VideoDB Agent Toolkit

What is VideoDB Agent Toolkit about?

Provides continuously updated, modular context files that expose VideoDB SDKs, docs, and real‑world examples to large language models and autonomous agents. The toolkit generates both a lightweight metadata file (llms.txt) and a comprehensive context bundle (llms-full.txt) and makes them available via a Model Context Protocol (MCP) server.

How to use VideoDB Agent Toolkit?

1. Clone the repository

   git clone https://github.com/video-db/agent-toolkit.git
   cd agent-toolkit
   

2. Install the MCP server (recommended with npx):

   npx -y videodb-director-mcp
   

   Set the required API key via environment variable API_KEY before running:

   export API_KEY=<YOUR_API_KEY>
   npx -y videodb-director-mcp
   

3. Consume the context files
   • Add https://videodb.io/llms.txt to your agent’s discovery list for quick metadata.
   • Pull the full context from https://videodb.io/llms-full.txt when deep integration is needed.
4. Customize
   • Edit config.yaml to include or exclude specific docs, notebooks, or SDK sections.
   • The GitHub Actions workflows will automatically rebuild the context on each change.

Key Features of VideoDB Agent Toolkit

• Modular context generation (instructions, SDK, docs, examples).
• Automated updates via GitHub Actions triggered by SDK, documentation, or notebook changes.
• Two output formats: lightweight llms.txt for discovery and full‑featured llms-full.txt for deep integration.
• MCP server for on‑demand context retrieval, compatible with any MCP‑enabled client.
• Centralized configuration through config.yaml (patterns, custom LLM prompts, layout).
• Token statistics displayed in the repository for transparency.

Use Cases of VideoDB Agent Toolkit

• AI‑driven IDEs (e.g., Cursor) that need up‑to‑date SDK usage examples.
• Chat assistants (Claude Code, Copilot) that can answer VideoDB‑specific queries.
• Custom agents that automatically discover the service via llms.txt.
• Automated documentation bots that generate answers from the latest docs.
• Continuous integration pipelines that validate code snippets against the latest SDK.

FAQ

• Do I need to run the MCP server locally? No, you can fetch the static llms.txt and llms-full.txt files directly from the hosted URLs. Run the MCP server only if you need dynamic context retrieval.
• What programming languages are supported? The toolkit ships Python SDK context but can be extended to any language by adding appropriate generators in the workflow.
• How are the context files kept up‑to‑date? GitHub Actions monitor changes in the SDK repo, documentation site, and example notebooks, then regenerate the files and push them to the repository.
• Can I customize the summarization prompts? Yes, edit the config.yaml file to provide custom LLM prompts for each content type.
• Is there a rate limit for the MCP endpoint? The MCP server follows the limits of the underlying VideoDB API keys; manage usage via your API plan.

VideoDB Agent Toolkit

The VideoDB Agent Toolkit exposes VideoDB context to LLMs and agents. It enables integration to AI-driven IDEs like Cursor, chat agents like Claude Code etc. This toolkit automates context generation, maintenance, and discoverability. It auto-syncs SDK versions, docs, and examples and is distributed through MCP and llms.txt

🚀 Quick Overview

The toolkit offers context files designed for use with LLMs, structured around key components:

llms-full.txt — Comprehensive context for deep integration.

llms.txt — Lightweight metadata for quick discovery.

MCP (Model Context Protocol) — A standardized protocol.

These components leverage automated workflows to ensure your AI applications always operate with accurate, up-to-date context.

📦 Toolkit Components

1. llms-full.txt (View »)

---

llms-full.txt consolidates everything your LLM agent needs, including:

• Comprehensive VideoDB overview.

• Complete SDK usage instructions and documentation.

• Detailed integration examples and best practices.

Real-world Examples:

• VideoDB's Director code-assistant agent (View Implementation )
• VideoDB's Discord Bot to power customer support and community help (View Implementation )
• Integrate llms-full.txt directly into your LLM-powered workflows, agent systems, or AI coding environments.

2. llms.txt (View »)

---

A streamlined file following the Answer.AI llms.txt proposal. Ideal for quick metadata exposure and LLM discovery.

ℹ️ Recommendation: Use llms.txt for lightweight discovery and metadata integration. Use llms-full.txt for complete functionality.

3. MCP (Model Context Protocol)

The VideoDB MCP Server connects with the Director backend framework, providing a single tool for many workflows. For development, it can be installed and used via uvx for isolated environments. For more details on MCPs, please visit here

Install uv

We need to install uv first.

For macOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

For Windows:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

You can also visit the installation steps of uv for more details here

Run the MCP Server

You can run the MCP server using uvx using the following command

uvx videodb-director-mcp --api-key=VIDEODB_API_KEY

Update VideoDB Director MCP package

To ensure you're using the latest version of the MCP server with uvx, start by clearing the cache:

uv cache clean

This command removes any outdated cached packages of videodb-director-mcp, allowing uvx to fetch the most recent version.

If you always want to use the latest version of the MCP server, update your command as follows:

uvx videodb-director-mcp@latest --api-key=<VIDEODB_API_KEY>

🧠 Anatomy of LLM Context Files

LLM context files in VideoDB are modular, automatically generated, and continuously updated from multiple sources:

🧩 Modular Structure:

• Instructions — Best practices and prompt guidelines View »

• SDK Context — SDK structure, classes, and interface definitions View »

• Docs Context — Summarized product documentation View »

• Examples Context — Real-world notebook examples View »

Automated Maintenance:

• Managed through GitHub Actions for automated updates.
• Triggered by changes to SDK repositories, documentation, or examples.
• Maintained centrally via a config.yaml file.

---

🛠️ Automation with GitHub Actions

Automatic context generation ensures your applications always have the latest information:

🔹 SDK Context Workflow (View)

• Automatically generates documentation from SDK repo updates.
• Uses Sphinx for Python SDKs.

🔹 Docs Context Workflow (View)

• Scrapes and summarizes documentation using FireCrawl and LLM-powered summarization.

🔹 Examples Context Workflow (View)

• Converts and summarizes notebooks into practical context examples.

🔹 Master Context Workflow (View)

• Combines all sub-components into unified llms-full.txt.
• Generates standards-compliant llms.txt.
• Updates documentation with token statistics for transparency.

---

🛠️ Customization via config.yaml

The config.yaml file centralizes all configurations, allowing easy customization:

• Inclusion & Exclusion Patterns for documentation and notebook processing
• Custom LLM Prompts for precise summarization tailored to each document type
• Layout Configuration for combining context components seamlessly

config.yaml > llms_full_txt_file defines how llms-full.txt is assembled:

llms_full_txt_file:
  input_files:
    - name: Instructions
      file_path: "context/instructions/prompt.md"
    - name: SDK Context
      file_path: "context/sdk/context/index.md"
    - name: Docs Context
      file_path: "context/docs/docs_context.md"
    - name: Examples Context
      file_path: "context/examples/examples_context.md"
  output_files:
    - name: llms_full_txt
      file_path: "context/llms-full.txt"
    - name: llms_full_md
      file_path: "context/llms-full.md"
  layout: |
    {{FILE1}}

    {{FILE2}}

    {{FILE3}}

    {{FILE4}}

💡 Best Practices for Context-Driven Development

• Automate Context Updates: Leverage GitHub Actions to maintain accuracy.
• Tailored Summaries: Use custom LLM prompts to ensure context relevance.
• Seamless Integration: Continuously integrate with existing LLM agents or IDEs.

By following these practices, you ensure your AI applications have reliable, relevant, and up-to-date context—critical for effective agent performance and developer productivity.

---

🚀 Get Started

Clone the toolkit repository and follow the setup instructions in config.yaml to start integrating VideoDB contexts into your LLM-powered applications today.

Explore further:

• VideoDB SDK
• Documentation
• Cookbook Examples

---