doc_assistant
Simplify video application development by organizing and managing document-related tasks efficiently within VideoDB Director.
Instructions
Context for creating video applications using VideoDB
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Implementation Reference
- The handler function for the 'doc_assistant' tool, registered via @mcp.tool decorator. It fetches VideoDB documentation from DOCS_ASSISTANT_TXT_URL and returns it as a string.@mcp.tool( name="doc_assistant", description="Context for creating video applications using VideoDB", ) def doc_assistant() -> str: try: response = requests.get(DOCS_ASSISTANT_TXT_URL) response.raise_for_status() return response.text except requests.exceptions.RequestException as e: return f"Error: Unable to fetch data from URL. Details: {str(e)}"
- Similar handler function registered as a resource via @mcp.resource with URI 'videodb://doc_assistant'. Implements the same logic as the tool version.@mcp.resource( "videodb://doc_assistant", name="doc_assistant", description="Context for creating video applications using VideoDB", ) def doc_assistant() -> str: try: response = requests.get(DOCS_ASSISTANT_TXT_URL) response.raise_for_status() return response.text except requests.exceptions.RequestException as e: return f"Error: Unable to fetch data from URL. Details: {str(e)}"
- modelcontextprotocol/videodb_director_mcp/__init__.py:1-9 (registration)Package __init__.py that imports and exports 'doc_assistant' function, making it available for import from the package.from videodb_director_mcp.main import ( call_director, play_video, code_assistant, doc_assistant, ) __all__ = ["call_director", "play_video", "code_assistant", "doc_assistant"]
- Defines DOCS_ASSISTANT_TXT_URL constant used by the doc_assistant handler to fetch the documentation content.CODE_ASSISTANT_TXT_URL = "https://videodb.io/llms-full.txt" DOCS_ASSISTANT_TXT_URL = "https://video-db.github.io/agent-toolkit/context/docs/docs_context.md"