Odysee Video Search by Keyword, Channel & Tag: MCP config, n8n workflow and API

{
  "mcpServers": {
    "odysee-video-search-by-keyword-channel-and-tag": {
      "command": "npx",
      "args": [
        "-y",
        "@apify/actors-mcp-server",
        "--tools",
        "fetch-actor-details,vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag"
      ],
      "env": {
        "APIFY_TOKEN": "YOUR_APIFY_TOKEN"
      }
    }
  }
}

{
  "mcpServers": {
    "odysee-video-search-by-keyword-channel-and-tag": {
      "url": "https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag",
      "headers": {
        "Authorization": "Bearer ${env:APIFY_TOKEN}"
      }
    }
  }
}

{
  "inputs": [
    {
      "type": "promptString",
      "id": "apify-token",
      "description": "Apify API token",
      "password": true
    }
  ],
  "servers": {
    "odysee-video-search-by-keyword-channel-and-tag": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag",
      "headers": {
        "Authorization": "Bearer ${input:apify-token}"
      }
    }
  }
}

https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag

[mcp_servers.odysee-video-search-by-keyword-channel-and-tag]
url = "https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag"
bearer_token_env_var = "APIFY_TOKEN"

gemini mcp add -t http -s user -H "Authorization: Bearer $APIFY_TOKEN" odysee-video-search-by-keyword-channel-and-tag "https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag"

https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag

curl -X POST "https://api.apify.com/v2/actors/vexaloom-labs~odysee-video-search-by-keyword-channel-and-tag/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"mode":"search","keyword":"open source","channel":"@veritasium","tag":"science","orderBy":"release_time","mediaType":"video","maxItems":3,"includeStats":true}'

import os
from apify_client import ApifyClient

client = ApifyClient(os.environ["APIFY_TOKEN"])
run_input = {
    "mode": "search",
    "keyword": "open source",
    "channel": "@veritasium",
    "tag": "science",
    "orderBy": "release_time",
    "mediaType": "video",
    "maxItems": 3,
    "includeStats": True,
}

run = client.actor("vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag").call(run_input=run_input)
if run is None:
    raise RuntimeError("The Actor run could not be started")
print(run.status, "dataset", run.default_dataset_id)
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

import { ApifyClient } from "apify-client";

const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const input = {
  "mode": "search",
  "keyword": "open source",
  "channel": "@veritasium",
  "tag": "science",
  "orderBy": "release_time",
  "mediaType": "video",
  "maxItems": 3,
  "includeStats": true
};

const run = await client.actor("vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag").call(input);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items.length, items[0]);

# Reads APIFY_TOKEN from the environment.
from langchain_apify import ApifyActorsTool

tool = ApifyActorsTool("vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag")
items = tool.invoke({"run_input": {
    "mode": "search",
    "keyword": "open source",
    "channel": "@veritasium",
    "tag": "science",
    "orderBy": "release_time",
    "mediaType": "video",
    "maxItems": 3,
    "includeStats": True,
}})
print(len(items), "records", items[:1])

# Give the same tool to an agent (pip install langchain langchain-openai):
# from langchain.agents import create_agent
# agent = create_agent(ChatOpenAI(model="gpt-5.4-mini"), [tool])

# Reads APIFY_API_TOKEN (Apify token) and OPENAI_API_KEY from the environment.
from crewai import Agent, Crew, Task
from crewai_tools import ApifyActorsTool

tool = ApifyActorsTool(actor_name="vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag")
agent = Agent(
    role="Data researcher",
    goal="Collect records with the Apify Actor and summarise them",
    backstory="You call Apify Actors to get live web data.",
    tools=[tool],
)
task = Task(
    description="Use Odysee Video Search by Keyword, Channel & Tag to get a few records and summarise what came back, with links. Call the tool with this run_input: {\"mode\":\"search\",\"keyword\":\"open source\",\"channel\":\"@veritasium\",\"tag\":\"science\",\"orderBy\":\"release_time\",\"mediaType\":\"video\",\"maxItems\":3,\"includeStats\":true}",
    agent=agent,
    expected_output="A short summary of the records with their links.",
)
print(Crew(agents=[agent], tasks=[task]).kickoff())

import json
import os

from llama_index.core import Document
from llama_index.readers.apify import ApifyActor

reader = ApifyActor(os.environ["APIFY_TOKEN"])
documents = reader.load_data(
    actor_id="vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag",
    run_input={
    "mode": "search",
    "keyword": "open source",
    "channel": "@veritasium",
    "tag": "science",
    "orderBy": "release_time",
    "mediaType": "video",
    "maxItems": 3,
    "includeStats": True,
},
    dataset_mapping_function=lambda item: Document(text=json.dumps(item), metadata={"url": item.get("viewUrl")}),
)
print(len(documents), "documents")

import asyncio
import os

from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp


async def main() -> None:
    async with MCPServerStreamableHttp(
        name="Apify",
        params={
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag",
            "headers": {"Authorization": f"Bearer {os.environ['APIFY_TOKEN']}"},
            "timeout": 120,
        },
        cache_tools_list=True,
    ) as server:
        tools = await server.list_tools()
        print("tools:", [t.name for t in tools])
        agent = Agent(name="Assistant", instructions="Use the Apify tools to get live data.", mcp_servers=[server])
        result = await Runner.run(agent, "Use Odysee Video Search by Keyword, Channel & Tag to get a few records and summarise what came back, with links.")
        print(result.final_output)


asyncio.run(main())

import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";

const mcp = new MCPClient({
  servers: {
    apify: {
      url: new URL("https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/odysee-video-search-by-keyword-channel-and-tag"),
      requestInit: { headers: { Authorization: `Bearer ${process.env.APIFY_TOKEN}` } },
    },
  },
  timeout: 300_000, // Actor runs can take minutes
});
const tools = await mcp.listTools();
console.log("tools:", Object.keys(tools));

const agent = new Agent({ id: "apify-agent", name: "Apify agent", instructions: "Use the Apify tools to get live data.", model: "openai/gpt-4o-mini", tools });
const result = await agent.generate("Use Odysee Video Search by Keyword, Channel & Tag to get a few records and summarise what came back, with links.");
console.log(result.text);
await mcp.disconnect();