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.

Content

PYPI · CONTENT-MCP · SCANNED SEP 20

Turn URLs, files and text into media, transcripts, summaries, translations and PDF.

Available components

+3 this week 78 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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 33 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency35
Schema Quality & AI Usability72
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1296 tokens (~117/item across 11 items; 11 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_upload" 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 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the Content MCP server?

Content runs locally as a PyPI package, launched with uvx content-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · content-mcp

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

  • 20 Sept 26 0
    • Stability: 0.97 → pass security
  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +16
    • Malware scan: unverified → pass security
  • 12 Sept 26 −15
    • Malware scan: pass → unverified security
    • Package version: 0.7.1 → 0.8.0 functional
  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 8 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

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 20 Sept 2026 · Analysed pypi/content-mcp@0.8.0

Provenance No attestation

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

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 33 packages
Packages resolved 33
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 11 exposed · ~802 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
analyze_source ~150

Analyze a source and report what can be produced from it. Accepts a URL, or **a path to a file on this machine** — the one this MCP server runs on. A local file is read and uploaded to the engine, which is the only way a file here becomes usable by an engine running elsewhere; the path is never assumed to exist on the engine's side. Over a network transport (streamable-http) local paths are refused outright rather than resolved: "this machine" would be the server's host, not the caller's, which is not what a path in a request means.

NameTypeReqDescription
credential
urlstringyes

Structured output declared, but exposes no named fields.

No examples provided.

cancel_job ~24

Request cooperative cancellation of a running job.

NameTypeReqDescription
job_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

delete_upload ~72

Delete bytes uploaded from this machine, before the TTL expires. `analyze_source` uploads a local file to the engine; the id it returns under `upload` is what this takes. Removes only that upload — never an artifact, never a file in the library.

NameTypeReqDescription
upload_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

download_artifact ~106

Save an artifact onto the machine running this MCP server. Use this when the user wants the file *here* rather than only in the engine's library — typically when the engine runs on another machine. `destination` is optional: omitted, the artifact keeps its own name in the server's download directory (CONTENT_MCP_DOWNLOAD_DIR, default ~/Downloads/Content). A path outside that directory is refused.

NameTypeReqDescription
artifact_idstringyes
destination

Structured output declared, but exposes no named fields.

No examples provided.

generate ~166

Start a job producing the requested outputs from an analyzed source. Each output is either a type string — ["video", "subtitles"] — or an object. Per-output settings go under "options", never beside "type": {"type": "subtitles", "options": {"languages": ["es"]}} {"type": "video", "options": {"selection": {"max_height": 1080}}, "delivery": {"mode": "deliver", "folder": "Talks"}} Other keys of an output object: id, from_sources, from_outputs, scope ("single" or "each_item" for a collection), required. An unknown key is refused rather than ignored.

NameTypeReqDescription
analysis_idstringyes
outputsarrayyes

Structured output declared, but exposes no named fields.

No examples provided.

get_artifact ~43

Artifact metadata; small text artifacts are inlined, larger/binary ones return a download reference (never raw bytes over MCP).

NameTypeReqDescription
artifact_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

get_config ~36

Server-side context for building requests: credential ids for authenticated sources, whether delivery-by-default is on, and the existing library folders.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

get_job ~79

Get a job's status and, once terminal, its produced artifacts. Carries `poll_after`: seconds to wait before calling this again — a heuristic (grows with elapsed time and the kind of work the job is doing), not a promise, and `null` once the job is terminal.

NameTypeReqDescription
job_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

list_capabilities ~27

Resolve the public capabilities available for an analyzed source.

NameTypeReqDescription
analysis_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

list_jobs ~23

List recent jobs (most recent first).

NameTypeReqDescription
limitinteger

Structured output declared, but exposes no named fields.

No examples provided.

retry_job ~76

Run a finished job's request again, as a new job. Re-runs the *whole* request: a playlist where one member failed re-downloads every member. Worth it for a transient failure, wasteful for a large collection — read the failure in `get_job` first.

NameTypeReqDescription
job_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the Content MCP server?

Content is an MCP server listed in the public MCP registry as io.github.LatentNoise/content. Turn URLs, files and text into media, transcripts, summaries, translations and PDF. This page covers its PyPI package (content-mcp).

Is the Content MCP server safe to use?

Content scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 Content MCP server expose?

Content exposes 11 tools: analyze_source, list_capabilities, generate, get_job, cancel_job, and 6 more. Their descriptions and schemas cost roughly 802 tokens of context every time the server is loaded.

Is the Content MCP server still maintained?

Content is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.