Chat with AI models using per-call micropayments in USDC on Base, authorized from your local wallet via x402.
MIT
731,453 tools. Updated 2026-11-01 09:28
"Using llama.cpp and Searxng with local models" matching MCP tools:
- Manage a local llama.cpp server by starting, stopping, or checking its status with configurable model, cache, and GPU settings.Apache 2.0
- List free-seat status and requestable local runtimes such as Ollama, llama.cpp, LM Studio, OpenAI-compatible servers, and vLLM.MIT
- List local Ollama models and retrieve queryable paid route labels for accessing AI models with payment options.MIT
- Perform web searches using SearXNG API to gather information, find news and articles, or explore diverse online sources for general queries and recent events.MIT
- List xAI API models, local Grok CLI models, and .grok model profiles separately to compare available options.MIT
Matching MCP Servers
- AlicenseAqualityCmaintenanceMCP server for local web search via SearXNG, providing unlimited queries without API keys or cost, with automatic fallback to public instances.31MIT
- FlicenseAqualityBmaintenanceEnables searching, comparing, and inspecting AI models by pricing, context window, and capabilities via the models.dev catalog.8-
Matching MCP Connectors
Epoch AI — AI models database
Ask Claude, GPT, Grok, GLM, Kimi or DeepSeek from your client; token price plus a $0.001 call fee.
- Search the web through a SearXNG instance and return paginated results with titles, URLs, and snippets, with filters for engines, language, time range, and safe search.MIT
- List all available models in Open WebUI, including Ollama local, OpenAI, and custom pipe models, with IDs, names, and sources.MIT
- Check if the local llama.cpp server is reachable and loaded, returning availability status and model metadata, to decide retry or cloud fallback.MIT
- Search the public web via local SearXNG for current or external information. Results are snippets, not verified facts; read important sources with web_read before relying on them.MIT
- List available compute backends including local GPU, Vertex AI, and Ollama, along with their models and latency.MIT
- Find web results via self-hosted SearXNG with local ML reranking. Filters blocked domains, boosts trusted ones, and returns top results with direct answers.MIT
- View available llama.cpp model configurations and check their current load status.Apache 2.0
- Searches the web via SearXNG and returns results with title, URL, and snippet. Supports pagination, time range, language, and safe search filtering.MIT
- Perform web searches via a private SearxNG instance, returning structured results with title, URL, and description. Includes pagination and graceful error handling.MIT
- Analyze images with MiniMax vision models. Use a local file path or remote URL to ask questions and get detailed answers, with options for adaptive thinking and token control.MIT
- Search the web via SearXNG to get ranked results with titles, URLs, and snippets. Use parameters to filter by language, time, and page number.MIT
- Performs web searches using SearXNG, returning results with titles, URLs, and snippets. Supports pagination, time range, language, and safety filters.MIT
- Run private web queries through a local SearXNG instance, rerank results with a local model, and return snippets, page highlights, or a cited answer.MIT
- Execute web searches via public SearXNG instances, returning structured results with URLs and summaries. Filter by time range, language, or enable detailed searches for comprehensive query responses.MIT
- Generate text embeddings with local models for semantic search, similarity comparisons, and clustering. Offload routine embedding tasks to save Claude tokens.MIT