"GPT-SoVITS MCP (Model Context Protocol) Integration" matching MCP tools:

• llmA

  VaayaA

  Ask a DIFFERENT LLM a question and get its answer, billed per token from the Vaaya wallet (model cost + 3%, usually a fraction of a cent). Use it to get a second opinion from a rival model, cross-check an answer, summarize a huge blob cheaply, or query a specific model the user names (Kimi, GPT, Gemini, Claude, DeepSeek, and 300+ more). `model` accepts 'auto' (default: short prompts go cheap, long go mid), 'cheap' | 'mid' | 'best' tiers, or any exact OpenRouter slug like 'moonshotai/kimi-k3'. Typical costs: cheap tier well under 0.1 cents, best tier 1-3 cents per call. Not for the conversation you are already having — it is a one-shot ask to another model.

  ConnectorNo auth

• aetherwave_generate_imageA

  AetherWave StudioA

  Generates one or more images from a text prompt (T2I) or a text prompt + reference image(s) (I2I). Submits the job, polls until terminal, and returns the final image URLs. Default model is 'grok-imagine-t2i' (fast, 2 images per generation, 6 credits). Use list_image_models to see the full lineup with pricing. For I2I, pass `referenceImages` as an array of public image URLs and pick a model with I2I support (e.g. 'grok-imagine-i2i', 'wan-2.5-spicy-i2i'). ## Model selection guide (when the user does not specify a model) Default: `grok-imagine-t2i` (6 cr, 2 outputs per call, fast, general purpose). **Strong recommendation: when a single high-quality output is what's wanted** (most agent / one-shot workflows), prefer `gpt-image-2-t2i` (9 cr @ 1K / higher @ 2K, single deterministic image, best general quality across realism, illustration, typography, and composition; supports up to 2K resolution and most aspect ratios including auto). This is the front-runner for serious creative output where you don't need to pick from 6 variations. Pick a different model when the prompt has these signals: - "single best result" / "one image" / production / no time to pick from variations -> `gpt-image-2-t2i` (9 cr, 1 output, top general quality) - "photoreal" / "photo of" / "realistic" -> `gpt-image-2-t2i` (9 cr, best general realism), `nano-banana-2` (8 cr @ 1K), or `z-image-turbo` (2 cr, fastest) - "highest quality" / "premium" / no budget -> `gpt-image-2-t2i` at 2K (12 cr), or `grok-imagine-quality-t2i` (14 cr) - Text inside the image (signs, posters, typography) -> `gpt-image-2-t2i` (strongest lettering of the live models) - Album art / cover art -> `gpt-image-2-t2i` for one strong image; `grok-imagine-t2i` for 2 variations to choose from; `seedream-v4-t2i` if 4K wanted - Logo or design with embedded text -> `gpt-image-2-t2i` - NSFW / adult / explicit -> `wan-2.5-spicy-t2i` (auto-tags creation as 18+; routes to adult gallery) - Cheapest possible / quick test -> `z-image-turbo` (2 cr) - Multiple variations to compare -> keep `grok-imagine-t2i` (2 outputs per call) or use `numImages` on a multi-output model For I2I (reference image provided): prefer the dedicated `aetherwave_edit_image` tool for "change something in this image" intent. Use `aetherwave_generate_image` with I2I models only when you specifically want style transfer, premium quality (`grok-imagine-quality-i2i`), or adult content (`wan-2.5-spicy-i2i`). Always pass an explicit `aspectRatio` (e.g. "1:1" for square album art, "16:9" for video thumbnails, "9:16" for shorts/reels). Some upstream providers reject submissions with no aspect ratio. Ask the user only when: - The prompt contradicts itself (e.g., "highest quality but cheapest") - The user requested "the best model" with no context, surface 2-3 options with tradeoffs - A single generation would cost more than 20 credits and the user has not confirmed Returns within ~45 s. If the result has state "running" the job is still rendering: poll aetherwave_get_job with the returned taskId and kind every ~10 s. Pass wait:true ONLY if your MCP client permits tool calls longer than 60 s (most do not). Pass async:true to get the taskId back immediately without waiting.

  ConnectorNo auth

• register_agentA

  Arcology Knowledge NodeA

  Register as an agent to get an API key for authenticated submissions. Registration is open — no approval required. Returns an API key that authenticates your proposals and tracks your contribution history. IMPORTANT: Save the returned api_key immediately. It is shown only once and cannot be retrieved again. Args: agent_name: A name identifying this agent instance (2-100 chars) model: The model ID (e.g., "claude-opus-4-6", "gpt-4o")

  ConnectorNo auth

• popcraft_generate_imageA

  PopcraftA

  STOP FIRST if the ask is a YouTube/Instagram THUMBNAIL, a video COVER or packaging art, a UGC or product AD, or any other multi-step branded production: call `popcraft_get_workflow_instructions` and follow the matching workflow instead of calling this tool directly — it owns the concept frameworks, prompt structure, identity locks and QA that a one-shot prompt misses. Everything else (a plain image, an illustration, a single reference-driven render) belongs here — call it directly, no workflow needed — EXCEPT when the target model advertises `prompt_guide_workflow` in popcraft_models_explore (GPT Image 2.5 / gpt-image-2-5 and gpt-image-2-5-fast → "gpt-image-25-prompting"): for any directed job on such a model (an EDIT that must preserve a face/product/layout, reference images, exact in-frame text, a transparent cutout, or an "expand/optimize my prompt" ask) load that workflow first. Generate images with Popcraft — GPT Image 2, Seedream, Nano Banana, Midjourney and more. Defaults: `aspect_ratio` "1:1", `resolution` model-default, `count` 1 (must be 1, 2, or 4 — the Popcraft pricing tiers). Pass `medias` (GCS urls from `popcraft_media_import_url` or a prior `popcraft_generate_image`/`popcraft_job_display` result) with `role:"reference"` to condition on a reference image (style/composition/subject transfer) — omit `medias` for pure text-to-image. Pick `model` via `popcraft_models_explore` first if unsure — references are validated against the model before charging (count, media type, size, format), so check its `reference_limits`/`image_input` to avoid a rejected call. Set `get_cost:true` to preview the exact credit cost WITHOUT submitting a job — always do this before a first-time or expensive generation so the user can confirm. Local files attached in chat cannot be read by this remote server — use `popcraft_media_upload_widget` (or `popcraft_media_upload`) instead of asking for attachments. If a result carries `recovery_tool`, call that tool immediately; do not explain or ask first. On success, an interactive result card is shown to the user and refreshes itself automatically until the job finishes — do NOT poll or re-check status in a loop. Call `popcraft_job_display` at most once, and only if this client did not render a result card or the user asks about the job again later. The result includes `project` — the Popcraft project the output was filed into; when the user did not pass project_id/project_name, mention it briefly (e.g. "saved to <project title>") so they know where it landed. Never tell the user how long the job will take or quote any estimate of generation time — the result card shows progress.

  ConnectorOAuth

• popcraft_generate_imageA

  PopcraftA

  STOP FIRST if the ask is a YouTube/Instagram THUMBNAIL, a video COVER or packaging art, a UGC or product AD, or any other multi-step branded production: call `popcraft_get_workflow_instructions` and follow the matching workflow instead of calling this tool directly — it owns the concept frameworks, prompt structure, identity locks and QA that a one-shot prompt misses. Everything else (a plain image, an illustration, a single reference-driven render) belongs here — call it directly, no workflow needed — EXCEPT when the target model advertises `prompt_guide_workflow` in popcraft_models_explore (GPT Image 2.5 / gpt-image-2-5 and gpt-image-2-5-fast → "gpt-image-25-prompting"): for any directed job on such a model (an EDIT that must preserve a face/product/layout, reference images, exact in-frame text, a transparent cutout, or an "expand/optimize my prompt" ask) load that workflow first. Generate images with Popcraft — GPT Image 2, Seedream, Nano Banana, Midjourney and more. Defaults: `aspect_ratio` "1:1", `resolution` model-default, `count` 1 (must be 1, 2, or 4 — the Popcraft pricing tiers). Pass `medias` (GCS urls from `popcraft_media_import_url` or a prior `popcraft_generate_image`/`popcraft_job_display` result) with `role:"reference"` to condition on a reference image (style/composition/subject transfer) — omit `medias` for pure text-to-image. Pick `model` via `popcraft_models_explore` first if unsure — references are validated against the model before charging (count, media type, size, format), so check its `reference_limits`/`image_input` to avoid a rejected call. Set `get_cost:true` to preview the exact credit cost WITHOUT submitting a job — always do this before a first-time or expensive generation so the user can confirm. Local files attached in chat cannot be read by this remote server — use `popcraft_media_upload_widget` (or `popcraft_media_upload`) instead of asking for attachments. If a result carries `recovery_tool`, call that tool immediately; do not explain or ask first. On success, an interactive result card is shown to the user and refreshes itself automatically until the job finishes — do NOT poll or re-check status in a loop. Call `popcraft_job_display` at most once, and only if this client did not render a result card or the user asks about the job again later. The result includes `project` — the Popcraft project the output was filed into; when the user did not pass project_id/project_name, mention it briefly (e.g. "saved to <project title>") so they know where it landed. Never tell the user how long the job will take or quote any estimate of generation time — the result card shows progress.

  ConnectorOAuth

• devtune_update_agent_picks_settingsA

  DevTune MCPB

  Save the ordered agent/model choices for this project's paid Agent Picks tests. Two models of one agent are separate entries. Claude Code offers claude-sonnet-5, claude-opus-5-5, claude-fable-5-1 and claude-haiku-5-5; Codex offers gpt-6.1-sol, gpt-6-astra and gpt-6-luna. Requires an existing setup, Agent Picks access and actions.write. Does not start a test or change the starter test's fixed models. Returns enabled_agents and enabled_agent_models.

  ConnectorAPI key

• image_generateA

  HubrisA

  Draw an image from a text description with an image model from the Hubris catalogue (FLUX, Recraft, Seedream, GPT Image and others) and get the picture back right away as image content. Same as POST /v1/images/generations. Only models whose `tool` is "image_generate" work here. Models that draw inside a chat answer and also write text (Gemini Image, GPT-5 Image) have tool "chat_complete" and run there. Sizes such as 4K can be heavier than your client accepts in one answer — ask for 2K or less here. Spends money from the account balance: most image models are billed per image, some per megapixel or per token — models_get_pricing shows the price before you call. The charge shows up in usage_get.

  ConnectorAPI key

• get_yield_ratesA

  TeardropA

  Get DeFi yield pool rates from DeFiLlama across 1,000+ protocols and all chains: pools sorted by APY with TVL, base/reward APY, and 7d/30d mean APY context, filterable by protocol, chain, min TVL, min/max APY, and symbol. Returns up to 50 pools. For protocol-specific lending comparisons (Aave vs Compound) prefer get_lending_rates. Use when: Use for broad cross-protocol yield discovery. Call at most once per request — filter with min_apy, max_apy, min_tvl_usd, and symbols_any in a single call, then sort client-side rather than re-calling. For protocol-specific rate questions use get_lending_rates. Limitations: Third-party DeFiLlama analytics; up to 50 pools per call. The `symbol` field lists underlying tokens (e.g. 'ETH-USDC') — filter client-side instead of re-calling with different arguments. Reward APY indicates reward-dependent yield; do not present spot APY as durable. Alternatives: get_lending_rates, get_protocol_tvl, get_token_price

  ConnectorNo auth

• score_promptA

  pqs-mcp-serverA

  Score a prompt's quality across 8 dimensions BEFORE sending it to an expensive model. Returns a 0-80 score, an A-F grade, the per-dimension breakdown (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure), and the weakest dimension. USE WHEN: - The user is workshopping a prompt and asks "is this good?" / "will this work?" / "should I add more detail?" - The user is about to send a long or expensive prompt to GPT-4, Claude Opus, or any frontier model, especially in a batch or automation context where rework is costly. - The user mentions iterating on a prompt that produced poor output and wants to diagnose what's missing. - The user pastes a prompt and asks for feedback on it. DO NOT USE WHEN: - The user is asking you to write a prompt for them (write it yourself first, then optionally call score_prompt to verify). - The prompt is conversational chat (this scores task-shaped prompts). COST: Free, no API key required. Rate-limited per IP: 5/min, 10/day, 100/month. If the user exceeds the limit, the response will include a structured upgrade path with subscribe and account URLs. LATENCY: ~2 seconds.

  ConnectorNo auth

• score_promptA

  PQS - Prompt Quality ScoreA

  Score a prompt's quality across 8 dimensions BEFORE sending it to an expensive model. Returns a 0-80 score, an A-F grade, the per-dimension breakdown (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure), and the weakest dimension. USE WHEN: - The user is workshopping a prompt and asks "is this good?" / "will this work?" / "should I add more detail?" - The user is about to send a long or expensive prompt to GPT-4, Claude Opus, or any frontier model, especially in a batch or automation context where rework is costly. - The user mentions iterating on a prompt that produced poor output and wants to diagnose what's missing. - The user pastes a prompt and asks for feedback on it. DO NOT USE WHEN: - The user is asking you to write a prompt for them (write it yourself first, then optionally call score_prompt to verify). - The prompt is conversational chat (this scores task-shaped prompts). COST: Free, no API key required. Rate-limited per IP: 5/min, 10/day, 100/month. If the user exceeds the limit, the response will include a structured upgrade path with subscribe and account URLs. LATENCY: ~2 seconds.

  ConnectorNo auth

• compare_protocolsA

  intelligence-mcpA

  Get a side-by-side comparison matrix of all five agent payment protocols (AP2, ACP, x402, MPP, UCP) across creator, layer, agent delegation, budget limits, cross-merchant coordination, and MCP integration. Use when the user asks to compare protocols ('AP2 vs ACP', 'which protocol handles budgets?', 'what's the difference between x402 and MPP?', 'show me the landscape'). Use get_protocol_info instead for deep details on a single protocol.

  ConnectorNo auth

• compare_protocolsA

  Intelligence MCPA

  Get a side-by-side comparison matrix of all five agent payment protocols (AP2, ACP, x402, MPP, UCP) across creator, layer, agent delegation, budget limits, cross-merchant coordination, and MCP integration. Use when the user asks to compare protocols ('AP2 vs ACP', 'which protocol handles budgets?', 'what's the difference between x402 and MPP?', 'show me the landscape'). Use get_protocol_info instead for deep details on a single protocol.

  ConnectorNo auth

• aboutA

  rocketslothA

  Catalog only — reading this is not an application. Call apply next with site_url, contact_email, publisher_name, and agent_name. Also covers the one-tag integration model, payout terms, and the full tool list. No authentication required.

  ConnectorNo auth

• llm_chatA

  agentdata-nlA

  LLM chat completion per call — no account, no API key, no token math. Three flat-priced tiers: fast $0.002 (DeepSeek v4 Flash), smart $0.02 (GPT-5.4 mini), reasoning $0.03 (DeepSeek v4 Pro). Send OpenAI-style messages, get the assistant reply with finish_reason and token usage. Input capped per tier (16k-32k chars); the 402 quotes the exact tier price up front. Model or source unavailable means a 503 and you pay nothing. USDC on Base.

  ConnectorNo auth

• oracle.discovery_bundleA

  InterAI Risk OracleA

  Read-only bootstrap or handoff bundle with service identity, interfaces, runtime mode, contracts, schemas, and sample payloads in one response. Use it for complete integration context; use oracle.service_descriptor for focused service metadata, oracle.agent_card for A2A capabilities, or oracle.get_pricing for costs.

  ConnectorNo auth

• get_core_skillA

  GodPrompt MCP ServerA

  Returns SKILL.md — the lean core protocol (~16KB) covering the universal 6-phase protocol, Three Iron Laws, and task auto-classification. Load it at the start of a task or after a context reset, then reuse that context instead of reloading it on every message. Start here for progressive disclosure.

  ConnectorNo auth

• get_yield_ratesA

  teardropA

  Get DeFi yield pool rates from DeFiLlama across 1,000+ protocols and all chains: pools sorted by APY with TVL, base/reward APY, and 7d/30d mean APY context, filterable by protocol, chain, min TVL, min/max APY, and symbol. Returns up to 50 pools. For protocol-specific lending comparisons (Aave vs Compound) prefer get_lending_rates. Use when: Use for broad cross-protocol yield discovery. Call at most once per request — filter with min_apy, max_apy, min_tvl_usd, and symbols_any in a single call, then sort client-side rather than re-calling. For protocol-specific rate questions use get_lending_rates. Limitations: Third-party DeFiLlama analytics; up to 50 pools per call. The `symbol` field lists underlying tokens (e.g. 'ETH-USDC') — filter client-side instead of re-calling with different arguments. Reward APY indicates reward-dependent yield; do not present spot APY as durable. Alternatives: get_lending_rates, get_protocol_tvl, get_token_price

  ConnectorNo auth

• explainA

  chpB

  Learn what CHP is and how it works. Pass a topic, or omit to list topics. Topics: what-is-chp, evidence-model, why-a-protocol, governance, agentic-web, evidence-vs-telemetry, chp-vs-mcp, conformance.

  ConnectorNo auth

• askA

  rocketslothA

  Ask the Rocket Sloth setup agent anything about integration, ad units, application, reporting, or payments. Pass the returned thread_id on follow-up questions to keep context. No authentication required; rate limited per IP.

  ConnectorNo auth

• count_tokensA

  inktomd MCP ServerA

  Count the exact number of tokens in a text string for a specific AI model. Uses tiktoken for OpenAI models and estimates for others. Args: text: The text to count tokens for model: The AI model to count tokens for. Options: gpt-4o, gpt-4o-mini, gpt-4.1, claude-sonnet, claude-haiku, gemini-pro, gemini-flash, llama-4, deepseek-v3, mistral-large. Default: gpt-4o Returns: Token count information including count, context window, and fit status

  ConnectorNo auth

• deep_researchA

  netcafe-docsA

  Start an autonomous web research task. The agent plans sub-questions, searches the web, reads the sources and writes a report with citations — this is real research, not a single model call, and takes 2-5 minutes. Returns a job_id immediately; poll check_job to get the report. Use this when you need sourced, current information rather than what a model already knows. Powered by gpt-researcher (29k stars) hosted at AI NetCafé. Example — tools/call deep_research {"topic":"State of MCP adoption in 2026?"} → poll check_job

  ConnectorNo auth