The server itself exposes 2 tools, and some of them can write to your Mux account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Mux.

How is this different from connecting Mux MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Mux MCP API changes?

We track the Mux MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Mux tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Mux?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Mux MCP server myself?

No. TrustGate connects to the Mux MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Mux directly.

Connect Mux MCP to your AI agents, securely.

One secured endpoint for every Mux call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Mux MCP now

What your agents can ask once Mux MCP is connected.

Select the tools your AI agents can call

2 tools from the Mux MCP schema.

Showing 2 tools

executehigh riskRuns TypeScript the agent writes against the full @mux/ts SDK, returning whatever the code returns or prints. On the hosted server each call runs in a fresh, isolated Mux-owned sandbox with network access limited to Mux API hosts. The server does not treat destructive operations specially.
search_docsreadQueries documentation about Mux's API and SDKs.

What Mux MCP exposes

Mux MCP groups its 2 tools into 2 categories, each with a suggested starting policy.

All 2 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Execution	Running TypeScript the agent writes against the full @mux/ts SDK. This reaches Mux Video (assets, direct uploads, playback IDs, tracks, live streams, delivery usage), Mux Data (metrics, dimensions, filters, real-time data, video views, exports), Mux Robots (jobs, workflows, directives), signing keys and account utilities, and webhook verification	Read / Write	One tool name covers the entire SDK, so filtering by tool name tells you nothing about what a call does. Authorize with a Read-only access token, or run the server locally where SDK methods can be restricted
Documentation	Querying documentation about Mux's API and SDKs	Read	Read-only and account-independent; the agent calls it to learn how to write the code it will then execute

Connect Mux MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Mux
Find Mux in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Mux MCP or block it. You allow the exact tools each agent can call, one by one.

Mux MCP	2 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 2 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Mux MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Mux MCP2 tools. The Code Mode pattern: one tool name stands in for the entire Mux SDK.
Coding assistants	Connection & credentialsper user	Execution1 tool
Internal copilots	Tool access policiesdeny by default	Documentation1 tool
Workflow automations	Request & response inspectioninline
Compatible MCP clients	Activity monitoringalerts and logs