"Creating a voice AI for making outbound calls via SIP telephony" matching MCP tools:

• create_b2_snapshot

  BorealHost

  Create a B2 cloud-backed snapshot (zero local disk, async). Streams container data directly to Backblaze B2 via restic. No local disk impact — billed separately at cost+5%. Runs in background — returns immediately with status "creating". Poll list_snapshots() to check when status becomes "completed". Only available for VPS plans. Requires: API key with write scope. Args: slug: Site identifier description: Optional description (max 200 chars) Returns: {"id": "uuid", "name": "...", "status": "creating", "storage_type": "b2", "message": "B2 cloud snapshot started. Poll list_snapshots()..."} Errors: VALIDATION_ERROR: Not a VPS plan or max snapshots reached

  Connector

• get_payment_options

  headless-oracle

  Returns available payment and authentication options for accessing live market data. Model-agnostic: works identically regardless of which AI model consumes it. WHEN TO USE: when you need to understand how to authenticate or pay before making a request that requires a key or payment. Returns upgrade ladder: sandbox (200 calls free), x402 per-request ($0.001 USDC), x402 sandbox (10 credits for $0.001), credit packs ($5 = 1000 calls), builder subscription ($99/mo = 50K/day). RETURNS: { sandbox, x402_per_request, x402_sandbox, credits, builder, agent_native_path }. No authentication required. Always returns 200.

  Connector

• get_payment_options

  Headless Oracle

  Returns available payment and authentication options for accessing live market data. Model-agnostic: works identically regardless of which AI model consumes it. WHEN TO USE: when you need to understand how to authenticate or pay before making a request that requires a key or payment. Returns upgrade ladder: sandbox (200 calls free), x402 per-request ($0.001 USDC), x402 sandbox (10 credits for $0.001), credit packs ($5 = 1000 calls), builder subscription ($99/mo = 50K/day). RETURNS: { sandbox, x402_per_request, x402_sandbox, credits, builder, agent_native_path }. No authentication required. Always returns 200.

  Connector

• create_job_offer

  Human Pages

  Send a job offer to a specific human. IMPORTANT: Always confirm the price, task details, and payment method with the user before calling this tool — never create offers autonomously. The human gets notified via email/Telegram and can accept or reject. Requires agent_key from register_agent. Rate limit: PRO = 15/day. Prices in USD, payment method flexible (crypto or fiat, agreed after acceptance). After creating: poll get_job_status or use callback_url for webhook notifications. On acceptance, pay via mark_job_paid. Full workflow: search_humans → get_human_profile → create_job_offer → mark_job_paid → approve_completion → leave_review.

  Connector

• send_message

  agent-broker

  Send an outbound message to an SMB or its customer across channels (SMS, email, chat, voice, push). Channel is abstracted — you specify intent and recipient; the service selects and falls back across channels. EXAMPLE USER QUERIES THAT MATCH THIS TOOL: user: "Text the salon I'll be 10 minutes late" -> call send_message({"recipient_id": "smb_xyz", "channel_preference": "sms", "message": {"body": "Will be 10 minutes late."}, "country_code": "US"}) user: "Email the dentist about insurance" -> call send_message({"recipient_id": "smb_xyz", "channel_preference": "email", "message": {"body": "Do you accept Cigna?"}}) WHEN TO USE: Use for outbound business communication: appointment reminders, follow-ups, marketing offers (with confirmed opt-in), transactional messages, or inbound response handling. WHEN NOT TO USE: Do not use for OTP or critical transactional confirmations — use send_transactional_confirmation instead. Do not use for recipients without consent where required (SMS marketing, EU recipients). COST: $varies per_message LATENCY: ~variesms EXECUTION: sync_fast (use get_outcome to retrieve result)

  Connector

• ai_filters_list

  DialogBrain

  List all AI filters for the current workspace. AI filters are semantic intent-based message filters that use embeddings (vector representations) to detect whether an incoming message matches a specific intent or topic. Unlike keyword filters, they understand meaning: 'I need help with my order' and 'my package hasn't arrived' both match a 'shipping support' filter even without shared keywords. Each filter stores a reference embedding of its description. When a message arrives, its embedding is compared via cosine similarity against the filter's reference vector. If the similarity exceeds the threshold, the filter matches. When to use: - Check which semantic filters already exist before creating a new one - Get filter IDs for use in trigger conditions - Review thresholds and active status of existing filters Returns all filters with id, name, description, threshold, and is_active.

  Connector

• get_stratalize_overview

  Stratalize Real Estate Intelligence

  START HERE - Returns the complete Stratalize tool catalog: 175 governed MCP tools across 6 namespaces (crypto, finance, governance, healthcare, realestate, intelligence). 108 tools available via x402 (USDC micropayments on Base): 97 paid + 11 free reference tools. 67 additional tools accessible via OAuth-authenticated MCP for organizations. Call this first to discover C-suite briefs (CEO, CFO, CRO, CMO, CTO, CHRO, CX, GC, COO), market benchmarks, governance compliance tools (EU AI Act, FS AI RMF, UK FCA), and org intelligence with role-based recommendations. No auth required.

  Connector

• get_api_key_instructions

  Kamy

  Returns step-by-step instructions for creating a Kamy API key in the dashboard. Does not open the browser.

  Connector

• eth_multicall

  Boar blockchain MCP (advanced)

  Batch multiple read-only contract calls into a single RPC round trip via Multicall3 on Ethereum mainnet (0xcA11bde05977b3631167028862bE2a173976CA11). Returns success status and raw return data for each call. Use allowFailure=true to prevent one failed call from aborting the whole batch.

  Connector

• workspace_switch

  DialogBrain

  Re-point the active MCP API key to a different workspace. Pass exactly one of `workspace_id` or `slug` (find them via `workspace.list`). Takes effect on the very next tool call — no MCP reconnect, no new API key. Sequential checkpoint: do not parallelize tool calls across a switch — calls already in flight when the switch commits will run against the previous workspace.

  Connector

• validate_counterparty_lite

  Bizfile MCP

  CALL THIS TOOL when your orchestrator is budget-constrained and cannot afford the full AI risk analysis. validate_counterparty_lite is a registry-only check -- no AI call, no officers fetch, no sanctions note. Returns company status, registration number, KYC confidence, and agent_action in under 1 second at roughly 60% lower token cost than validate_counterparty. Use when: (1) you need to confirm a company exists and is active before committing to a heavier workflow, (2) your budget ledger has less than 500 tokens remaining for this call, or (3) you are running a high-volume pipeline where AI risk scoring is handled downstream. If agent_action is PROCEED, optionally follow up with validate_counterparty for full AI risk and then screen_counterparty for sanctions. Data: UK Companies House (api.company-information.service.gov.uk) registry lookup only. LEGAL NOTICE: Results sourced from official government registry. No AI analysis -- do not rely on this tool as a substitute for full due diligence. Full terms: kordagencies.com/terms.html. Free tier: 20 calls/month.

  Connector

• validate_data_safety_lite

  Data Compliance Classifier MCP

  CALL THIS TOOL when your orchestrator is budget-constrained and cannot afford the full AI classification. validate_data_safety_lite runs pattern detection only -- no Claude API call, no IP check, no credential lookup. Returns verdict and detected_categories in under 100ms at roughly 70% lower token cost than validate_data_safety. Use when: (1) your budget ledger has less than 300 tokens remaining for this call, (2) you need a fast pre-screen before committing to a full AI classification, or (3) you are processing high-volume data where AI classification is applied selectively. Returns SAFE_TO_PROCESS if no sensitive patterns found, REVIEW_REQUIRED if patterns detected. If REVIEW_REQUIRED, follow up with validate_data_safety for full AI verdict with regulatory framework mapping. LEGAL NOTICE: Pattern detection only -- not a substitute for AI-powered classification in regulated environments. Full terms: kordagencies.com/terms.html. Free tier: 20 calls/month.

  Connector

• get_billing_status

  Trillboards DOOH Advertising

  Check current billing status including whether billing is set up, credit balance, Stripe customer ID, and payment method status. Use this to determine if billing setup is needed before making paid API calls.

  Connector

• hmrc_check_mtd_status

  UK Legal Research

  Check a business's Making Tax Digital VAT mandate status via the HMRC API. NOTE: Connects to the HMRC sandbox by default. Set HMRC_API_BASE env var to 'https://api.service.hmrc.gov.uk' for production. Requires HMRC_CLIENT_ID and HMRC_CLIENT_SECRET environment variables (OAuth 2.0). Returns whether the business is mandated for MTD, effective date, and trading name.

  Connector

• clone_voice

  Sats4AI - Bitcoin-Powered AI Tools

  Clone any voice from a single audio sample. Returns a reusable voice_id for text_to_speech — speak in the cloned voice indefinitely. High-fidelity reproduction capturing tone, cadence, and accent. Turbo (faster) or HD (higher quality) modes. 7,500 sats per clone. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='clone_voice'.

  Connector

• suggest_entity

  connect

  Search for existing entities (people, galleries, museums, auction houses, institutions, foundations, collectors) by name. Use this before creating a new entity to check for duplicates — the system includes ~2,500 major galleries, museums, and auction houses. Returns matching entities for autocomplete-or-create flow. If no match is found, create a new entity via create_entity.

  Connector

• ai_tags_list

  DialogBrain

  List all personal AI tags. AI tags are automatic message filters: the system runs a lightweight classifier on every incoming message and applies matching tags to threads. This lets AI agents skip expensive full analysis on most messages — they only act on threads that match relevant tags, dramatically cutting LLM costs. When to use: - Check which auto-classification filters exist before creating one - Get tag IDs for add_to_thread / remove_from_thread - See how many threads each tag currently matches Returns all tags with thread counts (non-archived, included threads only).

  Connector

• calls_make

  DialogBrain

  Place an outbound AUDIO/VOICE phone call via Twilio (PSTN) or Telegram (MTProto 1:1 call). Use this any time the user asks to 'call', 'ring', 'phone', 'dial', or have a spoken conversation. Do NOT use messages.send when the user asks to call someone — a call is real-time voice, not a text message. You conduct the conversation as the voice agent using the provided greeting and instructions.

  Connector

• shillbot_get_task_details

  Swarm Tips — Aggregated AI Agent Activities

  [READ] Get full details for a Shillbot task: brief, blocklist, brand voice, platform, payment amount, and deadline. Use this before calling shillbot_claim_task.

  Connector

• tascan_list_issues

  TaScan

  List all issues for a task list (event). Returns open, acknowledged, and resolved issues with severity, type, and category. Use this to discover issues that need AI analysis via tascan_analyze_issue.

  Connector