Onyx Knowledge Base
Bridges Onyx knowledge bases with semantic search and chat capabilities, enabling teams to access or...
Log in to your Onyx instance with API access.
- Ensure you have administrator or appropriate permissions to generate API tokens.
Navigate to the API section of the Onyx Admin Panel.
- Look for a section labeled "API" or "Tokens." The exact navigation may vary based on your Onyx installation.
Generate a new Onyx API token.
- Find the option to create an API token, usually labeled "Create Token," "New API Token," or similar.
- Optionally, configure the token with the desired permissions and description.
Copy the generated API token.
- The token will usually be displayed only once after creation. Copy it and store it securely.
(Optional) Locate your Onyx API URL.
- The default is typically
http://localhost:8080/api, but this might differ if your Onyx instance runs elsewhere. Check your deployment details or with your Onyx administrator.
- The default is typically
Add the API token and URL in the FastMCP connection interface.
- When prompted in FastMCP, paste the copied API token into the
ONYX_API_TOKENfield. - Enter your Onyx API URL (such as
http://localhost:8080/api) into theONYX_API_URLfield.
- When prompted in FastMCP, paste the copied API token into the
Click “Install Now” to add the ENVs and finish the setup.
Your Onyx MCP server should now be connected to your client or application!
Quick Start
Choose Connection Type for
Authentication Required
Please sign in to use FastMCP hosted connections
Configure Environment Variables for
Please provide values for the following environment variables:
started!
The MCP server should open in . If it doesn't open automatically, please check that you have the application installed.
Copy and run this command in your terminal:
Make sure Gemini CLI is installed:
Visit Gemini CLI documentation for installation instructions.
Make sure Claude Code is installed:
Visit Claude Code documentation for installation instructions.
Installation Steps:
Configuration
Installation Failed
More for AI and Machine Learning
View All →Blender
Experience seamless AI-powered 3D modeling by connecting Blender with Claude AI via the Model Context Protocol. BlenderMCP enables two-way communication, allowing you to create, modify, and inspect 3D scenes directly through AI prompts. Control objects, materials, lighting, and execute Python code in Blender effortlessly. Access assets from Poly Haven and generate AI-driven models using Hyper3D Rodin. This integration enhances creative workflows by combining Blender’s robust tools with Claude’s intelligent guidance, making 3D content creation faster, interactive, and more intuitive. Perfect for artists and developers seeking AI-assisted 3D design within Blender’s environment.
Video Edit (MoviePy)
MoviePy-based video editing server that provides comprehensive video and audio processing capabilities including trimming, merging, resizing, effects, format conversion, YouTube downloading, and text/image overlays through an in-memory object store for chaining operations efficiently.
ElevenLabs
Unleash powerful Text-to-Speech and audio processing with the official ElevenLabs MCP server. It enables MCP clients like Claude Desktop, Cursor, and OpenAI Agents to generate speech, clone voices, transcribe audio, and create unique sounds effortlessly. Customize voices, convert recordings, and build immersive audio scenes with easy-to-use APIs designed for creative and practical applications. This server integrates seamlessly, expanding your AI toolkit to bring rich, dynamic audio experiences to life across various platforms and projects.
TypeScript Refactoring
Provides TypeScript/JavaScript code analysis and refactoring capabilities using ts-morph, enabling intelligent code transformations with symbol renaming, file moving with import path corrections, cross-file reference updates, type signature analysis, and module dependency exploration across entire codebases.
Dual-Cycle Reasoner
Provides dual-cycle metacognitive reasoning framework that detects when autonomous agents get stuck in repetitive behaviors through statistical anomaly detection and semantic analysis, then automatically diagnoses failure causes and generates recovery strategies using case-based learning.
Ultra (Multi-AI Provider)
Unified server providing access to OpenAI O3, Google Gemini 2.5 Pro, and Azure OpenAI models with automatic usage tracking, cost estimation, and nine specialized development tools for code analysis, debugging, and documentation generation.