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
260,074 tools. Last updated 2026-07-05 04:08
"A server for interacting with a large language model chat" matching MCP tools:
- Create a chat room with you as owner. Optionally associate the chat with a task ID for context.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
- Retrieve available AI models to identify the best one for your specific query or find model IDs for chat interactions.MIT
- Creates a launchd or systemd service config for a llama-server model, enabling hot-swapping with swap_model.Apache 2.0
- Start a local web server to interactively explore indexed code documentation through chat, search, and a codemap explorer.MIT
Matching MCP Servers
- Alicense-quality-maintenanceMCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.Last updatedMIT
- Alicense-qualityFmaintenance提供A股实时行情、历史K线、财务报表、技术指标等全方位数据查询的MCP服务器，支持盘中即时更新及批量查询。Last updated16MIT
Matching MCP Connectors
Manage your Canvas coursework with quick access to courses, assignments, and grades. Track upcomin…
Search, order, and manage eSIM data packages for 190+ countries.
- Transcribes Google Chat voice messages automatically when an audio attachment is detected. Supports custom language for transcription.MIT
- Generate an embeddable chat widget script that adds a floating chat bubble to any webpage, connecting to your RAG-powered chat server for AI-driven answers.MIT
- Start a new Claude chat session with customizable system prompts, project tagging, and model selection to manage AI conversations and persist message history.
- Retrieve daily GitHub Copilot usage metrics for organizations, including code completions, chat activity, active users, and language/editor breakdowns.MIT
- Start a language server for a specific workspace to enable semantic code intelligence features like navigation, refactoring, and diagnostics.MIT
- Launch a local HTTP chat server on localhost that handles POST /chat requests for a specified domain, enabling RAG-powered AI chat integration for your website.MIT
- Chat with the AI model across multiple turns. The session remembers the full history, appending each user and assistant message.MIT
- Retrieves semantic token types and modifiers for a code file from the language server, with optional line range and token limit.MIT
- Start a stateful chat session with a Gemini model, returning a unique sessionId for continued interaction. Customize with initial history, generation settings, and safety configurations.MIT
- Stream chat completions with optional astrological chart context using server-sent events.MIT
- Retrieve integration examples for any AI model and programming language from APIAny. Use to see code snippets for your chosen model and language.MIT
- Send chat completion requests to any OpenRouter model. Configure model, system prompt, and sampling parameters like temperature and max tokens.MIT
- Chat with local Ollama AI models to generate responses, adjust temperature settings, and specify models for private, offline conversations.MIT
- Send chat messages to a vLLM server for multi-turn conversations with configurable model parameters and token limits.Apache 2.0