Query Okareo documentation to understand concepts like Scenarios, Checks, Targets, Drivers, Evaluations, and Simulations. Choose conceptual mode for technical detail or user_legible for plain-language explanations.
Apache 2.0
717,863 tools. Updated 2026-10-29 08:48
"Local RAG system for providing documentation to a large language model (LLM)" matching MCP tools:
- Convert local files or URLs in 22 formats (PDF, DOCX, PPTX, XLSX, EPUB, RTF) to heading-aware Markdown for RAG ingestion and LLM context.MIT
- Discover available module documentation pages to guide implementation. Use before retrieving specific docs or modifying generated source.MIT
- Register a generation model for testing by selecting an LLM from the registry, enabling use with run_test.Apache 2.0
- Update a registered generation model to point to a different LLM from the registry, enabling model swaps.Apache 2.0
- Delegate text or chat completion to a local LLM to save costs and keep data private. Supports streaming via progress notifications.Creative Commons Attribution Non Commercial No Derivatives 4.0 International
Matching MCP Servers
- FlicenseNot gradedqualityCmaintenanceMCP server for a modular RAG system that enables natural language question answering over enterprise documents with intent-aware routing, adaptive retrieval, and citation-backed responses.-
- FlicenseNot gradedqualityBmaintenanceEnables MCP clients like Claude Code to delegate coding tasks to a local model through a configurable coding-agent CLI backed by any OpenAI-compatible endpoint, with tools for health checks, task execution, and context-aware file modifications.-
Matching MCP Connectors
Check if a task runs locally vs cloud. Save money on calls that don't need cloud inference.
Fetch URLs and return clean Markdown for RAG — nav, ads and boilerplate stripped.
- Inspect local memory-system health as JSON, including memory counts, maintenance status, graph statistics, and LLM provider status for a selected project context.MIT
- Retrieve timed YouTube transcripts by video ID, including auto-generated tracks. Use for RAG/LLM ingestion, summaries, or searchable archives.MIT
- Check if a machine learning model fits on local hardware by estimating weight and KV-cache size, then comparing against available GPU VRAM or system RAM.Creative Commons Attribution Non Commercial No Derivatives 4.0 International
- Convert a natural-language show description into a validated cue list (scenes) for TouchDesigner via LLM or grammar parser. Optionally build a cue sequencer rig.MIT
- Verify that an LLM response engaged with the provided source document using the Semantic Grounding Index score. Ideal for auditing RAG pipeline provenance.Apache 2.0
- Check the current status of the RAG documentation index, including total chunks, configured sources, and last update times.Apache 2.0
- Register a GitHub repository as a documentation source for RAG indexing. Specify repo, branch, and file patterns, then run ingestion to make the docs searchable.Apache 2.0
- Search Python library documentation using natural language queries to find specific functions, classes, and usage examples from consolidated sources.MIT
- Get precise answers to any question about Lamatic.ai documentation by searching all indexed docs with RAG.MIT
- Generate an OPC UA YAML model from a natural language description using AI. Automatically detects companion specs and validates the model.Apache 2.0
- Send a prompt to a specific NVIDIA model, with optional system prompt, images, and generation settings, to get a text response.MIT
- Search Noir documentation to find language guides, tutorials, and API documentation by query.MIT
- Retrieve LLM-readable documentation for a module, including rules and implementation notes, to guide coding against the module contract.MIT
- Extract a YouTube video's captions as JSON with timestamped segments, joined text, and available languages for LLM, RAG, subtitle, and content-analysis pipelines.MIT
- Configure a custom large language model by specifying provider, model, API key, and parameters like temperature and max tokens.MIT