Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

com.mux/mcp

NPM · @MUX/MCP · 2 COMPONENTS · SCANNED SEP 25

The official MCP Server for the Mux API

0 this week 71 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • Known CVEs were checked across the 142 of 143 dependencies we could resolve, so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Dependency health was assessed across the 142 of 143 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency23
Schema Quality & AI Usability49
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 47756 tokens (~487/item across 98 items; 98 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage92
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 76% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 10 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_playback_id_video_assets" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 98 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the com.mux/mcp server?

com.mux/mcp runs locally as an npm package, launched with npx -y @mux/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @mux/mcp

# add to Claude Code
claude mcp add com-mux-mcp -- npx -y @mux/mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "com-mux-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@mux/mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-mux-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@mux/mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add com-mux-mcp -- npx -y @mux/mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-mux-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@mux/mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-mux-mcp --command npx --arg -y --arg @mux/mcp
# ~/.hermes/config.yaml
mcp_servers:
  com-mux-mcp:
    command: "npx"
    args: ["-y", "@mux/mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-mux-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@mux/mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add com-mux-mcp -t stdio -c npx -a -y @mux/mcp
// mcp.json
{
  "mcpServers": {
    "com-mux-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@mux/mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 25 Sept 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 23 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 22 Sept 26 +2
    • Stability: 0.97 → pass security
    • Security disclosure: unverified → pass ▲ functional
  • 21 Sept 26 −1
    • Security disclosure: pass → unverified ▼ functional
  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 15 Sept 26 +1
    • Stability: 0.97 → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 25 Sept 2026 · Analysed npm/@mux/mcp@12.8.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 142 packages
Packages resolved 142
Deprecated 1
Stale 42
Tree resolution Partial

The dependency tree was only partially resolved, so these counts may be incomplete.

Background: SBOMs and build attestations, explained →

MCP tools · 98 exposed · ~47,756 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
update_video_transcription_vocabularies ~659

When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance. Only omit if you're sure you don't need the data. Updates the details of a previously-created Transcription Vocabulary. Updates to Transcription Vocabularies are allowed while associated live streams are active. However, updates will not be applied to those streams while they are active. # Response Schema ```json { $ref: '#/$defs/transcription_vocabulary_response', $defs: { transcription_vocabulary_response: { type: 'object', properties: { data: { $ref: '#/$defs/transcription_vocabulary' } }, required: [ 'data' ] }, transcription_vocabulary: { type: 'object', properties: { id: { type: 'string', description: 'Unique identifier for the Transcription Vocabulary' }, created_at: { type: 'string', description: 'Time the Transcription Vocabulary was created, defined as a Unix timestamp (seconds since epoch).' }, updated_at: { type: 'string', description: 'Time the Transcription Vocabulary was updated, defined as a Unix timestamp (seconds since epoch).' }, name: { type: 'string', description: 'The user-supplied name of the Transcription Vocabulary.' }, passthrough: { type: 'string', description: 'Arbitrary user-supplied metadata set for the Transcription Vocabulary. Max 255 characters.' }, phrases: { type: 'array', description: 'Phrases, individual words, or proper names to include in the Transcription Vocabulary. When the Transcription Vocabulary is attached to a live stream\'s `generated_subtitles` configuration, the probability of successful speech recognition for these words or phrases is boosted.', items: { type: 'string', descr…

NameTypeReqDescription
TRANSCRIPTION_VOCABULARY_IDstringyes–
jq_filterstring–A jq filter to apply to the response to include certain fields. Consult the output schema in the tool description to see the fields that are available. For example: to include only the `name` field…
namestring–The user-supplied name of the Transcription Vocabulary.
passthroughstring–Arbitrary user-supplied metadata set for the Transcription Vocabulary. Max 255 characters.
phrasesarrayyesPhrases, individual words, or proper names to include in the Transcription Vocabulary. When the Transcription Vocabulary is attached to a live stream's `generated_subtitles`, the probability of succe…

No output schema declared.

No examples provided.

whoami_system_utilities ~395

When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance. Only omit if you're sure you don't need the data. Retrieve information about your current access token, including organization, environment, and permissions. Note that this can only be access with an access token, and _all_ access tokens can access this route, regardless of what permissions they have assigned. # Response Schema ```json { $ref: '#/$defs/whoami_response', $defs: { whoami_response: { type: 'object', properties: { data: { type: 'object', properties: { access_token_name: { type: 'string' }, environment_id: { type: 'string' }, environment_name: { type: 'string' }, environment_type: { type: 'string' }, organization_id: { type: 'string' }, organization_name: { type: 'string' }, permissions: { type: 'array', items: { type: 'string' } } }, required: [ 'access_token_name', 'environment_id', 'environment_name', 'environment_type', 'organization_id', 'organization_name', 'permissions' ] } }, required: [ 'data' ] } } } ```

NameTypeReqDescription
jq_filterstring–A jq filter to apply to the response to include certain fields. Consult the output schema in the tool description to see the fields that are available. For example: to include only the `name` field…

No output schema declared.

No examples provided.

Common questions

What is the com.mux/mcp server?

com.mux/mcp is listed in the public MCP registry as com.mux/mcp. The official MCP Server for the Mux API. This page covers its npm package (@mux/mcp).

Is the com.mux/mcp server safe to use?

com.mux/mcp scores 71 out of 100 on VerifyMCP. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the com.mux/mcp server expose?

com.mux/mcp exposes 98 tools: create_video_assets, retrieve_video_assets, update_video_assets, list_video_assets, create_playback_id_video_assets, and 93 more. Their descriptions and schemas cost roughly 47,756 tokens of context every time the server is loaded.

Is the com.mux/mcp server still maintained?

com.mux/mcp is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the com.mux/mcp server under?

com.mux/mcp declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.