Mux

98 tools. 44 can modify or destroy data without limits.

12 destructive tools with no built-in limits. Policy required.

Last updated:

44 can modify or destroy data
54 read-only
98 tools total
Read (54) Write / Execute (32) Destructive / Financial (12)

Destructive tools (cancel_video_uploads, delete_data_annotations, delete_new_asset_settings_static_renditions_video_live_streams) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (complete_video_live_streams, create_data_annotations, create_playback_id_video_assets) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

One command. Full control.

Intercept sits between your agent and Mux. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @mux/mcp
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
Deny destructive operations
cancel_video_uploads:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
complete_video_live_streams:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
animated_video_playback:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

READ 54 tools
Read animated_video_playback Read get_breakdown_monitoring_data_metrics Read get_breakdown_timeseries_monitoring_data_metrics Read get_histogram_timeseries_monitoring_data_metrics Read get_insights_data_metrics Read get_overall_values_data_metrics Read get_timeseries_data_metrics Read get_timeseries_monitoring_data_metrics Read list_breakdown_values_data_metrics Read list_data_annotations Read list_data_dimensions Read list_data_errors Read list_data_incidents Read list_data_metrics Read list_data_video_views Read list_dimensions_data_monitoring Read list_dimensions_data_real_time Read list_metrics_data_real_time Read list_monitoring_data_metrics Read list_related_data_incidents Read list_system_signing_keys Read list_trace_elements_data_dimensions Read list_values_data_dimensions Read list_values_data_filters Read list_video_assets Read list_video_delivery_usage Read list_video_drm_configurations Read list_video_live_streams Read list_video_playback_restrictions Read list_video_transcription_vocabularies Read list_video_uploads Read list_video_views_data_exports Read retrieve_breakdown_data_real_time Read retrieve_data_annotations Read retrieve_data_incidents Read retrieve_data_video_views Read retrieve_histogram_timeseries_data_real_time Read retrieve_input_info_video_assets Read retrieve_playback_id_video_assets Read retrieve_playback_id_video_live_streams Read retrieve_simulcast_target_video_live_streams Read retrieve_system_signing_keys Read retrieve_timeseries_data_real_time Read retrieve_video_assets Read retrieve_video_drm_configurations Read retrieve_video_live_streams Read retrieve_video_playback_ids Read retrieve_video_playback_restrictions Read retrieve_video_transcription_vocabularies Read retrieve_video_uploads Read static_rendition_video_playback Read thumbnail_video_playback Read track_video_playback Read whoami_system_utilities
Can an AI agent delete data through the Mux MCP server? +

Yes. The Mux server exposes 12 destructive tools including cancel_video_uploads, delete_data_annotations, delete_new_asset_settings_static_renditions_video_live_streams. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Mux? +

The Mux server has 32 write tools including complete_video_live_streams, create_data_annotations, create_playback_id_video_assets. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the Mux MCP server expose? +

98 tools across 3 categories: Destructive, Read, Write. 54 are read-only. 44 can modify, create, or delete data.

How do I add Intercept to my Mux setup? +

One line change. Instead of running the Mux server directly, prefix it with Intercept: intercept -c com-mux-mcp.yaml -- npx -y @@mux/mcp. Download a pre-built policy from policylayer.com/policies/com-mux-mcp and adjust the limits to match your use case.

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init
Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.