Skip to content
Scalekit Docs

Connect AI agents to the Mux MCP server

Vendor MCP2 toolsOAuth 2.1/DCRMediaDeveloper Tools

The Mux MCP connector routes your AI agent's tool calls to Mux's own MCP server through Scalekit. Each user signs in to Mux once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 2 tools.

  1. Terminal window
    npm install @scalekit-sdk/node dotenv

    Full SDK reference: Node.js | Python

  2. Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

    .env
    SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
    SCALEKIT_CLIENT_ID=<your-client-id>
    SCALEKIT_CLIENT_SECRET=<your-client-secret>
  3. quickstart.mts
    import { ScalekitClient } from '@scalekit-sdk/node'
    import 'dotenv/config'
    import { createInterface } from 'node:readline/promises'
    const scalekit = new ScalekitClient(
    process.env.SCALEKIT_ENVIRONMENT_URL,
    process.env.SCALEKIT_CLIENT_ID,
    process.env.SCALEKIT_CLIENT_SECRET,
    )
    const actions = scalekit.actions
    const connector = 'muxmcp'
    const identifier = 'user_123'
    // Generate an authorization link for the user
    const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
    console.log('Authorize Mux MCP:', link)
    const rl = createInterface({ input: process.stdin, output: process.stdout })
    await rl.question('Press Enter after authorizing...')
    rl.close()
    // Make your first call
    const result = await actions.executeTool({
    connector,
    identifier,
    toolName: 'muxmcp_search_docs',
    toolInput: { query: 'YOUR_QUERY', language: 'YOUR_LANGUAGE' },
    })
    console.log(result)
    Terminal window
    npx tsx quickstart.mts

Connect this agent connector to let your agent:

  • Search docs — Search SDK documentation to find methods, parameters, and usage examples for interacting with the API
  • Execute records — Runs JavaScript code to interact with the Mux API

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

muxmcp_execute#Runs JavaScript code to interact with the Mux API. Define an async function named "run" that takes a single parameter of an initialized SDK client. Returns anything the function returns plus console.log output. Code runs in a sandboxed container with no external network access beyond the Mux SDK client.2 params

Runs JavaScript code to interact with the Mux API. Define an async function named "run" that takes a single parameter of an initialized SDK client. Returns anything the function returns plus console.log output. Code runs in a sandboxed container with no external network access beyond the Mux SDK client.

NameTypeRequiredDescription
codestringrequiredCode to execute.
intentstringoptionalTask you are trying to perform. Used for improving the service.
muxmcp_search_docs#Search SDK documentation to find methods, parameters, and usage examples for interacting with the API. Use this before writing code when you need to discover the right approach.3 params

Search SDK documentation to find methods, parameters, and usage examples for interacting with the API. Use this before writing code when you need to discover the right approach.

NameTypeRequiredDescription
languagestringrequiredThe language for the SDK to search for.
querystringrequiredThe query to search for.
detailstringoptionalThe amount of detail to return.