"Allowing an AI agent to ask user questions during a task" matching MCP tools:

• get_wallet

  SOMA Brewing Company

  READ-ONLY wallet summary for a SOMA app user: their SOMA Coins balance plus a summary of coins expiring within the next 30 days. Requires a wallet token that only the human can generate inside the SOMA mobile app (Wallet tab → 'Share balance with your AI') — ask them for it; tokens expire after ~10 minutes. This tool can never claim, redeem, spend, or move coins (there are deliberately no claim/redeem tools over MCP). Returns { error: 'invalid_or_expired_token' } for a bad or stale token — ask the user to generate a fresh one in the app.

  Connector

• compose_landing

  Layero

  Drive the 3-step quiz flow and produce a complete landing. This is the **main entry point**. Don't ask the user questions in chat before calling this — the tool opens native quiz dialogs in the IDE itself. Call this immediately when the user describes what they want. The three quizzes are: 1. **Motivation** — what's being built, for whom, the desired action. 2. **Look & feel** — palette, tone, optional references. 3. **Final picks** — design system (top 3 matched), where submissions go, project name slug. Returns a ``ComposeResult`` with the file bundle to write to disk. The agent then writes the files using the IDE's filesystem tool and proceeds to integration setup / deploy.

  Connector

• formation.guided_setup

  Admin Substitute

  RECOMMENDED ENTRY POINT — Intelligent business formation engine. Provide context about the person (trade, state, qualifications, budget, goals) and get a personalised formation plan with: (1) auto-detected pathway (licensed contractor, fresh start, or investor/operator), (2) task list split into AI-actionable vs human-required, (3) direct government portal links, (4) trade-specific insights (common first jobs, suppliers, rates, growth tips), (5) recommended next tool calls, (6) follow-up questions to ask. Call this FIRST, then use the recommended tool chain for deeper dives.

  Connector

• analyze_business_vertical

  agent-ready-kit

  Use this immediately after scan_site to give the user a 'what this means for my business' framing. Detects the site's business vertical (auto dealership, law firm, healthcare, home services, ecommerce, digital agency, etc.) from JSON-LD schema + scraped text. Returns expected AI-search lift %, current competitor adoption %, and a positioning pitch tailored to the vertical. **If `should_ask_user` is true, the detection is low-confidence — ASK THE USER what category their business is in before continuing, rather than acting on the guessed vertical.** Also returns the site title and meta description so the calling agent can render a Site Summary card.

  Connector

• render_dxf

  aspicio-dxf-viewer-remote

  Render a DXF drawing to a PNG image you can look at. Use this to answer visual questions (what does it look like, where is a feature) — it returns an image, not text. For structural facts and measurements, prefer describe_dxf; never measure pixels. Some chat UIs do not display the returned image to the user: for URL sources the result also includes a direct image link — show it to the user (e.g. as a markdown image) when they need to see the render. When the user wants to see or explore the drawing themselves, prefer view_dxf (interactive viewer) — if your platform gates it behind user approval, offer it and ask rather than substituting a static render.

  Connector

• stobox_start_tokenization

  Stobox Intelligence & Tokenization

  Send the user's request to start tokenizing their real-world asset to the Stobox team, so a specialist contacts them (shares their email with Stobox, with their consent). Call this ONLY when the user explicitly wants to BEGIN (not just learn), has told you what asset they want to tokenize, and consents to be contacted. Requires a contact email. Returns confirmation + next steps. Do NOT call for general questions — use the search/lookup tools for those. Never invent an email; ask the user for it first.

  Connector

• get_pricing

  Almured

  Retrieve pricing entries for yourself or another agent. WHEN TO USE - Before routing a direct consultation to a target agent, to check what they charge. - To verify your own pricing configuration is set correctly. WHEN NOT TO USE - For real-time consultation pricing during an engagement — pricing is dormant during Phase 2-Infra and no payments happen yet. BEHAVIOR - Read-only. Rate-limited to 60 req/min. - agent_id is optional. Omit to retrieve your own pricing (auth required). Provide a UUID to read another agent's pricing. - Returns category, deliverable_type, price_cents, currency for each entry. - Dormant note is always appended during Phase 2-Infra. WORKFLOW - After checking target agent pricing, use ask_consultation with target_agent_id set; at scope_accepted the platform snapshots the price.

  Connector

• verify_agent

  TunnelMind Data API

  Reconciles a claimed bot User-Agent against the operator's OWN published IP-range feed (Googlebot, GPTBot, OAI-SearchBot, ChatGPT-User, PerplexityBot, Perplexity-User, Bingbot). A User-Agent is trivial to forge; membership in the operator's published CIDR ranges is not. This exposes the common attack: a scraper sending `User-Agent: Googlebot` from an IP in none of Google's ranges. Use this tool when: - A request claims to be a search/AI crawler and you must decide whether to trust that claim before serving, allowing, or logging it. - You are separating genuine declared agents from impersonators. Inputs: - `ip` (path, required): the IPv4 or IPv6 address to check. - `ua` (query, optional): the claimed User-Agent string. Omit to ask only "is this IP a known published bot range?". Returns: - `verdict`: one of - `verified` — the IP is inside the agent's published range (UA, if given, agrees). It genuinely is that bot. - `spoofed` — the UA claims a verifiable bot but the IP is in none of its published ranges. Impersonation. - `mismatch` — the IP is a real bot's range, but the UA names a different bot. - `unverifiable` — the UA names a real agent whose operator publishes no authoritative IP feed (e.g. Anthropic's ClaudeBot). Neither confirmed nor denied — never reported as spoofed. - `unknown` — no recognized bot UA and the IP is in no known range. - `is_verified_agent`, `is_spoofed`: booleans for the two actionable cases. - `agent`, `agent_label`, `matched_agent`, `claimed_agent`: the resolved identities. - `reason`: one-line explanation of the verdict. - `feeds_as_of_ms`: when the published ranges were last refreshed. Cost: - Counts as one request against the daily rate limit. Latency: - Typical: <50ms (one KV read + CIDR match). First call after a deploy may take ~1s if it has to warm the range cache.

  Connector

• create_portfolio_draft

  Bullrun

  Use when the user wants you to BUILD or PROPOSE a brand-new portfolio for them — e.g. "build me a portfolio", "put together a dividend portfolio", "draft a portfolio of AI stocks", "create a new portfolio for $10k". Generates a REVIEWABLE paper-portfolio draft for the signed-in Bullrun user from a natural-language brief (e.g. "a diversified European dividend portfolio"). Requires OAuth with the write:drafts scope and a Bullrun Pro account. This is DRAFT-ONLY and never changes any live position: the draft is saved to the user's account and appears in the Bullrun Portfolio tab under "Pending AI drafts", where the user reviews it and explicitly accepts it to create a new portfolio (or discards it). To suggest additions to an EXISTING portfolio instead, use create_position_draft. Tickers are chosen only from Bullrun's priced stock/ETF universe; pass instrumentUniverse for stocks only, ETFs only, or a mix. If the brief is vague, first ask ONE quick round of up to three multiple-choice questions (investing style, region focus, and size), each with a default the user can accept with "just pick for me", then build; skip any dimension the user already specified and do not interrogate across multiple turns.

  Connector

• submit_human_task

  Human For AI

  Submit a task for the human operator to perform in the real world. Returns a task_id immediately; the human reviews every task before accepting it (this is not instant execution). The operator is push-notified on submission; check_task_status shows seen_by_operator_at once a human has seen the task. Free during the pilot. contact_email must be a real mailbox (MX-checked) — it is how the deliverable reaches you. No mailbox? Set delivery to 'status_poll' instead: the deliverable arrives as text in operator_notes via check_task_status (limited to 1 such task per client per day).

  Connector

• niche_brand_kit_guided_setup

  Niche — Editorial Intelligence

  Return a structured question chain the agent walks the user through to populate the BrandKit, VoiceProfile, and (optionally) BrandProfile. Each entry carries an `intent` describing what the answer is for (so the agent paraphrases in its own voice based on the conversation it's already having) plus a `prompt_hint` fallback for agents that relay tools verbatim. Use this when the agent is helping a new user set up Niche and wants a predictable, brand-aware Q&A sequence instead of improvising. Tiered by impact: - Tier 0 (primary): URL ingest, fills 70-90% in one ask. - Tier 1 (gap_fill): only the fields URL ingest didn't fill. - Tier 2 (discipline): opt-in guardrails (topics off, banned terms, competitor stance). - Tier 3 (no_url): full fallback for users without a site. Per-question `applies_to_field` tells the agent where the answer writes (via niche_brand_kit_update or niche_brand_profile_set). `is_already_set` is computed from the user's current BrandKit and BrandProfile state so the agent skips questions already answered. Returns the full chain in one call; the agent inspects state, decides flow, and asks in any order (or skips entirely if the user volunteered the answer earlier in the conversation).

  Connector

• submit_feedback

  InsideOut (Riley)

  FEEDBACK: Submit feedback, bug reports, or feature requests to Luther Systems Use this tool to forward user feedback directly to the Luther Systems team. This includes bug reports, feature requests, questions, or general feedback about InsideOut. The agent itself can also use this tool to report issues it encounters during operation. REQUIRES: session_id, category, message OPTIONAL: user_email (for follow-up), user_name, source (default: 'mcp'), initiator ('user' or 'agent') Categories: bug_report, feature_request, general_feedback, question, security The 'initiator' field tracks who triggered the report: - 'user' — the user explicitly reported the issue or requested feedback submission - 'agent' — Riley detected an issue and initiated the feedback flow Examples: - User says 'the deploy button is broken' → submit_feedback(category='bug_report', message='...', initiator='user') - User says 'I wish it had dark mode' → submit_feedback(category='feature_request', message='...', initiator='user') - Deployment failed with Terraform error → submit_feedback(category='bug_report', message='Deployment failed: Terraform apply error on aws_alb resource — timeout waiting for ALB provisioning', initiator='agent')

  Connector

• submit_support_request

  Skala — Legal Platform for Startups

  Submit a support request to the Skala team on behalf of the user. Call this when the user needs human assistance that AI cannot provide, the question is too complex or high-risk, or the user explicitly asks for human support. IMPORTANT: Always confirm with the user before calling — describe what you will submit and ask for their approval. Before calling, compile the issue from conversation context into the description.

  Connector

• popular_skills

  BytesAgain AI Skills Search

  Return top N AI agent skills ranked by download count. Use for discovery or onboarding when user has no specific task in mind (e.g. "show me popular skills", "what can I do with this"). Do NOT use when user describes a specific task — use search_skills instead. Returns: slug, name, description, category, downloads, stars. On database error returns empty list — do not retry. Default limit 20, max 50. Follow up with get_skill only if user requests details on a specific result.

  Connector

• docs_search

  Social Fetch

  Search SocialFetch docs for API/SDK questions. For response fields use docs_read (defaults to outline). For cross-platform author/timestamp naming, search `field crosswalk` or read /product/ask-ai/field-crosswalk.

  Connector

• lint_task_spec

  Reality Graph Verification Tools

  Check whether a free-text work order for an AI coding agent is verifiable BEFORE handing it over. Heuristic, deterministic lint of the task's form against the four building blocks of a checkable task (goal, boundaries, acceptance criteria, validation plan) plus rule checks (vague adjectives without numbers, unnamed unhappy paths, missing file anchors). Returns a status table with evidence, the concrete questions that close each gap, and a fill-in skeleton. It checks form, not content — no LLM, nothing stored. Set lang='de' for a German report.

  Connector

• get_task_contract_template

  Reality Graph Verification Tools

  Returns Reality Graph's free fill-in template (v0) for a verifiable task contract: goal, non-goals, boundaries (may change / must not change / forbidden), 3-7 yes/no acceptance criteria, validation plan, expected evidence, assumptions, open questions — with a filled example and fill-in guidance. Write the contract before an AI agent runs; verify the result against it after. format='json' returns a machine-fillable JSON structure; default is a compact markdown skeleton. Set lang='de' for German. Static content, nothing stored.

  Connector

• confirm_ai_call

  Sats4AI - Bitcoin-Powered AI Tools

  Confirm an AI call after reviewing push-back questions, optionally providing answers to missing info. Required when ai_call returns state='pending_confirm'. Uses the original payment — no new payment needed. Returns call_id for polling with check_job_status(jobType='ai-call').

  Connector

• account

  rocketsloth

  View or update your account (authenticate with your API token sk_...; an approved account's Bearer web session — the in-page agent on rocketsloth.ai — is also accepted, so do not ask the user to paste an sk_ token when you already have a working session). action: view (default; account and site status) | update (contact_email and/or agent_name) | rotate_token (revoke the current API token and issue a new one; not available to web sessions — sessions rotate via https://rocketsloth.ai/recover).

  Connector

• kenwea.community.ask

  Kenwea — Sandbox Attestation & Agent Marketplace

  Ask the marketplace a question, including "why is there no X here?". This is the one write an unclaimed tourist agent may perform, and it exists so a newcomer can report a gap it found without first binding to an operator. Moderated and rate limited.

  Connector