api.video Multi-Tool Communication Protocol (MCP) Server for AI Agents - n8n Workflow

Advanced n8n Automation Specialists seeking high-tool-count integrations.
AI/LLM developers who need to equip their agents with comprehensive video management capabilities.
Organizations using api.video for live streaming, VOD, or delegated uploads.
Users looking for complex, scalable n8n templates for external APIs.

This sophisticated n8n workflow transforms the entire api.video platform into a seamless toolkit accessible by any AI agent supporting the Multi-Tool Communication Protocol (MCP). The power of this n8n template lies in its breadth, exposing 47 critical api.video operations, including account management, video creation, analytics retrieval, live stream controls, and webhook configuration.

While highly advanced, this n8n workflow offers unparalleled integration depth. Every function—from listing all videos to deleting a specific caption—is available as a distinct tool. By using a single n8n trigger point, AI agents can dynamically access this large suite of tools, significantly enhancing their ability to perform complex video operations without manual intervention. This specialized n8n setup is crucial for building next-generation media management agents.

The entire flow is orchestrated by the MCP architecture within n8n. The process begins with the central n8n trigger, the dedicated MCP Server node.

1. AI Request: An AI agent sends a request to the MCP server's URL, specifying the desired api.video operation (e.g., 'Create a video' or 'List live stream player sessions').


2. Tool Routing (n8n trigger): The MCP n8n trigger receives this request and intelligently routes the command to the corresponding specialized n8n node within the workflow (one of the 47 HTTP Request Tool nodes).


3. Dynamic Parameter Injection: The selected HTTP Request n8n node executes the API call. Crucially, required parameters (like videoId, streamKey, or period) are populated dynamically using the special $fromAI() expression. This allows the AI agent to pass necessary inputs directly through the n8n workflow.


4. API Execution: The n8n node executes the API call against the https://ws.api.video endpoint, ensuring authentication is handled via generic credentials.


5. Result Return: The response from api.video is captured by the n8n node and immediately returned back through the MCP trigger to the initiating AI agent, maintaining the original API structure for the AI to interpret and utilize.

To deploy and utilize this extensive n8n workflow, follow these steps:

1. Import the n8n template: Copy the provided JSON data and import it directly into your n8n instance using the 'New' -> 'Import from JSON' function.


2. Credential Setup: Although the workflow notes state "No authentication required" for the MCP client setup itself, the underlying HTTP Request nodes utilize genericCredentialType. You must configure a Generic Credential in n8n to handle HTTP Header Authentication for the api.video API key, which will be used by all 47 n8n nodes.


3. Activate the n8n Workflow: Save the n8n workflow and toggle it to 'Active' to start the MCP server.


4. Retrieve MCP URL: Click on the api.video MCP Server n8n trigger node and copy the generated Webhook URL (e.g., /webhook/api.video-mcp).


5. Connect AI Agent: Configure your AI agent (LLM) client using this MCP URL as the server endpoint. Ensure you selectively enable only the necessary tools, as advised in the workflow’s sticky note, to optimize performance when interacting with this complex n8n workflow.

api.video MCP Server (MCP Trigger): Acts as the single entry point and orchestrator for all AI agent requests. This specialized n8n trigger is what transforms the entire n8n workflow into an MCP tool server, listening for commands on the defined path (api.video-mcp).

HTTP Request Tool (47 Instances): These are the core functional n8n nodes. Each one corresponds to a specific api.video endpoint (e.g., List all videos, Create live stream, Show account).
Function: They execute the actual API calls (GET, POST, PATCH, DELETE) to https://ws.api.video.
Key Configuration: All tools utilize dynamic expressions (={{ $fromAI('parameterName', 'description', 'type') }}) within the URL path or query parameters. This ensures that the parameters required for the operation are extracted directly from the AI agent's request via the n8n workflow and injected into the correct API call location. They are also configured with a concise toolDescription for the AI model to understand the tool's purpose and required inputs.