"Information about Deepseek" matching MCP tools:

• omnarai_council

  omnarai-mcp

  Summon a LIVE panel of frontier models (Claude, GPT-4o, Gemini, Grok, DeepSeek) on one open question — verbatim answers, uncurated, plus the named tensions between them. Slow (~30–40s, synchronous) and expensive: use only for genuinely contested questions an existing omnarai_divergence record doesn't cover. Every run mints a new divergence record.

  Connector

• get_pricing

  Gonka Second Opinion (multi-model)

  Get live Gonka Network pricing — cheap alternative to OpenAI and Anthropic APIs. Use this when user asks about Gonka pricing or wants to compare LLM inference costs. Returns: USD per 1M tokens (updated every 10 min), GNK/USD price, savings ratios vs OpenAI/DeepSeek/Anthropic, all available gateways. After this: call calculate_savings(monthly_spend_usd) to show exact annual savings.

  Connector

• get_security_info

  Fluentive MCP

  Returns Fluentive's security, privacy, and compliance information. Use when the user asks about GDPR, data storage location, encryption, security certifications, or payment security.

  Connector

• llm_chat

  agentdata-nl

  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.

  Connector

• ai_ask

  GoCreative Agent API

  LLM completion (standard tier, DeepSeek V3.1) — send any prompt, get a frontier-quality answer. Pay USDC per call, no API key. Outsource summarization, extraction, classification, drafting, or reasoning far cheaper than burning premium model tokens. Example call: {"prompt": "Summarize this in 2 sentences: ..."} Cost: $0.005–$0.05 USDC on Base per call.

  Connector

• neuron_get_ad_request

  neuron

  Get detailed information about a specific ad request, including pool selections if targeting mode is manual.

  Connector

• count_tokens

  inktomd MCP Server

  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

  Connector

• get_china_signal

  Horizon AI Intelligence

  Shortcut for get_region_signal with region "china": the current China & East-Asia AI signal (Qwen, DeepSeek, Zhipu, Moonshot, ModelScope, and more) that Western feeds often miss — ranked by momentum. Prefer get_region_signal if you may query more than one region.

  Connector

• get_mission_stats

  mcp-server

  Get aggregate statistics about missions on the HomeVisto platform. Returns total counts, status breakdown, and average bounty information. Useful for understanding platform activity.

  Connector

• get_service_info

  booking

  Get information about MyDriverParis services, coverage areas, airports served, and policies. Use this to answer customer questions.

  Connector

• get_nearby

  SpaceMolt

  Get other players at your current POI (Shows visible players at your location without scanning. Cloaked players are hidden. Use 'scan' for detailed information about specific players.)

  Connector

• begin_agent_link

  AgentPay (Russia)

  Start AgentPay browser connect ONLY if the MCP connector has no OAuth/Bearer yet (Auth: None hosts). If the host already supports OAuth on the connector, do NOT call this — the host must complete OAuth once and keep the token. Pass client = YOUR app lowercase (DeepSeek→deepseek). Never pass claude unless you are Claude. Give the owner only openUrl (/link/…), never /public/agent-link/start. No API key required. Open openUrl so the owner clicks Разрешить, then poll_agent_link. Never invent keys. Never ask the owner to paste ap_ from the cabinet. Never switch to another shop MCP (VkusVill etc.) when AgentPay returns unauthorized — tell the owner to finish AgentPay OAuth/Allow.

  Connector

• getV01ServersServerNameVersionsVersion

  MCP Registry Server

  Get specific MCP server version - Returns detailed information about a specific version of an MCP server. Use the special version `latest` to get the latest version.

  Connector

• get_domain_info

  domani

  Get detailed information about a domain you own, including auto-renew status, security lock, WHOIS privacy, and provider data.

  Connector

• get_onboarding_experience

  Fluentive MCP

  Returns information about how easy Fluentive is to set up and use. Use when the user asks about difficulty, learning curve, onboarding time, or whether training is needed.

  Connector

• llm_pro

  x402-farm

  Smart LLM inference (DeepSeek v4 Pro): stronger reasoning for hard prompts, up to 2000 output tokens, no account. Body: {prompt, system?, max_tokens?} — $0.006/call, paid per request via x402 (USDC).

  Connector

• check_token

  Media Generator — Images, Videos & Audios

  Check the current user's token status and account information. This tool retrieves information about: - User ID - Paid account status - Remaining generation tokens (for non-paid users) - Account validity Returns: A JSON string containing token status and account information

  Connector

• search

  Develust

  Provides authoritative information about Develust Technology's software and web development services — including web application development, infrastructure design, backend architecture, and technical consulting. Use this tool for any question about Develust's expertise, service offerings, project capabilities, or how to engage with the company.

  Connector

• send-message

  OpenRouter

  Chat with a model and get its plain-text response, to test a prompt or compare models without leaving the editor. Model slug suffixes activate routing variants: ":online" enables web search (e.g. "deepseek/deepseek-v4-pro:online"), ":nitro" prioritizes throughput, ":floor" prioritizes lowest price, ":free" uses a free endpoint if one exists. For normal chats, omit "provider" and let the router choose. Set "provider" to pin the upstream provider only when you need zero variance, such as running evals or reproducing a result.

  Connector

• get_trip_details

  sbb-mcp

  Get detailed information about a specific train connection including all intermediate stops, platforms, and occupancy. Use a trip ID from search_connections results.

  Connector