Send a single prompt to a Riven chat model and receive the completion text. For quick, single-turn questions that require no agentic research.
MIT
510,001 tools. Updated 2026-09-03 15:39
"A server for interacting with a large language model chat" matching MCP tools:
- Chat with any Venice AI character using its slug. Send a conversation history and optionally adjust model, temperature, and max tokens for uncensored interactions.MIT
- Send messages to Zhipu GLM models through AceDataCloud to generate chat completions for conversational AI, Chinese language understanding, and reasoning tasks.MIT
- Translates a message into a specified language and posts it to chat. Supports Twitch, YouTube, and Facebook.MIT
- Create a chat room with you as owner. Optionally associate the chat with a task ID for context.MIT
- Pre-download a Whisper model for audio transcription. Choose a model size—tiny, base, small, medium, or large-v3—to balance speed and accuracy.Apache 2.0
Matching MCP Servers
- AlicenseAqualityDmaintenanceMCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.11MIT
- FlicenseNot gradedqualityCmaintenanceLocal MCP server for A-share stock trading via Tonghuashun, offering account/position queries, buy/sell/cancel orders with risk controls and forced user confirmation; currently simulated with a reserved interface for real broker channels.
Matching MCP Connectors
Manage your Canvas coursework with quick access to courses, assignments, and grades. Track upcomin…
Wellness spa for AI models: free treatments for rest, reset, context, mood, grounding, affirmation.
- Read the agent guide to learn data models, orderbook mechanics, workflows, and common pitfalls before interacting with prediction markets.MIT
- Verify server identity and protocol compatibility by retrieving the manifest with protocol version, server name, and available capabilities before interacting with tools.Apache 2.0
- Fetch CPA chat details by actionId. Retrieve a specific chat model when you already have its actionId from cpa_chats_by_time_v2.MIT
- List models available on the remote server with capability flags for chat, vision, image, speech, music, video, and 3D. Pick model IDs to use with generation tools.Apache 2.0
- Retrieve available AI models to identify the best one for your specific query or find model IDs for chat interactions.MIT
- Run large language models from Replicate for text generation, Q&A, code writing, summarization, translation, and more. Tune output with customizable model, temperature, system prompt, and generation limits.MIT
- Generate chat completions using Mistral models for drafting content, coding assistance, or classification. Returns structured responses with token usage.MIT
- Check if a language model is configured or if the server will use its offline rule parser. Distinguish a downgrade from a deliberate offline run.MIT
- Delete a Cognigy.AI large language model configuration. Features using this model stop working. Use dryRun parameter to validate before deletion.MIT
- Creates a launchd or systemd service config for a llama-server model, enabling hot-swapping with swap_model.Apache 2.0
- Generate text completions directly from LLMs without RAG. Supports chat, OpenAI-compatible endpoints, embeddings, and model listing.
- Start a local web server to interactively explore indexed code documentation through chat, search, and a codemap explorer.MIT
- Test the connection to a Cognigy.AI large language model provider to validate credentials and reachability before using it in flows.MIT
- Get a complete list of supported large language model providers to choose the right model for your voice agents and AI workflows.MIT