Mux MCP integration for AI agents.
Connect AI agents to Mux through 11 structured actions, including get asset, create asset, and cancel direct upload. Review authentication, inputs, workflows…
- ACTION CONTRACTS
- 11
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Mux integration exposes
The Mux Agent App exposes 11 provider-backed actions for video and developer tools work. Its current contract lets an authorized agent retrieve the latest processing state and media details for one mux video asset, create a mux on-demand video asset from a publicly accessible media url and return its initial processing state, and cancel a waiting mux direct upload so that a later upload cannot create an asset. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Mux account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Mux capabilities.
Showing 11 of 11 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_assetREADRetrieve the latest processing state and media details for one Mux video asset.
INPUTS: assetId
create_assetWRITECreate a Mux on-demand video asset from a publicly accessible media URL and return its initial processing state.
INPUTS: sourceUrl / playbackPolicies / videoQuality / maxResolutionTier / passthrough
cancel_direct_uploadHIGH IMPACTCancel a waiting Mux Direct Upload so that a later upload cannot create an asset.
INPUTS: uploadId
create_direct_uploadWRITECreate a signed Mux Direct Upload URL for client-side or server-side media ingest without proxying video bytes through the connector.
INPUTS: corsOrigin / newAssetSettings / test / timeout
create_playback_idWRITECreate a public, signed, or DRM playback ID for an existing Mux video asset.
delete_assetHIGH IMPACTPermanently delete a Mux video asset and all of its data.
INPUTS: assetId
get_direct_uploadREADRetrieve the status, signed URL, and resulting asset ID for a Mux Direct Upload.
INPUTS: uploadId
get_playback_idREADResolve a Mux playback ID to the asset or live stream it belongs to and its access policy.
INPUTS: playbackId
list_assetsREADList Mux video assets with cursor or page-based pagination and optional source filters.
INPUTS: limit / page / cursor / liveStreamId / uploadId
list_direct_uploadsREADList Mux Direct Uploads in the current environment, including waiting and completed uploads.
INPUTS: limit / page
update_assetWRITEUpdate the passthrough value or customer metadata for an existing Mux video asset.
INPUTS: assetId / passthrough / meta
INPUT CONTRACTS
Know what the action needs before it runs.
get_asset
assetIdREQUIRED- The Mux asset ID.
create_asset
sourceUrlREQUIRED- A publicly accessible HTTP(S) URL that Mux can download as the primary media input.
playbackPoliciesOPTIONAL- Playback policies to create with the asset. Omit this field to create an asset without a playback ID.
videoQualityOPTIONAL- The cost and encoding-quality tier. Mux uses the environment default when omitted.
maxResolutionTierOPTIONAL- The maximum resolution tier Mux should produce.
passthroughOPTIONAL- Opaque metadata returned in asset details and related webhooks.
cancel_direct_upload
uploadIdREQUIRED- The Mux Direct Upload ID.
create_direct_upload
corsOriginREQUIRED- The browser origin that will use the signed upload URL, or * for any origin.
newAssetSettingsOPTIONAL- Asset settings applied after a direct upload completes.
testOPTIONAL- Whether to create a free, watermarked test upload.
timeoutOPTIONAL- How long the signed upload URL remains valid, in seconds.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Asset
Retrieve the latest processing state and media details for one Mux video asset. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_assetControl Create Asset
Create a Mux on-demand video asset from a publicly accessible media URL and return its initial processing state. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_assetVerify with Get Direct Upload
Retrieve the status, signed URL, and resulting asset ID for a Mux Direct Upload. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_direct_uploadSAFETY BOUNDARY
Operate Mux with explicit limits
- Authorize Mux with API key and grant only the provider access required by the selected actions.
- 6 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `cancel_direct_upload` and `delete_asset` as high-impact operations and require an explicit approval boundary.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Mux rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Mux task completed successfully.
CONNECTION MODEL
API key
Mux access token secret used as the HTTP Basic Auth password. Create a token in the Mux Dashboard under Settings > Access Tokens: https://dashboard.mux.com/settings/access-tokens.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 5
- WRITE SIGNALS
- 4
- HIGH IMPACT
- 2
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Mux.