deterministic fingerprints; returns detected technologies with supporting evidence and observation details. Results are point-in-time observations; eligible CSI observations may be persisted best-effort. An empty detection means no supported fingerprint was observed in that scan — it does not prove the domain uses no technology. Side effect: eligible CSI observations may be persisted best-effort to maintain customer-vendor evidence. **USE WHEN:** an agent needs to determine which supported vendors or technologies are currently detected on a specific customer domain. **DO NOT USE WHEN:** the agent needs confirmed customer base of a vendor (use vendor-customer-confirmed-lookup), historical adoption/removal events (use vendor-customer-adoption-change-lookup), or customer transition signals (use vendor-customer-transition-signal-lookup). Parameter semantics: domain is the customer domain to inspect, not a vendor domain.

  ConnectorNo auth

• list_tracked_toolsA

  Havoptic AI Release IntelligenceA

  Deprecated: use list_tools. All AI coding tools Havoptic tracks (Claude Code, OpenAI Codex CLI, Cursor, Gemini CLI, Kiro CLI, GitHub Copilot CLI, Devin Desktop/Windsurf, Antigravity CLI, Grok Build), with release counts and their latest release.

  ConnectorNo auth